flowise@3.0.11

README.md

@@ -189,7 +189,7 @@ Deploy Flowise self-hosted in your existing infrastructure, we support various [
     -   [Railway](https://docs.flowiseai.com/configuration/deployment/railway)
 
         [![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/template/pn4G8S?referralCode=WVNPD9)
-
+        
     -   [Northflank](https://northflank.com/stacks/deploy-flowiseai)
 
         [![Deploy to Northflank](https://assets.northflank.com/deploy_to_northflank_smm_36700fb050.svg)](https://northflank.com/stacks/deploy-flowiseai)

SECURITY.md

@@ -1,38 +1,38 @@
-### Responsible Disclosure Policy
+### Responsible Disclosure Policy  
 
-At Flowise, we prioritize security and continuously work to safeguard our systems. However, vulnerabilities can still exist. If you identify a security issue, please report it to us so we can address it promptly. Your cooperation helps us better protect our platform and users.
+At Flowise, we prioritize security and continuously work to safeguard our systems. However, vulnerabilities can still exist. If you identify a security issue, please report it to us so we can address it promptly. Your cooperation helps us better protect our platform and users.  
 
-### Out of scope vulnerabilities
+### Out of scope vulnerabilities  
 
--   Clickjacking on pages without sensitive actions
+- Clickjacking on pages without sensitive actions  
--   CSRF on unauthenticated/logout/login pages
+- CSRF on unauthenticated/logout/login pages  
--   Attacks requiring MITM (Man-in-the-Middle) or physical device access
+- Attacks requiring MITM (Man-in-the-Middle) or physical device access  
--   Social engineering attacks
+- Social engineering attacks  
--   Activities that cause service disruption (DoS)
+- Activities that cause service disruption (DoS)  
--   Content spoofing and text injection without a valid attack vector
+- Content spoofing and text injection without a valid attack vector  
--   Email spoofing
+- Email spoofing  
--   Absence of DNSSEC, CAA, CSP headers
+- Absence of DNSSEC, CAA, CSP headers  
--   Missing Secure or HTTP-only flag on non-sensitive cookies
+- Missing Secure or HTTP-only flag on non-sensitive cookies  
--   Deadlinks
+- Deadlinks  
--   User enumeration
+- User enumeration  
 
-### Reporting Guidelines
+### Reporting Guidelines  
 
--   Submit your findings to https://github.com/FlowiseAI/Flowise/security
+- Submit your findings to https://github.com/FlowiseAI/Flowise/security
--   Provide clear details to help us reproduce and fix the issue quickly.
+- Provide clear details to help us reproduce and fix the issue quickly.  
 
-### Disclosure Guidelines
+### Disclosure Guidelines  
 
--   Do not publicly disclose vulnerabilities until we have assessed, resolved, and notified affected users.
+- Do not publicly disclose vulnerabilities until we have assessed, resolved, and notified affected users.  
--   If you plan to present your research (e.g., at a conference or in a blog), share a draft with us at least **30 days in advance** for review.
+- If you plan to present your research (e.g., at a conference or in a blog), share a draft with us at least **30 days in advance** for review.  
--   Avoid including:
+- Avoid including:  
-    -   Data from any Flowise customer projects
+  - Data from any Flowise customer projects  
-    -   Flowise user/customer information
+  - Flowise user/customer information  
-    -   Details about Flowise employees, contractors, or partners
+  - Details about Flowise employees, contractors, or partners  
 
-### Response to Reports
+### Response to Reports  
 
--   We will acknowledge your report within **5 business days** and provide an estimated resolution timeline.
+- We will acknowledge your report within **5 business days** and provide an estimated resolution timeline.  
--   Your report will be kept **confidential**, and your details will not be shared without your consent.
+- Your report will be kept **confidential**, and your details will not be shared without your consent.
-
+  
-We appreciate your efforts in helping us maintain a secure platform and look forward to working together to resolve any issues responsibly.
+We appreciate your efforts in helping us maintain a secure platform and look forward to working together to resolve any issues responsibly.  

package.json

@@ -1,6 +1,6 @@
 {
     "name": "flowise",
-    "version": "3.0.11",
+    "version": "10",
     "private": true,
     "homepage": "https://flowiseai.com",
     "workspaces": [
@@ -51,7 +51,7 @@
         "eslint-plugin-react-hooks": "^4.6.0",
         "eslint-plugin-unused-imports": "^2.0.0",
         "husky": "^8.0.1",
-        "kill-port": "2.0.1",
+        "kill-port": "^2.0.1",
         "lint-staged": "^13.0.3",
         "prettier": "^2.7.1",
         "pretty-quick": "^3.1.3",

packages/components/models.json

@@ -3,13 +3,6 @@
         {
             "name": "awsChatBedrock",
             "models": [
-                {
-                    "label": "anthropic.claude-opus-4-5-20251101-v1:0",
-                    "name": "anthropic.claude-opus-4-5-20251101-v1:0",
-                    "description": "Claude 4.5 Opus",
-                    "input_cost": 0.000005,
-                    "output_cost": 0.000025
-                },
                 {
                     "label": "anthropic.claude-sonnet-4-5-20250929-v1:0",
                     "name": "anthropic.claude-sonnet-4-5-20250929-v1:0",
@@ -322,12 +315,6 @@
         {
             "name": "azureChatOpenAI",
             "models": [
-                {
-                    "label": "gpt-5.1",
-                    "name": "gpt-5.1",
-                    "input_cost": 0.00000125,
-                    "output_cost": 0.00001
-                },
                 {
                     "label": "gpt-5",
                     "name": "gpt-5",
@@ -512,13 +499,6 @@
         {
             "name": "chatAnthropic",
             "models": [
-                {
-                    "label": "claude-opus-4-5",
-                    "name": "claude-opus-4-5",
-                    "description": "Claude 4.5 Opus",
-                    "input_cost": 0.000005,
-                    "output_cost": 0.000025
-                },
                 {
                     "label": "claude-sonnet-4-5",
                     "name": "claude-sonnet-4-5",
@@ -641,18 +621,6 @@
         {
             "name": "chatGoogleGenerativeAI",
             "models": [
-                {
-                    "label": "gemini-3-pro-preview",
-                    "name": "gemini-3-pro-preview",
-                    "input_cost": 0.00002,
-                    "output_cost": 0.00012
-                },
-                {
-                    "label": "gemini-3-pro-image-preview",
-                    "name": "gemini-3-pro-image-preview",
-                    "input_cost": 0.00002,
-                    "output_cost": 0.00012
-                },
                 {
                     "label": "gemini-2.5-pro",
                     "name": "gemini-2.5-pro",
@@ -665,12 +633,6 @@
                     "input_cost": 1.25e-6,
                     "output_cost": 0.00001
                 },
-                {
-                    "label": "gemini-2.5-flash-image",
-                    "name": "gemini-2.5-flash-image",
-                    "input_cost": 1.25e-6,
-                    "output_cost": 0.00001
-                },
                 {
                     "label": "gemini-2.5-flash-lite",
                     "name": "gemini-2.5-flash-lite",
@@ -723,12 +685,6 @@
         {
             "name": "chatGoogleVertexAI",
             "models": [
-                {
-                    "label": "gemini-3-pro-preview",
-                    "name": "gemini-3-pro-preview",
-                    "input_cost": 0.00002,
-                    "output_cost": 0.00012
-                },
                 {
                     "label": "gemini-2.5-pro",
                     "name": "gemini-2.5-pro",
@@ -795,13 +751,6 @@
                     "input_cost": 1.25e-7,
                     "output_cost": 3.75e-7
                 },
-                {
-                    "label": "claude-opus-4-5@20251101",
-                    "name": "claude-opus-4-5@20251101",
-                    "description": "Claude 4.5 Opus",
-                    "input_cost": 0.000005,
-                    "output_cost": 0.000025
-                },
                 {
                     "label": "claude-sonnet-4-5@20250929",
                     "name": "claude-sonnet-4-5@20250929",
@@ -1047,12 +996,6 @@
         {
             "name": "chatOpenAI",
             "models": [
-                {
-                    "label": "gpt-5.1",
-                    "name": "gpt-5.1",
-                    "input_cost": 0.00000125,
-                    "output_cost": 0.00001
-                },
                 {
                     "label": "gpt-5",
                     "name": "gpt-5",

packages/components/nodes/agentflow/Agent/Agent.ts

@@ -22,16 +22,15 @@ import zodToJsonSchema from 'zod-to-json-schema'
 import { getErrorMessage } from '../../../src/error'
 import { DataSource } from 'typeorm'
 import {
-    addImageArtifactsToMessages,
-    extractArtifactsFromResponse,
     getPastChatHistoryImageMessages,
     getUniqueImageMessages,
     processMessagesWithImages,
     replaceBase64ImagesWithFileReferences,
-    replaceInlineDataWithFileReferences,
     updateFlowState
 } from '../utils'
-import { convertMultiOptionsToStringArray, processTemplateVariables, configureStructuredOutput } from '../../../src/utils'
+import { convertMultiOptionsToStringArray, getCredentialData, getCredentialParam, processTemplateVariables } from '../../../src/utils'
+import { addSingleFileToStorage } from '../../../src/storageUtils'
+import fetch from 'node-fetch'
 
 interface ITool {
     agentSelectedTool: string
@@ -82,7 +81,7 @@ class Agent_Agentflow implements INode {
     constructor() {
         this.label = 'Agent'
         this.name = 'agentAgentflow'
-        this.version = 3.2
+        this.version = 2.2
         this.type = 'Agent'
         this.category = 'Agent Flows'
         this.description = 'Dynamically choose and utilize tools during runtime, enabling multi-step reasoning'
@@ -177,11 +176,6 @@ class Agent_Agentflow implements INode {
                         label: 'Google Search',
                         name: 'googleSearch',
                         description: 'Search real-time web content'
-                    },
-                    {
-                        label: 'Code Execution',
-                        name: 'codeExecution',
-                        description: 'Write and run Python code in a sandboxed environment'
                     }
                 ],
                 show: {
@@ -400,108 +394,6 @@ class Agent_Agentflow implements INode {
                 ],
                 default: 'userMessage'
             },
-            {
-                label: 'JSON Structured Output',
-                name: 'agentStructuredOutput',
-                description: 'Instruct the Agent to give output in a JSON structured schema',
-                type: 'array',
-                optional: true,
-                acceptVariable: true,
-                array: [
-                    {
-                        label: 'Key',
-                        name: 'key',
-                        type: 'string'
-                    },
-                    {
-                        label: 'Type',
-                        name: 'type',
-                        type: 'options',
-                        options: [
-                            {
-                                label: 'String',
-                                name: 'string'
-                            },
-                            {
-                                label: 'String Array',
-                                name: 'stringArray'
-                            },
-                            {
-                                label: 'Number',
-                                name: 'number'
-                            },
-                            {
-                                label: 'Boolean',
-                                name: 'boolean'
-                            },
-                            {
-                                label: 'Enum',
-                                name: 'enum'
-                            },
-                            {
-                                label: 'JSON Array',
-                                name: 'jsonArray'
-                            }
-                        ]
-                    },
-                    {
-                        label: 'Enum Values',
-                        name: 'enumValues',
-                        type: 'string',
-                        placeholder: 'value1, value2, value3',
-                        description: 'Enum values. Separated by comma',
-                        optional: true,
-                        show: {
-                            'agentStructuredOutput[$index].type': 'enum'
-                        }
-                    },
-                    {
-                        label: 'JSON Schema',
-                        name: 'jsonSchema',
-                        type: 'code',
-                        placeholder: `{
-    "answer": {
-        "type": "string",
-        "description": "Value of the answer"
-    },
-    "reason": {
-        "type": "string",
-        "description": "Reason for the answer"
-    },
-    "optional": {
-        "type": "boolean"
-    },
-    "count": {
-        "type": "number"
-    },
-    "children": {
-        "type": "array",
-        "items": {
-            "type": "object",
-            "properties": {
-                "value": {
-                    "type": "string",
-                    "description": "Value of the children's answer"
-                }
-            }
-        }
-    }
-}`,
-                        description: 'JSON schema for the structured output',
-                        optional: true,
-                        hideCodeExecute: true,
-                        show: {
-                            'agentStructuredOutput[$index].type': 'jsonArray'
-                        }
-                    },
-                    {
-                        label: 'Description',
-                        name: 'description',
-                        type: 'string',
-                        placeholder: 'Description of the key'
-                    }
-                ]
-            },
             {
                 label: 'Update Flow State',
                 name: 'agentUpdateState',
@@ -514,7 +406,8 @@ class Agent_Agentflow implements INode {
                         label: 'Key',
                         name: 'key',
                         type: 'asyncOptions',
-                        loadMethod: 'listRuntimeStateKeys'
+                        loadMethod: 'listRuntimeStateKeys',
+                        freeSolo: true
                     },
                     {
                         label: 'Value',
@@ -877,7 +770,6 @@ class Agent_Agentflow implements INode {
             const memoryType = nodeData.inputs?.agentMemoryType as string
             const userMessage = nodeData.inputs?.agentUserMessage as string
             const _agentUpdateState = nodeData.inputs?.agentUpdateState
-            const _agentStructuredOutput = nodeData.inputs?.agentStructuredOutput
             const agentMessages = (nodeData.inputs?.agentMessages as unknown as ILLMMessage[]) ?? []
 
             // Extract runtime state and history
@@ -903,8 +795,6 @@ class Agent_Agentflow implements INode {
             const llmWithoutToolsBind = (await newLLMNodeInstance.init(newNodeData, '', options)) as BaseChatModel
             let llmNodeInstance = llmWithoutToolsBind
 
-            const isStructuredOutput = _agentStructuredOutput && Array.isArray(_agentStructuredOutput) && _agentStructuredOutput.length > 0
-
             const agentToolsBuiltInOpenAI = convertMultiOptionsToStringArray(nodeData.inputs?.agentToolsBuiltInOpenAI)
             if (agentToolsBuiltInOpenAI && agentToolsBuiltInOpenAI.length > 0) {
                 for (const tool of agentToolsBuiltInOpenAI) {
@@ -1063,7 +953,7 @@ class Agent_Agentflow implements INode {
             // Initialize response and determine if streaming is possible
             let response: AIMessageChunk = new AIMessageChunk('')
             const isLastNode = options.isLastNode as boolean
-            const isStreamable = isLastNode && options.sseStreamer !== undefined && modelConfig?.streaming !== false && !isStructuredOutput
+            const isStreamable = isLastNode && options.sseStreamer !== undefined && modelConfig?.streaming !== false
 
             // Start analytics
             if (analyticHandlers && options.parentTraceIds) {
@@ -1071,6 +961,12 @@ class Agent_Agentflow implements INode {
                 llmIds = await analyticHandlers.onLLMStart(llmLabel, messages, options.parentTraceIds)
             }
 
+            // Track execution time
+            const startTime = Date.now()
+
+            // Get initial response from LLM
+            const sseStreamer: IServerSideEventStreamer | undefined = options.sseStreamer
+
             // Handle tool calls with support for recursion
             let usedTools: IUsedTool[] = []
             let sourceDocuments: Array<any> = []
@@ -1083,24 +979,12 @@ class Agent_Agentflow implements INode {
             const messagesBeforeToolCalls = [...messages]
             let _toolCallMessages: BaseMessageLike[] = []
 
-            /**
-             * Add image artifacts from previous assistant responses as user messages
-             * Images are converted from FILE-STORAGE::<image_path> to base 64 image_url format
-             */
-            await addImageArtifactsToMessages(messages, options)
-
             // Check if this is hummanInput for tool calls
             const _humanInput = nodeData.inputs?.humanInput
             const humanInput: IHumanInput = typeof _humanInput === 'string' ? JSON.parse(_humanInput) : _humanInput
             const humanInputAction = options.humanInputAction
             const iterationContext = options.iterationContext
 
-            // Track execution time
-            const startTime = Date.now()
-
-            // Get initial response from LLM
-            const sseStreamer: IServerSideEventStreamer | undefined = options.sseStreamer
-
             if (humanInput) {
                 if (humanInput.type !== 'proceed' && humanInput.type !== 'reject') {
                     throw new Error(`Invalid human input type. Expected 'proceed' or 'reject', but got '${humanInput.type}'`)
@@ -1118,8 +1002,7 @@ class Agent_Agentflow implements INode {
                     llmWithoutToolsBind,
                     isStreamable,
                     isLastNode,
-                    iterationContext,
+                    iterationContext
-                    isStructuredOutput
                 })
 
                 response = result.response
@@ -1148,14 +1031,7 @@ class Agent_Agentflow implements INode {
                 }
             } else {
                 if (isStreamable) {
-                    response = await this.handleStreamingResponse(
+                    response = await this.handleStreamingResponse(sseStreamer, llmNodeInstance, messages, chatId, abortController)
-                        sseStreamer,
-                        llmNodeInstance,
-                        messages,
-                        chatId,
-                        abortController,
-                        isStructuredOutput
-                    )
                 } else {
                     response = await llmNodeInstance.invoke(messages, { signal: abortController?.signal })
                 }
@@ -1177,8 +1053,7 @@ class Agent_Agentflow implements INode {
                     llmNodeInstance,
                     isStreamable,
                     isLastNode,
-                    iterationContext,
+                    iterationContext
-                    isStructuredOutput
                 })
 
                 response = result.response
@@ -1205,20 +1080,11 @@ class Agent_Agentflow implements INode {
                         sseStreamer.streamArtifactsEvent(chatId, flatten(artifacts))
                     }
                 }
-            } else if (!humanInput && !isStreamable && isLastNode && sseStreamer && !isStructuredOutput) {
+            } else if (!humanInput && !isStreamable && isLastNode && sseStreamer) {
                 // Stream whole response back to UI if not streaming and no tool calls
-                // Skip this if structured output is enabled - it will be streamed after conversion
                 let finalResponse = ''
                 if (response.content && Array.isArray(response.content)) {
-                    finalResponse = response.content
+                    finalResponse = response.content.map((item: any) => item.text).join('\n')
-                        .map((item: any) => {
-                            if ((item.text && !item.type) || (item.type === 'text' && item.text)) {
-                                return item.text
-                            }
-                            return ''
-                        })
-                        .filter((text: string) => text)
-                        .join('\n')
                 } else if (response.content && typeof response.content === 'string') {
                     finalResponse = response.content
                 } else {
@@ -1247,53 +1113,9 @@ class Agent_Agentflow implements INode {
             // Prepare final response and output object
             let finalResponse = ''
             if (response.content && Array.isArray(response.content)) {
-                // Process items and concatenate consecutive text items
+                finalResponse = response.content.map((item: any) => item.text).join('\n')
-                const processedParts: string[] = []
-                let currentTextBuffer = ''
-
-                for (const item of response.content) {
-                    const itemAny = item as any
-                    const isTextItem = (itemAny.text && !itemAny.type) || (itemAny.type === 'text' && itemAny.text)
-
-                    if (isTextItem) {
-                        // Accumulate consecutive text items
-                        currentTextBuffer += itemAny.text
-                    } else {
-                        // Flush accumulated text before processing other types
-                        if (currentTextBuffer) {
-                            processedParts.push(currentTextBuffer)
-                            currentTextBuffer = ''
-                        }
-
-                        // Process non-text items
-                        if (itemAny.type === 'executableCode' && itemAny.executableCode) {
-                            // Format executable code as a code block
-                            const language = itemAny.executableCode.language?.toLowerCase() || 'python'
-                            processedParts.push(`\n\`\`\`${language}\n${itemAny.executableCode.code}\n\`\`\`\n`)
-                        } else if (itemAny.type === 'codeExecutionResult' && itemAny.codeExecutionResult) {
-                            // Format code execution result
-                            const outcome = itemAny.codeExecutionResult.outcome || 'OUTCOME_OK'
-                            const output = itemAny.codeExecutionResult.output || ''
-                            if (outcome === 'OUTCOME_OK' && output) {
-                                processedParts.push(`**Code Output:**\n\`\`\`\n${output}\n\`\`\`\n`)
-                            } else if (outcome !== 'OUTCOME_OK') {
-                                processedParts.push(`**Code Execution Error:**\n\`\`\`\n${output}\n\`\`\`\n`)
-                            }
-                        }
-                    }
-                }
-
-                // Flush any remaining text
-                if (currentTextBuffer) {
-                    processedParts.push(currentTextBuffer)
-                }
-
-                finalResponse = processedParts.filter((text) => text).join('\n')
             } else if (response.content && typeof response.content === 'string') {
                 finalResponse = response.content
-            } else if (response.content === '') {
-                // Empty response content, this could happen when there is only image data
-                finalResponse = ''
             } else {
                 finalResponse = JSON.stringify(response, null, 2)
             }
@@ -1309,13 +1131,10 @@ class Agent_Agentflow implements INode {
                 }
             }
 
-            // Extract artifacts from annotations in response metadata and replace inline data
+            // Extract artifacts from annotations in response metadata
             if (response.response_metadata) {
-                const {
+                const { artifacts: extractedArtifacts, fileAnnotations: extractedFileAnnotations } =
-                    artifacts: extractedArtifacts,
+                    await this.extractArtifactsFromResponse(response.response_metadata, newNodeData, options)
-                    fileAnnotations: extractedFileAnnotations,
-                    savedInlineImages
-                } = await extractArtifactsFromResponse(response.response_metadata, newNodeData, options)
                 if (extractedArtifacts.length > 0) {
                     artifacts = [...artifacts, ...extractedArtifacts]
 
@@ -1333,11 +1152,6 @@ class Agent_Agentflow implements INode {
                         sseStreamer.streamFileAnnotationsEvent(chatId, fileAnnotations)
                     }
                 }
-
-                // Replace inlineData base64 with file references in the response
-                if (savedInlineImages && savedInlineImages.length > 0) {
-                    replaceInlineDataWithFileReferences(response, savedInlineImages)
-                }
             }
 
             // Replace sandbox links with proper download URLs. Example: [Download the script](sandbox:/mnt/data/dummy_bar_graph.py)
@@ -1345,23 +1159,6 @@ class Agent_Agentflow implements INode {
                 finalResponse = await this.processSandboxLinks(finalResponse, options.baseURL, options.chatflowid, chatId)
             }
 
-            // If is structured output, then invoke LLM again with structured output at the very end after all tool calls
-            if (isStructuredOutput) {
-                llmNodeInstance = configureStructuredOutput(llmNodeInstance, _agentStructuredOutput)
-                const prompt = 'Convert the following response to the structured output format: ' + finalResponse
-                response = await llmNodeInstance.invoke(prompt, { signal: abortController?.signal })
-
-                if (typeof response === 'object') {
-                    finalResponse = '```json\n' + JSON.stringify(response, null, 2) + '\n```'
-                } else {
-                    finalResponse = response
-                }
-
-                if (isLastNode && sseStreamer) {
-                    sseStreamer.streamTokenEvent(chatId, finalResponse)
-                }
-            }
-
             const output = this.prepareOutputObject(
                 response,
                 availableTools,
@@ -1374,8 +1171,7 @@ class Agent_Agentflow implements INode {
                 artifacts,
                 additionalTokens,
                 isWaitingForHumanInput,
-                fileAnnotations,
+                fileAnnotations
-                isStructuredOutput
             )
 
             // End analytics tracking
@@ -1396,15 +1192,9 @@ class Agent_Agentflow implements INode {
             // Process template variables in state
             newState = processTemplateVariables(newState, finalResponse)
 
-            /**
-             * Remove the temporarily added image artifact messages before storing
-             * This is to avoid storing the actual base64 data into database
-             */
-            const messagesToStore = messages.filter((msg: any) => !msg._isTemporaryImageMessage)
-
             // Replace the actual messages array with one that includes the file references for images instead of base64 data
             const messagesWithFileReferences = replaceBase64ImagesWithFileReferences(
-                messagesToStore,
+                messages,
                 runtimeImageMessagesWithFileRef,
                 pastImageMessagesWithFileRef
             )
@@ -1543,12 +1333,7 @@ class Agent_Agentflow implements INode {
         // Handle Gemini googleSearch tool
         if (groundingMetadata && groundingMetadata.webSearchQueries && Array.isArray(groundingMetadata.webSearchQueries)) {
             // Check for duplicates
-            const isDuplicate = builtInUsedTools.find(
+            if (!builtInUsedTools.find((tool) => tool.tool === 'googleSearch')) {
-                (tool) =>
-                    tool.tool === 'googleSearch' &&
-                    JSON.stringify((tool.toolInput as any)?.queries) === JSON.stringify(groundingMetadata.webSearchQueries)
-            )
-            if (!isDuplicate) {
                 builtInUsedTools.push({
                     tool: 'googleSearch',
                     toolInput: {
@@ -1562,12 +1347,7 @@ class Agent_Agentflow implements INode {
         // Handle Gemini urlContext tool
         if (urlContextMetadata && urlContextMetadata.urlMetadata && Array.isArray(urlContextMetadata.urlMetadata)) {
             // Check for duplicates
-            const isDuplicate = builtInUsedTools.find(
+            if (!builtInUsedTools.find((tool) => tool.tool === 'urlContext')) {
-                (tool) =>
-                    tool.tool === 'urlContext' &&
-                    JSON.stringify((tool.toolInput as any)?.urlMetadata) === JSON.stringify(urlContextMetadata.urlMetadata)
-            )
-            if (!isDuplicate) {
                 builtInUsedTools.push({
                     tool: 'urlContext',
                     toolInput: {
@@ -1578,55 +1358,47 @@ class Agent_Agentflow implements INode {
             }
         }
 
-        // Handle Gemini codeExecution tool
-        if (response.content && Array.isArray(response.content)) {
-            for (let i = 0; i < response.content.length; i++) {
-                const item = response.content[i]
-
-                if (item.type === 'executableCode' && item.executableCode) {
-                    const language = item.executableCode.language || 'PYTHON'
-                    const code = item.executableCode.code || ''
-                    let toolOutput = ''
-
-                    // Check for duplicates
-                    const isDuplicate = builtInUsedTools.find(
-                        (tool) =>
-                            tool.tool === 'codeExecution' &&
-                            (tool.toolInput as any)?.language === language &&
-                            (tool.toolInput as any)?.code === code
-                    )
-                    if (isDuplicate) {
-                        continue
-                    }
-
-                    // Check the next item for the output
-                    const nextItem = i + 1 < response.content.length ? response.content[i + 1] : null
-
-                    if (nextItem) {
-                        if (nextItem.type === 'codeExecutionResult' && nextItem.codeExecutionResult) {
-                            const outcome = nextItem.codeExecutionResult.outcome
-                            const output = nextItem.codeExecutionResult.output || ''
-                            toolOutput = outcome === 'OUTCOME_OK' ? output : `Error: ${output}`
-                        } else if (nextItem.type === 'inlineData') {
-                            toolOutput = 'Generated image data'
-                        }
-                    }
-
-                    builtInUsedTools.push({
-                        tool: 'codeExecution',
-                        toolInput: {
-                            language,
-                            code
-                        },
-                        toolOutput
-                    })
-                }
-            }
-        }
-
         return builtInUsedTools
     }
 
+    /**
+     * Saves base64 image data to storage and returns file information
+     */
+    private async saveBase64Image(
+        outputItem: any,
+        options: ICommonObject
+    ): Promise<{ filePath: string; fileName: string; totalSize: number } | null> {
+        try {
+            if (!outputItem.result) {
+                return null
+            }
+
+            // Extract base64 data and create buffer
+            const base64Data = outputItem.result
+            const imageBuffer = Buffer.from(base64Data, 'base64')
+
+            // Determine file extension and MIME type
+            const outputFormat = outputItem.output_format || 'png'
+            const fileName = `generated_image_${outputItem.id || Date.now()}.${outputFormat}`
+            const mimeType = outputFormat === 'png' ? 'image/png' : 'image/jpeg'
+
+            // Save the image using the existing storage utility
+            const { path, totalSize } = await addSingleFileToStorage(
+                mimeType,
+                imageBuffer,
+                fileName,
+                options.orgId,
+                options.chatflowid,
+                options.chatId
+            )
+
+            return { filePath: path, fileName, totalSize }
+        } catch (error) {
+            console.error('Error saving base64 image:', error)
+            return null
+        }
+    }
+
     /**
      * Handles memory management based on the specified memory type
      */
@@ -1789,62 +1561,32 @@ class Agent_Agentflow implements INode {
         llmNodeInstance: BaseChatModel,
         messages: BaseMessageLike[],
         chatId: string,
-        abortController: AbortController,
+        abortController: AbortController
-        isStructuredOutput: boolean = false
     ): Promise<AIMessageChunk> {
         let response = new AIMessageChunk('')
 
         try {
             for await (const chunk of await llmNodeInstance.stream(messages, { signal: abortController?.signal })) {
-                if (sseStreamer && !isStructuredOutput) {
+                if (sseStreamer) {
                     let content = ''
-
+                    if (Array.isArray(chunk.content) && chunk.content.length > 0) {
-                    if (typeof chunk === 'string') {
+                        const contents = chunk.content as MessageContentText[]
-                        content = chunk
+                        content = contents.map((item) => item.text).join('')
-                    } else if (Array.isArray(chunk.content) && chunk.content.length > 0) {
+                    } else {
-                        content = chunk.content
-                            .map((item: any) => {
-                                if ((item.text && !item.type) || (item.type === 'text' && item.text)) {
-                                    return item.text
-                                } else if (item.type === 'executableCode' && item.executableCode) {
-                                    const language = item.executableCode.language?.toLowerCase() || 'python'
-                                    return `\n\`\`\`${language}\n${item.executableCode.code}\n\`\`\`\n`
-                                } else if (item.type === 'codeExecutionResult' && item.codeExecutionResult) {
-                                    const outcome = item.codeExecutionResult.outcome || 'OUTCOME_OK'
-                                    const output = item.codeExecutionResult.output || ''
-                                    if (outcome === 'OUTCOME_OK' && output) {
-                                        return `**Code Output:**\n\`\`\`\n${output}\n\`\`\`\n`
-                                    } else if (outcome !== 'OUTCOME_OK') {
-                                        return `**Code Execution Error:**\n\`\`\`\n${output}\n\`\`\`\n`
-                                    }
-                                }
-                                return ''
-                            })
-                            .filter((text: string) => text)
-                            .join('')
-                    } else if (chunk.content) {
                         content = chunk.content.toString()
                     }
                     sseStreamer.streamTokenEvent(chatId, content)
                 }
 
-                const messageChunk = typeof chunk === 'string' ? new AIMessageChunk(chunk) : chunk
+                response = response.concat(chunk)
-                response = response.concat(messageChunk)
             }
         } catch (error) {
             console.error('Error during streaming:', error)
             throw error
         }
-
-        // Only convert to string if all content items are text (no inlineData or other special types)
         if (Array.isArray(response.content) && response.content.length > 0) {
-            const hasNonTextContent = response.content.some(
+            const responseContents = response.content as MessageContentText[]
-                (item: any) => item.type === 'inlineData' || item.type === 'executableCode' || item.type === 'codeExecutionResult'
+            response.content = responseContents.map((item) => item.text).join('')
-            )
-            if (!hasNonTextContent) {
-                const responseContents = response.content as MessageContentText[]
-                response.content = responseContents.map((item) => item.text).join('')
-            }
         }
         return response
     }
@@ -1864,8 +1606,7 @@ class Agent_Agentflow implements INode {
         artifacts: any[],
         additionalTokens: number = 0,
         isWaitingForHumanInput: boolean = false,
-        fileAnnotations: any[] = [],
+        fileAnnotations: any[] = []
-        isStructuredOutput: boolean = false
     ): any {
         const output: any = {
             content: finalResponse,
@@ -1900,15 +1641,6 @@ class Agent_Agentflow implements INode {
             output.responseMetadata = response.response_metadata
         }
 
-        if (isStructuredOutput && typeof response === 'object') {
-            const structuredOutput = response as Record<string, any>
-            for (const key in structuredOutput) {
-                if (structuredOutput[key] !== undefined && structuredOutput[key] !== null) {
-                    output[key] = structuredOutput[key]
-                }
-            }
-        }
-
         // Add used tools, source documents and artifacts to output
         if (usedTools && usedTools.length > 0) {
             output.usedTools = flatten(usedTools)
@@ -1974,8 +1706,7 @@ class Agent_Agentflow implements INode {
         llmNodeInstance,
         isStreamable,
         isLastNode,
-        iterationContext,
+        iterationContext
-        isStructuredOutput = false
     }: {
         response: AIMessageChunk
         messages: BaseMessageLike[]
@@ -1989,7 +1720,6 @@ class Agent_Agentflow implements INode {
         isStreamable: boolean
         isLastNode: boolean
         iterationContext: ICommonObject
-        isStructuredOutput?: boolean
     }): Promise<{
         response: AIMessageChunk
         usedTools: IUsedTool[]
@@ -2069,9 +1799,7 @@ class Agent_Agentflow implements INode {
                     const toolCallDetails = '```json\n' + JSON.stringify(toolCall, null, 2) + '\n```'
                     const responseContent = response.content + `\nAttempting to use tool:\n${toolCallDetails}`
                     response.content = responseContent
-                    if (!isStructuredOutput) {
+                    sseStreamer?.streamTokenEvent(chatId, responseContent)
-                        sseStreamer?.streamTokenEvent(chatId, responseContent)
-                    }
                     return { response, usedTools, sourceDocuments, artifacts, totalTokens, isWaitingForHumanInput: true }
                 }
 
@@ -2177,7 +1905,7 @@ class Agent_Agentflow implements INode {
                 const lastToolOutput = usedTools[0]?.toolOutput || ''
                 const lastToolOutputString = typeof lastToolOutput === 'string' ? lastToolOutput : JSON.stringify(lastToolOutput, null, 2)
 
-                if (sseStreamer && !isStructuredOutput) {
+                if (sseStreamer) {
                     sseStreamer.streamTokenEvent(chatId, lastToolOutputString)
                 }
 
@@ -2206,19 +1934,12 @@ class Agent_Agentflow implements INode {
         let newResponse: AIMessageChunk
 
         if (isStreamable) {
-            newResponse = await this.handleStreamingResponse(
+            newResponse = await this.handleStreamingResponse(sseStreamer, llmNodeInstance, messages, chatId, abortController)
-                sseStreamer,
-                llmNodeInstance,
-                messages,
-                chatId,
-                abortController,
-                isStructuredOutput
-            )
         } else {
             newResponse = await llmNodeInstance.invoke(messages, { signal: abortController?.signal })
 
             // Stream non-streaming response if this is the last node
-            if (isLastNode && sseStreamer && !isStructuredOutput) {
+            if (isLastNode && sseStreamer) {
                 let responseContent = JSON.stringify(newResponse, null, 2)
                 if (typeof newResponse.content === 'string') {
                     responseContent = newResponse.content
@@ -2253,8 +1974,7 @@ class Agent_Agentflow implements INode {
                 llmNodeInstance,
                 isStreamable,
                 isLastNode,
-                iterationContext,
+                iterationContext
-                isStructuredOutput
             })
 
             // Merge results from recursive tool calls
@@ -2285,8 +2005,7 @@ class Agent_Agentflow implements INode {
         llmWithoutToolsBind,
         isStreamable,
         isLastNode,
-        iterationContext,
+        iterationContext
-        isStructuredOutput = false
     }: {
         humanInput: IHumanInput
         humanInputAction: Record<string, any> | undefined
@@ -2301,7 +2020,6 @@ class Agent_Agentflow implements INode {
         isStreamable: boolean
         isLastNode: boolean
         iterationContext: ICommonObject
-        isStructuredOutput?: boolean
     }): Promise<{
         response: AIMessageChunk
         usedTools: IUsedTool[]
@@ -2504,7 +2222,7 @@ class Agent_Agentflow implements INode {
                 const lastToolOutput = usedTools[0]?.toolOutput || ''
                 const lastToolOutputString = typeof lastToolOutput === 'string' ? lastToolOutput : JSON.stringify(lastToolOutput, null, 2)
 
-                if (sseStreamer && !isStructuredOutput) {
+                if (sseStreamer) {
                     sseStreamer.streamTokenEvent(chatId, lastToolOutputString)
                 }
 
@@ -2535,19 +2253,12 @@ class Agent_Agentflow implements INode {
         }
 
         if (isStreamable) {
-            newResponse = await this.handleStreamingResponse(
+            newResponse = await this.handleStreamingResponse(sseStreamer, llmNodeInstance, messages, chatId, abortController)
-                sseStreamer,
-                llmNodeInstance,
-                messages,
-                chatId,
-                abortController,
-                isStructuredOutput
-            )
         } else {
             newResponse = await llmNodeInstance.invoke(messages, { signal: abortController?.signal })
 
             // Stream non-streaming response if this is the last node
-            if (isLastNode && sseStreamer && !isStructuredOutput) {
+            if (isLastNode && sseStreamer) {
                 let responseContent = JSON.stringify(newResponse, null, 2)
                 if (typeof newResponse.content === 'string') {
                     responseContent = newResponse.content
@@ -2582,8 +2293,7 @@ class Agent_Agentflow implements INode {
                 llmNodeInstance,
                 isStreamable,
                 isLastNode,
-                iterationContext,
+                iterationContext
-                isStructuredOutput
             })
 
             // Merge results from recursive tool calls
@@ -2598,6 +2308,190 @@ class Agent_Agentflow implements INode {
         return { response: newResponse, usedTools, sourceDocuments, artifacts, totalTokens, isWaitingForHumanInput }
     }
 
+    /**
+     * Extracts artifacts from response metadata (both annotations and built-in tools)
+     */
+    private async extractArtifactsFromResponse(
+        responseMetadata: any,
+        modelNodeData: INodeData,
+        options: ICommonObject
+    ): Promise<{ artifacts: any[]; fileAnnotations: any[] }> {
+        const artifacts: any[] = []
+        const fileAnnotations: any[] = []
+
+        if (!responseMetadata?.output || !Array.isArray(responseMetadata.output)) {
+            return { artifacts, fileAnnotations }
+        }
+
+        for (const outputItem of responseMetadata.output) {
+            // Handle container file citations from annotations
+            if (outputItem.type === 'message' && outputItem.content && Array.isArray(outputItem.content)) {
+                for (const contentItem of outputItem.content) {
+                    if (contentItem.annotations && Array.isArray(contentItem.annotations)) {
+                        for (const annotation of contentItem.annotations) {
+                            if (annotation.type === 'container_file_citation' && annotation.file_id && annotation.filename) {
+                                try {
+                                    // Download and store the file content
+                                    const downloadResult = await this.downloadContainerFile(
+                                        annotation.container_id,
+                                        annotation.file_id,
+                                        annotation.filename,
+                                        modelNodeData,
+                                        options
+                                    )
+
+                                    if (downloadResult) {
+                                        const fileType = this.getArtifactTypeFromFilename(annotation.filename)
+
+                                        if (fileType === 'png' || fileType === 'jpeg' || fileType === 'jpg') {
+                                            const artifact = {
+                                                type: fileType,
+                                                data: downloadResult.filePath
+                                            }
+
+                                            artifacts.push(artifact)
+                                        } else {
+                                            fileAnnotations.push({
+                                                filePath: downloadResult.filePath,
+                                                fileName: annotation.filename
+                                            })
+                                        }
+                                    }
+                                } catch (error) {
+                                    console.error('Error processing annotation:', error)
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+
+            // Handle built-in tool artifacts (like image generation)
+            if (outputItem.type === 'image_generation_call' && outputItem.result) {
+                try {
+                    const savedImageResult = await this.saveBase64Image(outputItem, options)
+                    if (savedImageResult) {
+                        // Replace the base64 result with the file path in the response metadata
+                        outputItem.result = savedImageResult.filePath
+
+                        // Create artifact in the same format as other image artifacts
+                        const fileType = this.getArtifactTypeFromFilename(savedImageResult.fileName)
+                        artifacts.push({
+                            type: fileType,
+                            data: savedImageResult.filePath
+                        })
+                    }
+                } catch (error) {
+                    console.error('Error processing image generation artifact:', error)
+                }
+            }
+        }
+
+        return { artifacts, fileAnnotations }
+    }
+
+    /**
+     * Downloads file content from container file citation
+     */
+    private async downloadContainerFile(
+        containerId: string,
+        fileId: string,
+        filename: string,
+        modelNodeData: INodeData,
+        options: ICommonObject
+    ): Promise<{ filePath: string; totalSize: number } | null> {
+        try {
+            const credentialData = await getCredentialData(modelNodeData.credential ?? '', options)
+            const openAIApiKey = getCredentialParam('openAIApiKey', credentialData, modelNodeData)
+
+            if (!openAIApiKey) {
+                console.warn('No OpenAI API key available for downloading container file')
+                return null
+            }
+
+            // Download the file using OpenAI Container API
+            const response = await fetch(`https://api.openai.com/v1/containers/${containerId}/files/${fileId}/content`, {
+                method: 'GET',
+                headers: {
+                    Accept: '*/*',
+                    Authorization: `Bearer ${openAIApiKey}`
+                }
+            })
+
+            if (!response.ok) {
+                console.warn(
+                    `Failed to download container file ${fileId} from container ${containerId}: ${response.status} ${response.statusText}`
+                )
+                return null
+            }
+
+            // Extract the binary data from the Response object
+            const data = await response.arrayBuffer()
+            const dataBuffer = Buffer.from(data)
+            const mimeType = this.getMimeTypeFromFilename(filename)
+
+            // Store the file using the same storage utility as OpenAIAssistant
+            const { path, totalSize } = await addSingleFileToStorage(
+                mimeType,
+                dataBuffer,
+                filename,
+                options.orgId,
+                options.chatflowid,
+                options.chatId
+            )
+
+            return { filePath: path, totalSize }
+        } catch (error) {
+            console.error('Error downloading container file:', error)
+            return null
+        }
+    }
+
+    /**
+     * Gets MIME type from filename extension
+     */
+    private getMimeTypeFromFilename(filename: string): string {
+        const extension = filename.toLowerCase().split('.').pop()
+        const mimeTypes: { [key: string]: string } = {
+            png: 'image/png',
+            jpg: 'image/jpeg',
+            jpeg: 'image/jpeg',
+            gif: 'image/gif',
+            pdf: 'application/pdf',
+            txt: 'text/plain',
+            csv: 'text/csv',
+            json: 'application/json',
+            html: 'text/html',
+            xml: 'application/xml'
+        }
+        return mimeTypes[extension || ''] || 'application/octet-stream'
+    }
+
+    /**
+     * Gets artifact type from filename extension for UI rendering
+     */
+    private getArtifactTypeFromFilename(filename: string): string {
+        const extension = filename.toLowerCase().split('.').pop()
+        const artifactTypes: { [key: string]: string } = {
+            png: 'png',
+            jpg: 'jpeg',
+            jpeg: 'jpeg',
+            html: 'html',
+            htm: 'html',
+            md: 'markdown',
+            markdown: 'markdown',
+            json: 'json',
+            js: 'javascript',
+            javascript: 'javascript',
+            tex: 'latex',
+            latex: 'latex',
+            txt: 'text',
+            csv: 'text',
+            pdf: 'text'
+        }
+        return artifactTypes[extension || ''] || 'text'
+    }
+
     /**
      * Processes sandbox links in the response text and converts them to file annotations
      */

packages/components/nodes/agentflow/CustomFunction/CustomFunction.ts

@@ -60,7 +60,7 @@ class CustomFunction_Agentflow implements INode {
     constructor() {
         this.label = 'Custom Function'
         this.name = 'customFunctionAgentflow'
-        this.version = 1.1
+        this.version = 1.0
         this.type = 'CustomFunction'
         this.category = 'Agent Flows'
         this.description = 'Execute custom function'
@@ -107,7 +107,8 @@ class CustomFunction_Agentflow implements INode {
                         label: 'Key',
                         name: 'key',
                         type: 'asyncOptions',
-                        loadMethod: 'listRuntimeStateKeys'
+                        loadMethod: 'listRuntimeStateKeys',
+                        freeSolo: true
                     },
                     {
                         label: 'Value',
@@ -133,7 +134,7 @@ class CustomFunction_Agentflow implements INode {
 
     async run(nodeData: INodeData, input: string, options: ICommonObject): Promise<any> {
         const javascriptFunction = nodeData.inputs?.customFunctionJavascriptFunction as string
-        const functionInputVariables = (nodeData.inputs?.customFunctionInputVariables as ICustomFunctionInputVariables[]) ?? []
+        const functionInputVariables = nodeData.inputs?.customFunctionInputVariables as ICustomFunctionInputVariables[]
         const _customFunctionUpdateState = nodeData.inputs?.customFunctionUpdateState
 
         const state = options.agentflowRuntime?.state as ICommonObject
@@ -146,17 +147,11 @@ class CustomFunction_Agentflow implements INode {
 
         const variables = await getVars(appDataSource, databaseEntities, nodeData, options)
         const flow = {
-            input,
-            state,
             chatflowId: options.chatflowid,
             sessionId: options.sessionId,
             chatId: options.chatId,
-            rawOutput: options.postProcessing?.rawOutput || '',
+            input,
-            chatHistory: options.postProcessing?.chatHistory || [],
+            state
-            sourceDocuments: options.postProcessing?.sourceDocuments,
-            usedTools: options.postProcessing?.usedTools,
-            artifacts: options.postProcessing?.artifacts,
-            fileAnnotations: options.postProcessing?.fileAnnotations
         }
 
         // Create additional sandbox variables for custom function inputs

packages/components/nodes/agentflow/ExecuteFlow/ExecuteFlow.ts

@@ -30,7 +30,7 @@ class ExecuteFlow_Agentflow implements INode {
     constructor() {
         this.label = 'Execute Flow'
         this.name = 'executeFlowAgentflow'
-        this.version = 1.2
+        this.version = 1.1
         this.type = 'ExecuteFlow'
         this.category = 'Agent Flows'
         this.description = 'Execute another flow'
@@ -102,7 +102,8 @@ class ExecuteFlow_Agentflow implements INode {
                         label: 'Key',
                         name: 'key',
                         type: 'asyncOptions',
-                        loadMethod: 'listRuntimeStateKeys'
+                        loadMethod: 'listRuntimeStateKeys',
+                        freeSolo: true
                     },
                     {
                         label: 'Value',

packages/components/nodes/agentflow/HumanInput/HumanInput.ts

@@ -241,11 +241,8 @@ class HumanInput_Agentflow implements INode {
                     if (isStreamable) {
                         const sseStreamer: IServerSideEventStreamer = options.sseStreamer as IServerSideEventStreamer
                         for await (const chunk of await llmNodeInstance.stream(messages)) {
-                            const content = typeof chunk === 'string' ? chunk : chunk.content.toString()
+                            sseStreamer.streamTokenEvent(chatId, chunk.content.toString())
-                            sseStreamer.streamTokenEvent(chatId, content)
+                            response = response.concat(chunk)
-
-                            const messageChunk = typeof chunk === 'string' ? new AIMessageChunk(chunk) : chunk
-                            response = response.concat(messageChunk)
                         }
                         humanInputDescription = response.content as string
                     } else {

packages/components/nodes/agentflow/LLM/LLM.ts

@@ -2,19 +2,17 @@ import { BaseChatModel } from '@langchain/core/language_models/chat_models'
 import { ICommonObject, IMessage, INode, INodeData, INodeOptionsValue, INodeParams, IServerSideEventStreamer } from '../../../src/Interface'
 import { AIMessageChunk, BaseMessageLike, MessageContentText } from '@langchain/core/messages'
 import { DEFAULT_SUMMARIZER_TEMPLATE } from '../prompt'
+import { z } from 'zod'
 import { AnalyticHandler } from '../../../src/handler'
-import { ILLMMessage } from '../Interface.Agentflow'
+import { ILLMMessage, IStructuredOutput } from '../Interface.Agentflow'
 import {
-    addImageArtifactsToMessages,
-    extractArtifactsFromResponse,
     getPastChatHistoryImageMessages,
     getUniqueImageMessages,
     processMessagesWithImages,
     replaceBase64ImagesWithFileReferences,
-    replaceInlineDataWithFileReferences,
     updateFlowState
 } from '../utils'
-import { processTemplateVariables, configureStructuredOutput } from '../../../src/utils'
+import { processTemplateVariables } from '../../../src/utils'
 import { flatten } from 'lodash'
 
 class LLM_Agentflow implements INode {
@@ -34,7 +32,7 @@ class LLM_Agentflow implements INode {
     constructor() {
         this.label = 'LLM'
         this.name = 'llmAgentflow'
-        this.version = 1.1
+        this.version = 1.0
         this.type = 'LLM'
         this.category = 'Agent Flows'
         this.description = 'Large language models to analyze user-provided inputs and generate responses'
@@ -290,7 +288,8 @@ class LLM_Agentflow implements INode {
                         label: 'Key',
                         name: 'key',
                         type: 'asyncOptions',
-                        loadMethod: 'listRuntimeStateKeys'
+                        loadMethod: 'listRuntimeStateKeys',
+                        freeSolo: true
                     },
                     {
                         label: 'Value',
@@ -450,16 +449,10 @@ class LLM_Agentflow implements INode {
             }
             delete nodeData.inputs?.llmMessages
 
-            /**
-             * Add image artifacts from previous assistant responses as user messages
-             * Images are converted from FILE-STORAGE::<image_path> to base 64 image_url format
-             */
-            await addImageArtifactsToMessages(messages, options)
-
             // Configure structured output if specified
             const isStructuredOutput = _llmStructuredOutput && Array.isArray(_llmStructuredOutput) && _llmStructuredOutput.length > 0
             if (isStructuredOutput) {
-                llmNodeInstance = configureStructuredOutput(llmNodeInstance, _llmStructuredOutput)
+                llmNodeInstance = this.configureStructuredOutput(llmNodeInstance, _llmStructuredOutput)
             }
 
             // Initialize response and determine if streaming is possible
@@ -475,11 +468,9 @@ class LLM_Agentflow implements INode {
 
             // Track execution time
             const startTime = Date.now()
+
             const sseStreamer: IServerSideEventStreamer | undefined = options.sseStreamer
 
-            /*
-             * Invoke LLM
-             */
             if (isStreamable) {
                 response = await this.handleStreamingResponse(sseStreamer, llmNodeInstance, messages, chatId, abortController)
             } else {
@@ -504,40 +495,6 @@ class LLM_Agentflow implements INode {
             const endTime = Date.now()
             const timeDelta = endTime - startTime
 
-            // Extract artifacts and file annotations from response metadata
-            let artifacts: any[] = []
-            let fileAnnotations: any[] = []
-            if (response.response_metadata) {
-                const {
-                    artifacts: extractedArtifacts,
-                    fileAnnotations: extractedFileAnnotations,
-                    savedInlineImages
-                } = await extractArtifactsFromResponse(response.response_metadata, newNodeData, options)
-
-                if (extractedArtifacts.length > 0) {
-                    artifacts = extractedArtifacts
-
-                    // Stream artifacts if this is the last node
-                    if (isLastNode && sseStreamer) {
-                        sseStreamer.streamArtifactsEvent(chatId, artifacts)
-                    }
-                }
-
-                if (extractedFileAnnotations.length > 0) {
-                    fileAnnotations = extractedFileAnnotations
-
-                    // Stream file annotations if this is the last node
-                    if (isLastNode && sseStreamer) {
-                        sseStreamer.streamFileAnnotationsEvent(chatId, fileAnnotations)
-                    }
-                }
-
-                // Replace inlineData base64 with file references in the response
-                if (savedInlineImages && savedInlineImages.length > 0) {
-                    replaceInlineDataWithFileReferences(response, savedInlineImages)
-                }
-            }
-
             // Update flow state if needed
             let newState = { ...state }
             if (_llmUpdateState && Array.isArray(_llmUpdateState) && _llmUpdateState.length > 0) {
@@ -557,22 +514,10 @@ class LLM_Agentflow implements INode {
                 finalResponse = response.content.map((item: any) => item.text).join('\n')
             } else if (response.content && typeof response.content === 'string') {
                 finalResponse = response.content
-            } else if (response.content === '') {
-                // Empty response content, this could happen when there is only image data
-                finalResponse = ''
             } else {
                 finalResponse = JSON.stringify(response, null, 2)
             }
-            const output = this.prepareOutputObject(
+            const output = this.prepareOutputObject(response, finalResponse, startTime, endTime, timeDelta, isStructuredOutput)
-                response,
-                finalResponse,
-                startTime,
-                endTime,
-                timeDelta,
-                isStructuredOutput,
-                artifacts,
-                fileAnnotations
-            )
 
             // End analytics tracking
             if (analyticHandlers && llmIds) {
@@ -584,23 +529,12 @@ class LLM_Agentflow implements INode {
                 this.sendStreamingEvents(options, chatId, response)
             }
 
-            // Stream file annotations if any were extracted
-            if (fileAnnotations.length > 0 && isLastNode && sseStreamer) {
-                sseStreamer.streamFileAnnotationsEvent(chatId, fileAnnotations)
-            }
-
             // Process template variables in state
             newState = processTemplateVariables(newState, finalResponse)
 
-            /**
-             * Remove the temporarily added image artifact messages before storing
-             * This is to avoid storing the actual base64 data into database
-             */
-            const messagesToStore = messages.filter((msg: any) => !msg._isTemporaryImageMessage)
-
             // Replace the actual messages array with one that includes the file references for images instead of base64 data
             const messagesWithFileReferences = replaceBase64ImagesWithFileReferences(
-                messagesToStore,
+                messages,
                 runtimeImageMessagesWithFileRef,
                 pastImageMessagesWithFileRef
             )
@@ -651,13 +585,7 @@ class LLM_Agentflow implements INode {
                     {
                         role: returnRole,
                         content: finalResponse,
-                        name: nodeData?.label ? nodeData?.label.toLowerCase().replace(/\s/g, '_').trim() : nodeData?.id,
+                        name: nodeData?.label ? nodeData?.label.toLowerCase().replace(/\s/g, '_').trim() : nodeData?.id
-                        ...(((artifacts && artifacts.length > 0) || (fileAnnotations && fileAnnotations.length > 0)) && {
-                            additional_kwargs: {
-                                ...(artifacts && artifacts.length > 0 && { artifacts }),
-                                ...(fileAnnotations && fileAnnotations.length > 0 && { fileAnnotations })
-                            }
-                        })
                     }
                 ]
             }
@@ -827,6 +755,59 @@ class LLM_Agentflow implements INode {
         }
     }
 
+    /**
+     * Configures structured output for the LLM
+     */
+    private configureStructuredOutput(llmNodeInstance: BaseChatModel, llmStructuredOutput: IStructuredOutput[]): BaseChatModel {
+        try {
+            const zodObj: ICommonObject = {}
+            for (const sch of llmStructuredOutput) {
+                if (sch.type === 'string') {
+                    zodObj[sch.key] = z.string().describe(sch.description || '')
+                } else if (sch.type === 'stringArray') {
+                    zodObj[sch.key] = z.array(z.string()).describe(sch.description || '')
+                } else if (sch.type === 'number') {
+                    zodObj[sch.key] = z.number().describe(sch.description || '')
+                } else if (sch.type === 'boolean') {
+                    zodObj[sch.key] = z.boolean().describe(sch.description || '')
+                } else if (sch.type === 'enum') {
+                    const enumValues = sch.enumValues?.split(',').map((item: string) => item.trim()) || []
+                    zodObj[sch.key] = z
+                        .enum(enumValues.length ? (enumValues as [string, ...string[]]) : ['default'])
+                        .describe(sch.description || '')
+                } else if (sch.type === 'jsonArray') {
+                    const jsonSchema = sch.jsonSchema
+                    if (jsonSchema) {
+                        try {
+                            // Parse the JSON schema
+                            const schemaObj = JSON.parse(jsonSchema)
+
+                            // Create a Zod schema from the JSON schema
+                            const itemSchema = this.createZodSchemaFromJSON(schemaObj)
+
+                            // Create an array schema of the item schema
+                            zodObj[sch.key] = z.array(itemSchema).describe(sch.description || '')
+                        } catch (err) {
+                            console.error(`Error parsing JSON schema for ${sch.key}:`, err)
+                            // Fallback to generic array of records
+                            zodObj[sch.key] = z.array(z.record(z.any())).describe(sch.description || '')
+                        }
+                    } else {
+                        // If no schema provided, use generic array of records
+                        zodObj[sch.key] = z.array(z.record(z.any())).describe(sch.description || '')
+                    }
+                }
+            }
+            const structuredOutput = z.object(zodObj)
+
+            // @ts-ignore
+            return llmNodeInstance.withStructuredOutput(structuredOutput)
+        } catch (exception) {
+            console.error(exception)
+            return llmNodeInstance
+        }
+    }
+
     /**
      * Handles streaming response from the LLM
      */
@@ -843,20 +824,16 @@ class LLM_Agentflow implements INode {
             for await (const chunk of await llmNodeInstance.stream(messages, { signal: abortController?.signal })) {
                 if (sseStreamer) {
                     let content = ''
-
+                    if (Array.isArray(chunk.content) && chunk.content.length > 0) {
-                    if (typeof chunk === 'string') {
-                        content = chunk
-                    } else if (Array.isArray(chunk.content) && chunk.content.length > 0) {
                         const contents = chunk.content as MessageContentText[]
                         content = contents.map((item) => item.text).join('')
-                    } else if (chunk.content) {
+                    } else {
                         content = chunk.content.toString()
                     }
                     sseStreamer.streamTokenEvent(chatId, content)
                 }
 
-                const messageChunk = typeof chunk === 'string' ? new AIMessageChunk(chunk) : chunk
+                response = response.concat(chunk)
-                response = response.concat(messageChunk)
             }
         } catch (error) {
             console.error('Error during streaming:', error)
@@ -878,9 +855,7 @@ class LLM_Agentflow implements INode {
         startTime: number,
         endTime: number,
         timeDelta: number,
-        isStructuredOutput: boolean,
+        isStructuredOutput: boolean
-        artifacts: any[] = [],
-        fileAnnotations: any[] = []
     ): any {
         const output: any = {
             content: finalResponse,
@@ -899,10 +874,6 @@ class LLM_Agentflow implements INode {
             output.usageMetadata = response.usage_metadata
         }
 
-        if (response.response_metadata) {
-            output.responseMetadata = response.response_metadata
-        }
-
         if (isStructuredOutput && typeof response === 'object') {
             const structuredOutput = response as Record<string, any>
             for (const key in structuredOutput) {
@@ -912,14 +883,6 @@ class LLM_Agentflow implements INode {
             }
         }
 
-        if (artifacts && artifacts.length > 0) {
-            output.artifacts = flatten(artifacts)
-        }
-
-        if (fileAnnotations && fileAnnotations.length > 0) {
-            output.fileAnnotations = fileAnnotations
-        }
-
         return output
     }
 
@@ -944,6 +907,107 @@ class LLM_Agentflow implements INode {
 
         sseStreamer.streamEndEvent(chatId)
     }
+
+    /**
+     * Creates a Zod schema from a JSON schema object
+     * @param jsonSchema The JSON schema object
+     * @returns A Zod schema
+     */
+    private createZodSchemaFromJSON(jsonSchema: any): z.ZodTypeAny {
+        // If the schema is an object with properties, create an object schema
+        if (typeof jsonSchema === 'object' && jsonSchema !== null) {
+            const schemaObj: Record<string, z.ZodTypeAny> = {}
+
+            // Process each property in the schema
+            for (const [key, value] of Object.entries(jsonSchema)) {
+                if (value === null) {
+                    // Handle null values
+                    schemaObj[key] = z.null()
+                } else if (typeof value === 'object' && !Array.isArray(value)) {
+                    // Check if the property has a type definition
+                    if ('type' in value) {
+                        const type = value.type as string
+                        const description = ('description' in value ? (value.description as string) : '') || ''
+
+                        // Create the appropriate Zod type based on the type property
+                        if (type === 'string') {
+                            schemaObj[key] = z.string().describe(description)
+                        } else if (type === 'number') {
+                            schemaObj[key] = z.number().describe(description)
+                        } else if (type === 'boolean') {
+                            schemaObj[key] = z.boolean().describe(description)
+                        } else if (type === 'array') {
+                            // If it's an array type, check if items is defined
+                            if ('items' in value && value.items) {
+                                const itemSchema = this.createZodSchemaFromJSON(value.items)
+                                schemaObj[key] = z.array(itemSchema).describe(description)
+                            } else {
+                                // Default to array of any if items not specified
+                                schemaObj[key] = z.array(z.any()).describe(description)
+                            }
+                        } else if (type === 'object') {
+                            // If it's an object type, check if properties is defined
+                            if ('properties' in value && value.properties) {
+                                const nestedSchema = this.createZodSchemaFromJSON(value.properties)
+                                schemaObj[key] = nestedSchema.describe(description)
+                            } else {
+                                // Default to record of any if properties not specified
+                                schemaObj[key] = z.record(z.any()).describe(description)
+                            }
+                        } else {
+                            // Default to any for unknown types
+                            schemaObj[key] = z.any().describe(description)
+                        }
+
+                        // Check if the property is optional
+                        if ('optional' in value && value.optional === true) {
+                            schemaObj[key] = schemaObj[key].optional()
+                        }
+                    } else if (Array.isArray(value)) {
+                        // Array values without a type property
+                        if (value.length > 0) {
+                            // If the array has items, recursively create a schema for the first item
+                            const itemSchema = this.createZodSchemaFromJSON(value[0])
+                            schemaObj[key] = z.array(itemSchema)
+                        } else {
+                            // Empty array, allow any array
+                            schemaObj[key] = z.array(z.any())
+                        }
+                    } else {
+                        // It's a nested object without a type property, recursively create schema
+                        schemaObj[key] = this.createZodSchemaFromJSON(value)
+                    }
+                } else if (Array.isArray(value)) {
+                    // Array values
+                    if (value.length > 0) {
+                        // If the array has items, recursively create a schema for the first item
+                        const itemSchema = this.createZodSchemaFromJSON(value[0])
+                        schemaObj[key] = z.array(itemSchema)
+                    } else {
+                        // Empty array, allow any array
+                        schemaObj[key] = z.array(z.any())
+                    }
+                } else {
+                    // For primitive values (which shouldn't be in the schema directly)
+                    // Use the corresponding Zod type
+                    if (typeof value === 'string') {
+                        schemaObj[key] = z.string()
+                    } else if (typeof value === 'number') {
+                        schemaObj[key] = z.number()
+                    } else if (typeof value === 'boolean') {
+                        schemaObj[key] = z.boolean()
+                    } else {
+                        schemaObj[key] = z.any()
+                    }
+                }
+            }
+
+            return z.object(schemaObj)
+        }
+
+        // Fallback to any for unknown types
+        return z.any()
+    }
 }
 
 module.exports = { nodeClass: LLM_Agentflow }

packages/components/nodes/agentflow/Loop/Loop.ts

@@ -20,7 +20,7 @@ class Loop_Agentflow implements INode {
     constructor() {
         this.label = 'Loop'
         this.name = 'loopAgentflow'
-        this.version = 1.2
+        this.version = 1.1
         this.type = 'Loop'
         this.category = 'Agent Flows'
         this.description = 'Loop back to a previous node'
@@ -64,7 +64,8 @@ class Loop_Agentflow implements INode {
                         label: 'Key',
                         name: 'key',
                         type: 'asyncOptions',
-                        loadMethod: 'listRuntimeStateKeys'
+                        loadMethod: 'listRuntimeStateKeys',
+                        freeSolo: true
                     },
                     {
                         label: 'Value',

packages/components/nodes/agentflow/Retriever/Retriever.ts

@@ -36,7 +36,7 @@ class Retriever_Agentflow implements INode {
     constructor() {
         this.label = 'Retriever'
         this.name = 'retrieverAgentflow'
-        this.version = 1.1
+        this.version = 1.0
         this.type = 'Retriever'
         this.category = 'Agent Flows'
         this.description = 'Retrieve information from vector database'
@@ -87,7 +87,8 @@ class Retriever_Agentflow implements INode {
                         label: 'Key',
                         name: 'key',
                         type: 'asyncOptions',
-                        loadMethod: 'listRuntimeStateKeys'
+                        loadMethod: 'listRuntimeStateKeys',
+                        freeSolo: true
                     },
                     {
                         label: 'Value',

packages/components/nodes/agentflow/Tool/Tool.ts

@@ -29,7 +29,7 @@ class Tool_Agentflow implements INode {
     constructor() {
         this.label = 'Tool'
         this.name = 'toolAgentflow'
-        this.version = 1.2
+        this.version = 1.1
         this.type = 'Tool'
         this.category = 'Agent Flows'
         this.description = 'Tools allow LLM to interact with external systems'
@@ -80,7 +80,8 @@ class Tool_Agentflow implements INode {
                         label: 'Key',
                         name: 'key',
                         type: 'asyncOptions',
-                        loadMethod: 'listRuntimeStateKeys'
+                        loadMethod: 'listRuntimeStateKeys',
+                        freeSolo: true
                     },
                     {
                         label: 'Value',

packages/components/nodes/agentflow/utils.ts

@@ -1,11 +1,10 @@
-import { BaseMessage, MessageContentImageUrl, AIMessageChunk } from '@langchain/core/messages'
+import { BaseMessage, MessageContentImageUrl } from '@langchain/core/messages'
 import { getImageUploads } from '../../src/multiModalUtils'
-import { addSingleFileToStorage, getFileFromStorage } from '../../src/storageUtils'
+import { getFileFromStorage } from '../../src/storageUtils'
-import { ICommonObject, IFileUpload, INodeData } from '../../src/Interface'
+import { ICommonObject, IFileUpload } from '../../src/Interface'
 import { BaseMessageLike } from '@langchain/core/messages'
 import { IFlowState } from './Interface.Agentflow'
-import { getCredentialData, getCredentialParam, handleEscapeCharacters, mapMimeTypeToInputField } from '../../src/utils'
+import { handleEscapeCharacters, mapMimeTypeToInputField } from '../../src/utils'
-import fetch from 'node-fetch'
 
 export const addImagesToMessages = async (
     options: ICommonObject,
@@ -19,8 +18,7 @@ export const addImagesToMessages = async (
         for (const upload of imageUploads) {
             let bf = upload.data
             if (upload.type == 'stored-file') {
-                const fileName = upload.name.replace(/^FILE-STORAGE::/, '')
+                const contents = await getFileFromStorage(upload.name, options.orgId, options.chatflowid, options.chatId)
-                const contents = await getFileFromStorage(fileName, options.orgId, options.chatflowid, options.chatId)
                 // as the image is stored in the server, read the file and convert it to base64
                 bf = 'data:' + upload.mime + ';base64,' + contents.toString('base64')
 
@@ -91,9 +89,8 @@ export const processMessagesWithImages = async (
                 if (item.type === 'stored-file' && item.name && item.mime.startsWith('image/')) {
                     hasImageReferences = true
                     try {
-                        const fileName = item.name.replace(/^FILE-STORAGE::/, '')
                         // Get file contents from storage
-                        const contents = await getFileFromStorage(fileName, options.orgId, options.chatflowid, options.chatId)
+                        const contents = await getFileFromStorage(item.name, options.orgId, options.chatflowid, options.chatId)
 
                         // Create base64 data URL
                         const base64Data = 'data:' + item.mime + ';base64,' + contents.toString('base64')
@@ -325,8 +322,7 @@ export const getPastChatHistoryImageMessages = async (
                 const imageContents: MessageContentImageUrl[] = []
                 for (const upload of uploads) {
                     if (upload.type === 'stored-file' && upload.mime.startsWith('image/')) {
-                        const fileName = upload.name.replace(/^FILE-STORAGE::/, '')
+                        const fileData = await getFileFromStorage(upload.name, options.orgId, options.chatflowid, options.chatId)
-                        const fileData = await getFileFromStorage(fileName, options.orgId, options.chatflowid, options.chatId)
                         // as the image is stored in the server, read the file and convert it to base64
                         const bf = 'data:' + upload.mime + ';base64,' + fileData.toString('base64')
 
@@ -460,437 +456,6 @@ export const getPastChatHistoryImageMessages = async (
     }
 }
 
-/**
- * Gets MIME type from filename extension
- */
-export const getMimeTypeFromFilename = (filename: string): string => {
-    const extension = filename.toLowerCase().split('.').pop()
-    const mimeTypes: { [key: string]: string } = {
-        png: 'image/png',
-        jpg: 'image/jpeg',
-        jpeg: 'image/jpeg',
-        gif: 'image/gif',
-        pdf: 'application/pdf',
-        txt: 'text/plain',
-        csv: 'text/csv',
-        json: 'application/json',
-        html: 'text/html',
-        xml: 'application/xml'
-    }
-    return mimeTypes[extension || ''] || 'application/octet-stream'
-}
-
-/**
- * Gets artifact type from filename extension for UI rendering
- */
-export const getArtifactTypeFromFilename = (filename: string): string => {
-    const extension = filename.toLowerCase().split('.').pop()
-    const artifactTypes: { [key: string]: string } = {
-        png: 'png',
-        jpg: 'jpeg',
-        jpeg: 'jpeg',
-        html: 'html',
-        htm: 'html',
-        md: 'markdown',
-        markdown: 'markdown',
-        json: 'json',
-        js: 'javascript',
-        javascript: 'javascript',
-        tex: 'latex',
-        latex: 'latex',
-        txt: 'text',
-        csv: 'text',
-        pdf: 'text'
-    }
-    return artifactTypes[extension || ''] || 'text'
-}
-
-/**
- * Saves base64 image data to storage and returns file information
- */
-export const saveBase64Image = async (
-    outputItem: any,
-    options: ICommonObject
-): Promise<{ filePath: string; fileName: string; totalSize: number } | null> => {
-    try {
-        if (!outputItem.result) {
-            return null
-        }
-
-        // Extract base64 data and create buffer
-        const base64Data = outputItem.result
-        const imageBuffer = Buffer.from(base64Data, 'base64')
-
-        // Determine file extension and MIME type
-        const outputFormat = outputItem.output_format || 'png'
-        const fileName = `generated_image_${outputItem.id || Date.now()}.${outputFormat}`
-        const mimeType = outputFormat === 'png' ? 'image/png' : 'image/jpeg'
-
-        // Save the image using the existing storage utility
-        const { path, totalSize } = await addSingleFileToStorage(
-            mimeType,
-            imageBuffer,
-            fileName,
-            options.orgId,
-            options.chatflowid,
-            options.chatId
-        )
-
-        return { filePath: path, fileName, totalSize }
-    } catch (error) {
-        console.error('Error saving base64 image:', error)
-        return null
-    }
-}
-
-/**
- * Saves Gemini inline image data to storage and returns file information
- */
-export const saveGeminiInlineImage = async (
-    inlineItem: any,
-    options: ICommonObject
-): Promise<{ filePath: string; fileName: string; totalSize: number } | null> => {
-    try {
-        if (!inlineItem.data || !inlineItem.mimeType) {
-            return null
-        }
-
-        // Extract base64 data and create buffer
-        const base64Data = inlineItem.data
-        const imageBuffer = Buffer.from(base64Data, 'base64')
-
-        // Determine file extension from MIME type
-        const mimeType = inlineItem.mimeType
-        let extension = 'png'
-        if (mimeType.includes('jpeg') || mimeType.includes('jpg')) {
-            extension = 'jpg'
-        } else if (mimeType.includes('png')) {
-            extension = 'png'
-        } else if (mimeType.includes('gif')) {
-            extension = 'gif'
-        } else if (mimeType.includes('webp')) {
-            extension = 'webp'
-        }
-
-        const fileName = `gemini_generated_image_${Date.now()}.${extension}`
-
-        // Save the image using the existing storage utility
-        const { path, totalSize } = await addSingleFileToStorage(
-            mimeType,
-            imageBuffer,
-            fileName,
-            options.orgId,
-            options.chatflowid,
-            options.chatId
-        )
-
-        return { filePath: path, fileName, totalSize }
-    } catch (error) {
-        console.error('Error saving Gemini inline image:', error)
-        return null
-    }
-}
-
-/**
- * Downloads file content from container file citation
- */
-export const downloadContainerFile = async (
-    containerId: string,
-    fileId: string,
-    filename: string,
-    modelNodeData: INodeData,
-    options: ICommonObject
-): Promise<{ filePath: string; totalSize: number } | null> => {
-    try {
-        const credentialData = await getCredentialData(modelNodeData.credential ?? '', options)
-        const openAIApiKey = getCredentialParam('openAIApiKey', credentialData, modelNodeData)
-
-        if (!openAIApiKey) {
-            console.warn('No OpenAI API key available for downloading container file')
-            return null
-        }
-
-        // Download the file using OpenAI Container API
-        const response = await fetch(`https://api.openai.com/v1/containers/${containerId}/files/${fileId}/content`, {
-            method: 'GET',
-            headers: {
-                Accept: '*/*',
-                Authorization: `Bearer ${openAIApiKey}`
-            }
-        })
-
-        if (!response.ok) {
-            console.warn(
-                `Failed to download container file ${fileId} from container ${containerId}: ${response.status} ${response.statusText}`
-            )
-            return null
-        }
-
-        // Extract the binary data from the Response object
-        const data = await response.arrayBuffer()
-        const dataBuffer = Buffer.from(data)
-        const mimeType = getMimeTypeFromFilename(filename)
-
-        // Store the file using the same storage utility as OpenAIAssistant
-        const { path, totalSize } = await addSingleFileToStorage(
-            mimeType,
-            dataBuffer,
-            filename,
-            options.orgId,
-            options.chatflowid,
-            options.chatId
-        )
-
-        return { filePath: path, totalSize }
-    } catch (error) {
-        console.error('Error downloading container file:', error)
-        return null
-    }
-}
-
-/**
- * Replace inlineData base64 with file references in the response content
- */
-export const replaceInlineDataWithFileReferences = (
-    response: AIMessageChunk,
-    savedInlineImages: Array<{ filePath: string; fileName: string; mimeType: string }>
-): void => {
-    // Check if content is an array
-    if (!Array.isArray(response.content)) {
-        return
-    }
-
-    // Replace base64 data with file references in response content
-    let savedImageIndex = 0
-    for (let i = 0; i < response.content.length; i++) {
-        const contentItem = response.content[i]
-        if (
-            typeof contentItem === 'object' &&
-            contentItem.type === 'inlineData' &&
-            contentItem.inlineData &&
-            savedImageIndex < savedInlineImages.length
-        ) {
-            const savedImage = savedInlineImages[savedImageIndex]
-            // Replace with file reference
-            response.content[i] = {
-                type: 'stored-file',
-                name: savedImage.fileName,
-                mime: savedImage.mimeType,
-                path: savedImage.filePath
-            }
-            savedImageIndex++
-        }
-    }
-
-    // Clear the inlineData from response_metadata to avoid duplication
-    if (response.response_metadata?.inlineData) {
-        delete response.response_metadata.inlineData
-    }
-}
-
-/**
- * Extracts artifacts from response metadata (both annotations and built-in tools)
- */
-export const extractArtifactsFromResponse = async (
-    responseMetadata: any,
-    modelNodeData: INodeData,
-    options: ICommonObject
-): Promise<{
-    artifacts: any[]
-    fileAnnotations: any[]
-    savedInlineImages?: Array<{ filePath: string; fileName: string; mimeType: string }>
-}> => {
-    const artifacts: any[] = []
-    const fileAnnotations: any[] = []
-    const savedInlineImages: Array<{ filePath: string; fileName: string; mimeType: string }> = []
-
-    // Handle Gemini inline data (image generation)
-    if (responseMetadata?.inlineData && Array.isArray(responseMetadata.inlineData)) {
-        for (const inlineItem of responseMetadata.inlineData) {
-            if (inlineItem.type === 'gemini_inline_data' && inlineItem.data && inlineItem.mimeType) {
-                try {
-                    const savedImageResult = await saveGeminiInlineImage(inlineItem, options)
-                    if (savedImageResult) {
-                        // Create artifact in the same format as other image artifacts
-                        const fileType = getArtifactTypeFromFilename(savedImageResult.fileName)
-                        artifacts.push({
-                            type: fileType,
-                            data: savedImageResult.filePath
-                        })
-
-                        // Track saved image for replacing base64 data in content
-                        savedInlineImages.push({
-                            filePath: savedImageResult.filePath,
-                            fileName: savedImageResult.fileName,
-                            mimeType: inlineItem.mimeType
-                        })
-                    }
-                } catch (error) {
-                    console.error('Error processing Gemini inline image artifact:', error)
-                }
-            }
-        }
-    }
-
-    if (!responseMetadata?.output || !Array.isArray(responseMetadata.output)) {
-        return { artifacts, fileAnnotations, savedInlineImages: savedInlineImages.length > 0 ? savedInlineImages : undefined }
-    }
-
-    for (const outputItem of responseMetadata.output) {
-        // Handle container file citations from annotations
-        if (outputItem.type === 'message' && outputItem.content && Array.isArray(outputItem.content)) {
-            for (const contentItem of outputItem.content) {
-                if (contentItem.annotations && Array.isArray(contentItem.annotations)) {
-                    for (const annotation of contentItem.annotations) {
-                        if (annotation.type === 'container_file_citation' && annotation.file_id && annotation.filename) {
-                            try {
-                                // Download and store the file content
-                                const downloadResult = await downloadContainerFile(
-                                    annotation.container_id,
-                                    annotation.file_id,
-                                    annotation.filename,
-                                    modelNodeData,
-                                    options
-                                )
-
-                                if (downloadResult) {
-                                    const fileType = getArtifactTypeFromFilename(annotation.filename)
-
-                                    if (fileType === 'png' || fileType === 'jpeg' || fileType === 'jpg') {
-                                        const artifact = {
-                                            type: fileType,
-                                            data: downloadResult.filePath
-                                        }
-
-                                        artifacts.push(artifact)
-                                    } else {
-                                        fileAnnotations.push({
-                                            filePath: downloadResult.filePath,
-                                            fileName: annotation.filename
-                                        })
-                                    }
-                                }
-                            } catch (error) {
-                                console.error('Error processing annotation:', error)
-                            }
-                        }
-                    }
-                }
-            }
-        }
-
-        // Handle built-in tool artifacts (like image generation)
-        if (outputItem.type === 'image_generation_call' && outputItem.result) {
-            try {
-                const savedImageResult = await saveBase64Image(outputItem, options)
-                if (savedImageResult) {
-                    // Replace the base64 result with the file path in the response metadata
-                    outputItem.result = savedImageResult.filePath
-
-                    // Create artifact in the same format as other image artifacts
-                    const fileType = getArtifactTypeFromFilename(savedImageResult.fileName)
-                    artifacts.push({
-                        type: fileType,
-                        data: savedImageResult.filePath
-                    })
-                }
-            } catch (error) {
-                console.error('Error processing image generation artifact:', error)
-            }
-        }
-    }
-
-    return { artifacts, fileAnnotations, savedInlineImages: savedInlineImages.length > 0 ? savedInlineImages : undefined }
-}
-
-/**
- * Add image artifacts from previous assistant messages as user messages
- * This allows the LLM to see and reference the generated images in the conversation
- * Messages are marked with a special flag for later removal
- */
-export const addImageArtifactsToMessages = async (messages: BaseMessageLike[], options: ICommonObject): Promise<void> => {
-    const imageExtensions = ['png', 'jpg', 'jpeg', 'gif', 'webp']
-    const messagesToInsert: Array<{ index: number; message: any }> = []
-
-    // Iterate through messages to find assistant messages with image artifacts
-    for (let i = 0; i < messages.length; i++) {
-        const message = messages[i] as any
-
-        // Check if this is an assistant message with artifacts
-        if (
-            (message.role === 'assistant' || message.role === 'ai') &&
-            message.additional_kwargs?.artifacts &&
-            Array.isArray(message.additional_kwargs.artifacts)
-        ) {
-            const artifacts = message.additional_kwargs.artifacts
-            const imageArtifacts: Array<{ type: string; name: string; mime: string }> = []
-
-            // Extract image artifacts
-            for (const artifact of artifacts) {
-                if (artifact.type && artifact.data) {
-                    // Check if this is an image artifact by file type
-                    if (imageExtensions.includes(artifact.type.toLowerCase())) {
-                        // Extract filename from the file path
-                        const fileName = artifact.data.split('/').pop() || artifact.data
-                        const mimeType = `image/${artifact.type.toLowerCase()}`
-
-                        imageArtifacts.push({
-                            type: 'stored-file',
-                            name: fileName,
-                            mime: mimeType
-                        })
-                    }
-                }
-            }
-
-            // If we found image artifacts, prepare to insert a user message after this assistant message
-            if (imageArtifacts.length > 0) {
-                // Check if the next message already contains these image artifacts to avoid duplicates
-                const nextMessage = messages[i + 1] as any
-                const shouldInsert =
-                    !nextMessage ||
-                    nextMessage.role !== 'user' ||
-                    !Array.isArray(nextMessage.content) ||
-                    !nextMessage.content.some(
-                        (item: any) =>
-                            (item.type === 'stored-file' || item.type === 'image_url') &&
-                            imageArtifacts.some((artifact) => {
-                                // Compare with and without FILE-STORAGE:: prefix
-                                const artifactName = artifact.name.replace('FILE-STORAGE::', '')
-                                const itemName = item.name?.replace('FILE-STORAGE::', '') || ''
-                                return artifactName === itemName
-                            })
-                    )
-
-                if (shouldInsert) {
-                    messagesToInsert.push({
-                        index: i + 1,
-                        message: {
-                            role: 'user',
-                            content: imageArtifacts,
-                            _isTemporaryImageMessage: true // Mark for later removal
-                        }
-                    })
-                }
-            }
-        }
-    }
-
-    // Insert messages in reverse order to maintain correct indices
-    for (let i = messagesToInsert.length - 1; i >= 0; i--) {
-        const { index, message } = messagesToInsert[i]
-        messages.splice(index, 0, message)
-    }
-
-    // Convert stored-file references to base64 image_url format
-    if (messagesToInsert.length > 0) {
-        const { updatedMessages } = await processMessagesWithImages(messages, options)
-        // Replace the messages array content with the updated messages
-        messages.length = 0
-        messages.push(...updatedMessages)
-    }
-}
-
 /**
  * Updates the flow state with new values
  */

packages/components/nodes/agents/ConversationalRetrievalToolAgent/ConversationalRetrievalToolAgent.ts

@@ -5,7 +5,7 @@ import { RunnableSequence } from '@langchain/core/runnables'
 import { BaseChatModel } from '@langchain/core/language_models/chat_models'
 import { ChatPromptTemplate, MessagesPlaceholder, HumanMessagePromptTemplate, PromptTemplate } from '@langchain/core/prompts'
 import { formatToOpenAIToolMessages } from 'langchain/agents/format_scratchpad/openai_tools'
-import { getBaseClasses, transformBracesWithColon, convertChatHistoryToText, convertBaseMessagetoIMessage } from '../../../src/utils'
+import { getBaseClasses, transformBracesWithColon } from '../../../src/utils'
 import { type ToolsAgentStep } from 'langchain/agents/openai/output_parser'
 import {
     FlowiseMemory,
@@ -23,10 +23,8 @@ import { Moderation, checkInputs, streamResponse } from '../../moderation/Modera
 import { formatResponse } from '../../outputparsers/OutputParserHelpers'
 import type { Document } from '@langchain/core/documents'
 import { BaseRetriever } from '@langchain/core/retrievers'
-import { RESPONSE_TEMPLATE, REPHRASE_TEMPLATE } from '../../chains/ConversationalRetrievalQAChain/prompts'
+import { RESPONSE_TEMPLATE } from '../../chains/ConversationalRetrievalQAChain/prompts'
 import { addImagesToMessages, llmSupportsVision } from '../../../src/multiModalUtils'
-import { StringOutputParser } from '@langchain/core/output_parsers'
-import { Tool } from '@langchain/core/tools'
 
 class ConversationalRetrievalToolAgent_Agents implements INode {
     label: string
@@ -44,7 +42,7 @@ class ConversationalRetrievalToolAgent_Agents implements INode {
     constructor(fields?: { sessionId?: string }) {
         this.label = 'Conversational Retrieval Tool Agent'
         this.name = 'conversationalRetrievalToolAgent'
-        this.author = 'niztal(falkor) and nikitas-novatix'
+        this.author = 'niztal(falkor)'
         this.version = 1.0
         this.type = 'AgentExecutor'
         this.category = 'Agents'
@@ -81,26 +79,6 @@ class ConversationalRetrievalToolAgent_Agents implements INode {
                 optional: true,
                 default: RESPONSE_TEMPLATE
             },
-            {
-                label: 'Rephrase Prompt',
-                name: 'rephrasePrompt',
-                type: 'string',
-                description: 'Using previous chat history, rephrase question into a standalone question',
-                warning: 'Prompt must include input variables: {chat_history} and {question}',
-                rows: 4,
-                additionalParams: true,
-                optional: true,
-                default: REPHRASE_TEMPLATE
-            },
-            {
-                label: 'Rephrase Model',
-                name: 'rephraseModel',
-                type: 'BaseChatModel',
-                description:
-                    'Optional: Use a different (faster/cheaper) model for rephrasing. If not specified, uses the main Tool Calling Chat Model.',
-                optional: true,
-                additionalParams: true
-            },
             {
                 label: 'Input Moderation',
                 description: 'Detect text that could generate harmful output and prevent it from being sent to the language model',
@@ -125,9 +103,8 @@ class ConversationalRetrievalToolAgent_Agents implements INode {
         this.sessionId = fields?.sessionId
     }
 
-    // The agent will be prepared in run() with the correct user message - it needs the actual runtime input for rephrasing
+    async init(nodeData: INodeData, input: string, options: ICommonObject): Promise<any> {
-    async init(_nodeData: INodeData, _input: string, _options: ICommonObject): Promise<any> {
+        return prepareAgent(nodeData, options, { sessionId: this.sessionId, chatId: options.chatId, input })
-        return null
     }
 
     async run(nodeData: INodeData, input: string, options: ICommonObject): Promise<string | ICommonObject> {
@@ -171,23 +148,6 @@ class ConversationalRetrievalToolAgent_Agents implements INode {
                 sseStreamer.streamUsedToolsEvent(chatId, res.usedTools)
                 usedTools = res.usedTools
             }
-
-            // If the tool is set to returnDirect, stream the output to the client
-            if (res.usedTools && res.usedTools.length) {
-                let inputTools = nodeData.inputs?.tools
-                inputTools = flatten(inputTools)
-                for (const tool of res.usedTools) {
-                    const inputTool = inputTools.find((inputTool: Tool) => inputTool.name === tool.tool)
-                    if (inputTool && (inputTool as any).returnDirect && shouldStreamResponse) {
-                        sseStreamer.streamTokenEvent(chatId, tool.toolOutput)
-                        // Prevent CustomChainHandler from streaming the same output again
-                        if (res.output === tool.toolOutput) {
-                            res.output = ''
-                        }
-                    }
-                }
-            }
-            // The CustomChainHandler will send the stream end event
         } else {
             res = await executor.invoke({ input }, { callbacks: [loggerHandler, ...callbacks] })
             if (res.sourceDocuments) {
@@ -250,11 +210,9 @@ const prepareAgent = async (
     flowObj: { sessionId?: string; chatId?: string; input?: string }
 ) => {
     const model = nodeData.inputs?.model as BaseChatModel
-    const rephraseModel = (nodeData.inputs?.rephraseModel as BaseChatModel) || model // Use main model if not specified
     const maxIterations = nodeData.inputs?.maxIterations as string
     const memory = nodeData.inputs?.memory as FlowiseMemory
     let systemMessage = nodeData.inputs?.systemMessage as string
-    let rephrasePrompt = nodeData.inputs?.rephrasePrompt as string
     let tools = nodeData.inputs?.tools
     tools = flatten(tools)
     const memoryKey = memory.memoryKey ? memory.memoryKey : 'chat_history'
@@ -262,9 +220,6 @@ const prepareAgent = async (
     const vectorStoreRetriever = nodeData.inputs?.vectorStoreRetriever as BaseRetriever
 
     systemMessage = transformBracesWithColon(systemMessage)
-    if (rephrasePrompt) {
-        rephrasePrompt = transformBracesWithColon(rephrasePrompt)
-    }
 
     const prompt = ChatPromptTemplate.fromMessages([
         ['system', systemMessage ? systemMessage : `You are a helpful AI assistant.`],
@@ -308,37 +263,6 @@ const prepareAgent = async (
 
     const modelWithTools = model.bindTools(tools)
 
-    // Function to get standalone question (either rephrased or original)
-    const getStandaloneQuestion = async (input: string): Promise<string> => {
-        // If no rephrase prompt, return the original input
-        if (!rephrasePrompt) {
-            return input
-        }
-
-        // Get chat history (use empty string if none)
-        const messages = (await memory.getChatMessages(flowObj?.sessionId, true)) as BaseMessage[]
-        const iMessages = convertBaseMessagetoIMessage(messages)
-        const chatHistoryString = convertChatHistoryToText(iMessages)
-
-        // Always rephrase to normalize/expand user queries for better retrieval
-        try {
-            const CONDENSE_QUESTION_PROMPT = PromptTemplate.fromTemplate(rephrasePrompt)
-            const condenseQuestionChain = RunnableSequence.from([CONDENSE_QUESTION_PROMPT, rephraseModel, new StringOutputParser()])
-            const res = await condenseQuestionChain.invoke({
-                question: input,
-                chat_history: chatHistoryString
-            })
-            return res
-        } catch (error) {
-            console.error('Error rephrasing question:', error)
-            // On error, fall back to original input
-            return input
-        }
-    }
-
-    // Get standalone question before creating runnable
-    const standaloneQuestion = await getStandaloneQuestion(flowObj?.input || '')
-
     const runnableAgent = RunnableSequence.from([
         {
             [inputKey]: (i: { input: string; steps: ToolsAgentStep[] }) => i.input,
@@ -348,9 +272,7 @@ const prepareAgent = async (
                 return messages ?? []
             },
             context: async (i: { input: string; chatHistory?: string }) => {
-                // Use the standalone question (rephrased or original) for retrieval
+                const relevantDocs = await vectorStoreRetriever.invoke(i.input)
-                const retrievalQuery = standaloneQuestion || i.input
-                const relevantDocs = await vectorStoreRetriever.invoke(retrievalQuery)
                 const formattedDocs = formatDocs(relevantDocs)
                 return formattedDocs
             }
@@ -373,6 +295,4 @@ const prepareAgent = async (
     return executor
 }
 
-module.exports = {
+module.exports = { nodeClass: ConversationalRetrievalToolAgent_Agents }
-    nodeClass: ConversationalRetrievalToolAgent_Agents
-}

packages/components/nodes/agents/OpenAIAssistant/OpenAIAssistant.ts

@@ -578,7 +578,7 @@ class OpenAIAssistant_Agents implements INode {
                                         toolOutput
                                     })
                                 } catch (e) {
-                                    await analyticHandlers.onToolError(toolIds, e)
+                                    await analyticHandlers.onToolEnd(toolIds, e)
                                     console.error('Error executing tool', e)
                                     throw new Error(
                                         `Error executing tool. Tool: ${tool.name}. Thread ID: ${threadId}. Run ID: ${runThreadId}`
@@ -703,7 +703,7 @@ class OpenAIAssistant_Agents implements INode {
                                                 toolOutput
                                             })
                                         } catch (e) {
-                                            await analyticHandlers.onToolError(toolIds, e)
+                                            await analyticHandlers.onToolEnd(toolIds, e)
                                             console.error('Error executing tool', e)
                                             clearInterval(timeout)
                                             reject(
@@ -1096,7 +1096,7 @@ async function handleToolSubmission(params: ToolSubmissionParams): Promise<ToolS
                                 toolOutput
                             })
                         } catch (e) {
-                            await analyticHandlers.onToolError(toolIds, e)
+                            await analyticHandlers.onToolEnd(toolIds, e)
                             console.error('Error executing tool', e)
                             throw new Error(`Error executing tool. Tool: ${tool.name}. Thread ID: ${threadId}. Run ID: ${runThreadId}`)
                         }

packages/components/nodes/chatmodels/ChatGoogleGenerativeAI/FlowiseChatGoogleGenerativeAI.ts

@@ -607,12 +607,7 @@ export class LangchainChatGoogleGenerativeAI
     private client: GenerativeModel
 
     get _isMultimodalModel() {
-        return (
+        return this.model.includes('vision') || this.model.startsWith('gemini-1.5') || this.model.startsWith('gemini-2')
-            this.model.includes('vision') ||
-            this.model.startsWith('gemini-1.5') ||
-            this.model.startsWith('gemini-2') ||
-            this.model.startsWith('gemini-3')
-        )
     }
 
     constructor(fields: GoogleGenerativeAIChatInput) {

packages/components/nodes/chatmodels/ChatGoogleGenerativeAI/utils/common.ts

@@ -452,7 +452,6 @@ export function mapGenerateContentResultToChatResult(
     const [candidate] = response.candidates
     const { content: candidateContent, ...generationInfo } = candidate
     let content: MessageContent | undefined
-    const inlineDataItems: any[] = []
 
     if (Array.isArray(candidateContent?.parts) && candidateContent.parts.length === 1 && candidateContent.parts[0].text) {
         content = candidateContent.parts[0].text
@@ -473,18 +472,6 @@ export function mapGenerateContentResultToChatResult(
                     type: 'codeExecutionResult',
                     codeExecutionResult: p.codeExecutionResult
                 }
-            } else if ('inlineData' in p && p.inlineData) {
-                // Extract inline image data for processing by Agent
-                inlineDataItems.push({
-                    type: 'gemini_inline_data',
-                    mimeType: p.inlineData.mimeType,
-                    data: p.inlineData.data
-                })
-                // Return the inline data as part of the content structure
-                return {
-                    type: 'inlineData',
-                    inlineData: p.inlineData
-                }
             }
             return p
         })
@@ -501,12 +488,6 @@ export function mapGenerateContentResultToChatResult(
         text = block?.text ?? text
     }
 
-    // Build response_metadata with inline data if present
-    const response_metadata: any = {}
-    if (inlineDataItems.length > 0) {
-        response_metadata.inlineData = inlineDataItems
-    }
-
     const generation: ChatGeneration = {
         text,
         message: new AIMessage({
@@ -521,8 +502,7 @@ export function mapGenerateContentResultToChatResult(
             additional_kwargs: {
                 ...generationInfo
             },
-            usage_metadata: extra?.usageMetadata,
+            usage_metadata: extra?.usageMetadata
-            response_metadata: Object.keys(response_metadata).length > 0 ? response_metadata : undefined
         }),
         generationInfo
     }
@@ -553,8 +533,6 @@ export function convertResponseContentToChatGenerationChunk(
     const [candidate] = response.candidates
     const { content: candidateContent, ...generationInfo } = candidate
     let content: MessageContent | undefined
-    const inlineDataItems: any[] = []
-
     // Checks if some parts do not have text. If false, it means that the content is a string.
     if (Array.isArray(candidateContent?.parts) && candidateContent.parts.every((p) => 'text' in p)) {
         content = candidateContent.parts.map((p) => p.text).join('')
@@ -575,18 +553,6 @@ export function convertResponseContentToChatGenerationChunk(
                     type: 'codeExecutionResult',
                     codeExecutionResult: p.codeExecutionResult
                 }
-            } else if ('inlineData' in p && p.inlineData) {
-                // Extract inline image data for processing by Agent
-                inlineDataItems.push({
-                    type: 'gemini_inline_data',
-                    mimeType: p.inlineData.mimeType,
-                    data: p.inlineData.data
-                })
-                // Return the inline data as part of the content structure
-                return {
-                    type: 'inlineData',
-                    inlineData: p.inlineData
-                }
             }
             return p
         })
@@ -616,12 +582,6 @@ export function convertResponseContentToChatGenerationChunk(
         )
     }
 
-    // Build response_metadata with inline data if present
-    const response_metadata: any = {}
-    if (inlineDataItems.length > 0) {
-        response_metadata.inlineData = inlineDataItems
-    }
-
     return new ChatGenerationChunk({
         text,
         message: new AIMessageChunk({
@@ -631,8 +591,7 @@ export function convertResponseContentToChatGenerationChunk(
             // Each chunk can have unique "generationInfo", and merging strategy is unclear,
             // so leave blank for now.
             additional_kwargs: {},
-            usage_metadata: extra.usageMetadata,
+            usage_metadata: extra.usageMetadata
-            response_metadata: Object.keys(response_metadata).length > 0 ? response_metadata : undefined
         }),
         generationInfo
     })

packages/components/nodes/chatmodels/ChatHuggingFace/ChatHuggingFace.ts

@@ -41,17 +41,15 @@ class ChatHuggingFace_ChatModels implements INode {
                 label: 'Model',
                 name: 'model',
                 type: 'string',
-                description:
+                description: 'If using own inference endpoint, leave this blank',
-                    'Model name (e.g., deepseek-ai/DeepSeek-V3.2-Exp:novita). If model includes provider (:) or using router endpoint, leave Endpoint blank.',
+                placeholder: 'gpt2'
-                placeholder: 'deepseek-ai/DeepSeek-V3.2-Exp:novita'
             },
             {
                 label: 'Endpoint',
                 name: 'endpoint',
                 type: 'string',
                 placeholder: 'https://xyz.eu-west-1.aws.endpoints.huggingface.cloud/gpt2',
-                description:
+                description: 'Using your own inference endpoint',
-                    'Custom inference endpoint (optional). Not needed for models with providers (:) or router endpoints. Leave blank to use Inference Providers.',
                 optional: true
             },
             {
@@ -126,15 +124,6 @@ class ChatHuggingFace_ChatModels implements INode {
         const credentialData = await getCredentialData(nodeData.credential ?? '', options)
         const huggingFaceApiKey = getCredentialParam('huggingFaceApiKey', credentialData, nodeData)
 
-        if (!huggingFaceApiKey) {
-            console.error('[ChatHuggingFace] API key validation failed: No API key found')
-            throw new Error('HuggingFace API key is required. Please configure it in the credential settings.')
-        }
-
-        if (!huggingFaceApiKey.startsWith('hf_')) {
-            console.warn('[ChatHuggingFace] API key format warning: Key does not start with "hf_"')
-        }
-
         const obj: Partial<HFInput> = {
             model,
             apiKey: huggingFaceApiKey

packages/components/nodes/chatmodels/ChatHuggingFace/core.ts

@@ -56,9 +56,9 @@ export class HuggingFaceInference extends LLM implements HFInput {
         this.apiKey = fields?.apiKey ?? getEnvironmentVariable('HUGGINGFACEHUB_API_KEY')
         this.endpointUrl = fields?.endpointUrl
         this.includeCredentials = fields?.includeCredentials
-        if (!this.apiKey || this.apiKey.trim() === '') {
+        if (!this.apiKey) {
             throw new Error(
-                'Please set an API key for HuggingFace Hub. Either configure it in the credential settings in the UI, or set the environment variable HUGGINGFACEHUB_API_KEY.'
+                'Please set an API key for HuggingFace Hub in the environment variable HUGGINGFACEHUB_API_KEY or in the apiKey field of the HuggingFaceInference constructor.'
             )
         }
     }
@@ -68,21 +68,19 @@ export class HuggingFaceInference extends LLM implements HFInput {
     }
 
     invocationParams(options?: this['ParsedCallOptions']) {
-        // Return parameters compatible with chatCompletion API (OpenAI-compatible format)
+        return {
-        const params: any = {
+            model: this.model,
-            temperature: this.temperature,
+            parameters: {
-            max_tokens: this.maxTokens,
+                // make it behave similar to openai, returning only the generated text
-            stop: options?.stop ?? this.stopSequences,
+                return_full_text: false,
-            top_p: this.topP
+                temperature: this.temperature,
+                max_new_tokens: this.maxTokens,
+                stop: options?.stop ?? this.stopSequences,
+                top_p: this.topP,
+                top_k: this.topK,
+                repetition_penalty: this.frequencyPenalty
+            }
         }
-        // Include optional parameters if they are defined
-        if (this.topK !== undefined) {
-            params.top_k = this.topK
-        }
-        if (this.frequencyPenalty !== undefined) {
-            params.frequency_penalty = this.frequencyPenalty
-        }
-        return params
     }
 
     async *_streamResponseChunks(
@@ -90,109 +88,51 @@ export class HuggingFaceInference extends LLM implements HFInput {
         options: this['ParsedCallOptions'],
         runManager?: CallbackManagerForLLMRun
     ): AsyncGenerator<GenerationChunk> {
-        try {
+        const hfi = await this._prepareHFInference()
-            const client = await this._prepareHFInference()
+        const stream = await this.caller.call(async () =>
-            const stream = await this.caller.call(async () =>
+            hfi.textGenerationStream({
-                client.chatCompletionStream({
+                ...this.invocationParams(options),
-                    model: this.model,
+                inputs: prompt
-                    messages: [{ role: 'user', content: prompt }],
+            })
-                    ...this.invocationParams(options)
+        )
+        for await (const chunk of stream) {
+            const token = chunk.token.text
+            yield new GenerationChunk({ text: token, generationInfo: chunk })
+            await runManager?.handleLLMNewToken(token ?? '')
+
+            // stream is done
+            if (chunk.generated_text)
+                yield new GenerationChunk({
+                    text: '',
+                    generationInfo: { finished: true }
                 })
-            )
-            for await (const chunk of stream) {
-                const token = chunk.choices[0]?.delta?.content || ''
-                if (token) {
-                    yield new GenerationChunk({ text: token, generationInfo: chunk })
-                    await runManager?.handleLLMNewToken(token)
-                }
-                // stream is done when finish_reason is set
-                if (chunk.choices[0]?.finish_reason) {
-                    yield new GenerationChunk({
-                        text: '',
-                        generationInfo: { finished: true }
-                    })
-                    break
-                }
-            }
-        } catch (error: any) {
-            console.error('[ChatHuggingFace] Error in _streamResponseChunks:', error)
-            // Provide more helpful error messages
-            if (error?.message?.includes('endpointUrl') || error?.message?.includes('third-party provider')) {
-                throw new Error(
-                    `Cannot use custom endpoint with model "${this.model}" that includes a provider. Please leave the Endpoint field blank in the UI. Original error: ${error.message}`
-                )
-            }
-            throw error
         }
     }
 
     /** @ignore */
     async _call(prompt: string, options: this['ParsedCallOptions']): Promise<string> {
-        try {
+        const hfi = await this._prepareHFInference()
-            const client = await this._prepareHFInference()
+        const args = { ...this.invocationParams(options), inputs: prompt }
-            // Use chatCompletion for chat models (v4 supports conversational models via Inference Providers)
+        const res = await this.caller.callWithOptions({ signal: options.signal }, hfi.textGeneration.bind(hfi), args)
-            const args = {
+        return res.generated_text
-                model: this.model,
-                messages: [{ role: 'user', content: prompt }],
-                ...this.invocationParams(options)
-            }
-            const res = await this.caller.callWithOptions({ signal: options.signal }, client.chatCompletion.bind(client), args)
-            const content = res.choices[0]?.message?.content || ''
-            if (!content) {
-                console.error('[ChatHuggingFace] No content in response:', JSON.stringify(res))
-                throw new Error(`No content received from HuggingFace API. Response: ${JSON.stringify(res)}`)
-            }
-            return content
-        } catch (error: any) {
-            console.error('[ChatHuggingFace] Error in _call:', error.message)
-            // Provide more helpful error messages
-            if (error?.message?.includes('endpointUrl') || error?.message?.includes('third-party provider')) {
-                throw new Error(
-                    `Cannot use custom endpoint with model "${this.model}" that includes a provider. Please leave the Endpoint field blank in the UI. Original error: ${error.message}`
-                )
-            }
-            if (error?.message?.includes('Invalid username or password') || error?.message?.includes('authentication')) {
-                throw new Error(
-                    `HuggingFace API authentication failed. Please verify your API key is correct and starts with "hf_". Original error: ${error.message}`
-                )
-            }
-            throw error
-        }
     }
 
     /** @ignore */
     private async _prepareHFInference() {
-        if (!this.apiKey || this.apiKey.trim() === '') {
+        const { HfInference } = await HuggingFaceInference.imports()
-            console.error('[ChatHuggingFace] API key validation failed: Empty or undefined')
+        const hfi = new HfInference(this.apiKey, {
-            throw new Error('HuggingFace API key is required. Please configure it in the credential settings.')
+            includeCredentials: this.includeCredentials
-        }
+        })
-
+        return this.endpointUrl ? hfi.endpoint(this.endpointUrl) : hfi
-        const { InferenceClient } = await HuggingFaceInference.imports()
-        // Use InferenceClient for chat models (works better with Inference Providers)
-        const client = new InferenceClient(this.apiKey)
-
-        // Don't override endpoint if model uses a provider (contains ':') or if endpoint is router-based
-        // When using Inference Providers, endpoint should be left blank - InferenceClient handles routing automatically
-        if (
-            this.endpointUrl &&
-            !this.model.includes(':') &&
-            !this.endpointUrl.includes('/v1/chat/completions') &&
-            !this.endpointUrl.includes('router.huggingface.co')
-        ) {
-            return client.endpoint(this.endpointUrl)
-        }
-
-        // Return client without endpoint override - InferenceClient will use Inference Providers automatically
-        return client
     }
 
     /** @ignore */
     static async imports(): Promise<{
-        InferenceClient: typeof import('@huggingface/inference').InferenceClient
+        HfInference: typeof import('@huggingface/inference').HfInference
     }> {
         try {
-            const { InferenceClient } = await import('@huggingface/inference')
+            const { HfInference } = await import('@huggingface/inference')
-            return { InferenceClient }
+            return { HfInference }
         } catch (e) {
             throw new Error('Please install huggingface as a dependency with, e.g. `pnpm install @huggingface/inference`')
         }

packages/components/nodes/chatmodels/ChatOpenRouter/ChatOpenRouter.ts

@@ -1,8 +1,7 @@
-import { ChatOpenAI as LangchainChatOpenAI, ChatOpenAIFields } from '@langchain/openai'
+import { ChatOpenAI, ChatOpenAIFields } from '@langchain/openai'
 import { BaseCache } from '@langchain/core/caches'
-import { ICommonObject, IMultiModalOption, INode, INodeData, INodeParams } from '../../../src/Interface'
+import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
 import { getBaseClasses, getCredentialData, getCredentialParam } from '../../../src/utils'
-import { ChatOpenRouter } from './FlowiseChatOpenRouter'
 
 class ChatOpenRouter_ChatModels implements INode {
     label: string
@@ -24,7 +23,7 @@ class ChatOpenRouter_ChatModels implements INode {
         this.icon = 'openRouter.svg'
         this.category = 'Chat Models'
         this.description = 'Wrapper around Open Router Inference API'
-        this.baseClasses = [this.type, ...getBaseClasses(LangchainChatOpenAI)]
+        this.baseClasses = [this.type, ...getBaseClasses(ChatOpenAI)]
         this.credential = {
             label: 'Connect Credential',
             name: 'credential',
@@ -115,40 +114,6 @@ class ChatOpenRouter_ChatModels implements INode {
                 type: 'json',
                 optional: true,
                 additionalParams: true
-            },
-            {
-                label: 'Allow Image Uploads',
-                name: 'allowImageUploads',
-                type: 'boolean',
-                description:
-                    'Allow image input. Refer to the <a href="https://docs.flowiseai.com/using-flowise/uploads#image" target="_blank">docs</a> for more details.',
-                default: false,
-                optional: true
-            },
-            {
-                label: 'Image Resolution',
-                description: 'This parameter controls the resolution in which the model views the image.',
-                name: 'imageResolution',
-                type: 'options',
-                options: [
-                    {
-                        label: 'Low',
-                        name: 'low'
-                    },
-                    {
-                        label: 'High',
-                        name: 'high'
-                    },
-                    {
-                        label: 'Auto',
-                        name: 'auto'
-                    }
-                ],
-                default: 'low',
-                optional: false,
-                show: {
-                    allowImageUploads: true
-                }
             }
         ]
     }
@@ -165,8 +130,6 @@ class ChatOpenRouter_ChatModels implements INode {
         const basePath = (nodeData.inputs?.basepath as string) || 'https://openrouter.ai/api/v1'
         const baseOptions = nodeData.inputs?.baseOptions
         const cache = nodeData.inputs?.cache as BaseCache
-        const allowImageUploads = nodeData.inputs?.allowImageUploads as boolean
-        const imageResolution = nodeData.inputs?.imageResolution as string
 
         const credentialData = await getCredentialData(nodeData.credential ?? '', options)
         const openRouterApiKey = getCredentialParam('openRouterApiKey', credentialData, nodeData)
@@ -192,7 +155,7 @@ class ChatOpenRouter_ChatModels implements INode {
             try {
                 parsedBaseOptions = typeof baseOptions === 'object' ? baseOptions : JSON.parse(baseOptions)
             } catch (exception) {
-                throw new Error("Invalid JSON in the ChatOpenRouter's BaseOptions: " + exception)
+                throw new Error("Invalid JSON in the ChatCerebras's BaseOptions: " + exception)
             }
         }
 
@@ -203,15 +166,7 @@ class ChatOpenRouter_ChatModels implements INode {
             }
         }
 
-        const multiModalOption: IMultiModalOption = {
+        const model = new ChatOpenAI(obj)
-            image: {
-                allowImageUploads: allowImageUploads ?? false,
-                imageResolution
-            }
-        }
-
-        const model = new ChatOpenRouter(nodeData.id, obj)
-        model.setMultiModalOption(multiModalOption)
         return model
     }
 }

packages/components/nodes/chatmodels/ChatOpenRouter/FlowiseChatOpenRouter.ts

@@ -1,29 +0,0 @@
-import { ChatOpenAI as LangchainChatOpenAI, ChatOpenAIFields } from '@langchain/openai'
-import { IMultiModalOption, IVisionChatModal } from '../../../src'
-
-export class ChatOpenRouter extends LangchainChatOpenAI implements IVisionChatModal {
-    configuredModel: string
-    configuredMaxToken?: number
-    multiModalOption: IMultiModalOption
-    id: string
-
-    constructor(id: string, fields?: ChatOpenAIFields) {
-        super(fields)
-        this.id = id
-        this.configuredModel = fields?.modelName ?? ''
-        this.configuredMaxToken = fields?.maxTokens
-    }
-
-    revertToOriginalModel(): void {
-        this.model = this.configuredModel
-        this.maxTokens = this.configuredMaxToken
-    }
-
-    setMultiModalOption(multiModalOption: IMultiModalOption): void {
-        this.multiModalOption = multiModalOption
-    }
-
-    setVisionModel(): void {
-        // pass - OpenRouter models don't need model switching
-    }
-}

packages/components/nodes/documentloaders/Unstructured/Unstructured.ts

@@ -27,6 +27,8 @@ type Element = {
 }
 
 export class UnstructuredLoader extends BaseDocumentLoader {
+    public filePath: string
+
     private apiUrl = process.env.UNSTRUCTURED_API_URL || 'https://api.unstructuredapp.io/general/v0/general'
 
     private apiKey: string | undefined = process.env.UNSTRUCTURED_API_KEY
@@ -136,7 +138,7 @@ export class UnstructuredLoader extends BaseDocumentLoader {
         })
 
         if (!response.ok) {
-            throw new Error(`Failed to partition file with error ${response.status} and message ${await response.text()}`)
+            throw new Error(`Failed to partition file ${this.filePath} with error ${response.status} and message ${await response.text()}`)
         }
 
         const elements = await response.json()

packages/components/nodes/documentloaders/Unstructured/UnstructuredFolder.ts

@@ -1,6 +1,3 @@
-/*
-* Uncomment this if you want to use the UnstructuredFolder to load a folder from the file system
-
 import { omit } from 'lodash'
 import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
 import {
@@ -519,4 +516,3 @@ class UnstructuredFolder_DocumentLoaders implements INode {
 }
 
 module.exports = { nodeClass: UnstructuredFolder_DocumentLoaders }
-*/

packages/components/nodes/embeddings/HuggingFaceInferenceEmbedding/core.ts

@@ -23,22 +23,24 @@ export class HuggingFaceInferenceEmbeddings extends Embeddings implements Huggin
         this.model = fields?.model ?? 'sentence-transformers/distilbert-base-nli-mean-tokens'
         this.apiKey = fields?.apiKey ?? getEnvironmentVariable('HUGGINGFACEHUB_API_KEY')
         this.endpoint = fields?.endpoint ?? ''
-        const hf = new HfInference(this.apiKey)
+        this.client = new HfInference(this.apiKey)
-        // v4 uses Inference Providers by default; only override if custom endpoint provided
+        if (this.endpoint) this.client.endpoint(this.endpoint)
-        this.client = this.endpoint ? hf.endpoint(this.endpoint) : hf
     }
 
     async _embed(texts: string[]): Promise<number[][]> {
         // replace newlines, which can negatively affect performance.
         const clean = texts.map((text) => text.replace(/\n/g, ' '))
+        const hf = new HfInference(this.apiKey)
         const obj: any = {
             inputs: clean
         }
-        if (!this.endpoint) {
+        if (this.endpoint) {
+            hf.endpoint(this.endpoint)
+        } else {
             obj.model = this.model
         }
 
-        const res = await this.caller.callWithOptions({}, this.client.featureExtraction.bind(this.client), obj)
+        const res = await this.caller.callWithOptions({}, hf.featureExtraction.bind(hf), obj)
         return res as number[][]
     }
 

packages/components/nodes/llms/HuggingFaceInference/core.ts

@@ -78,8 +78,6 @@ export class HuggingFaceInference extends LLM implements HFInput {
     async _call(prompt: string, options: this['ParsedCallOptions']): Promise<string> {
         const { HfInference } = await HuggingFaceInference.imports()
         const hf = new HfInference(this.apiKey)
-        // v4 uses Inference Providers by default; only override if custom endpoint provided
-        const hfClient = this.endpoint ? hf.endpoint(this.endpoint) : hf
         const obj: any = {
             parameters: {
                 // make it behave similar to openai, returning only the generated text
@@ -92,10 +90,12 @@ export class HuggingFaceInference extends LLM implements HFInput {
             },
             inputs: prompt
         }
-        if (!this.endpoint) {
+        if (this.endpoint) {
+            hf.endpoint(this.endpoint)
+        } else {
             obj.model = this.model
         }
-        const res = await this.caller.callWithOptions({ signal: options.signal }, hfClient.textGeneration.bind(hfClient), obj)
+        const res = await this.caller.callWithOptions({ signal: options.signal }, hf.textGeneration.bind(hf), obj)
         return res.generated_text
     }
 

packages/components/nodes/recordmanager/MySQLRecordManager/MySQLrecordManager.ts

@@ -62,6 +62,7 @@ class MySQLRecordManager_RecordManager implements INode {
                 label: 'Namespace',
                 name: 'namespace',
                 type: 'string',
+                description: 'If not specified, chatflowid will be used',
                 additionalParams: true,
                 optional: true
             },
@@ -218,16 +219,7 @@ class MySQLRecordManager implements RecordManagerInterface {
                 unique key \`unique_key_namespace\` (\`key\`,
 \`namespace\`));`)
 
-            // Add doc_id column if it doesn't exist (migration for existing tables)
+            const columns = [`updated_at`, `key`, `namespace`, `group_id`]
-            const checkColumn = await queryRunner.manager.query(
-                `SELECT COUNT(1) ColumnExists FROM INFORMATION_SCHEMA.COLUMNS 
-                    WHERE table_schema=DATABASE() AND table_name='${tableName}' AND column_name='doc_id';`
-            )
-            if (checkColumn[0].ColumnExists === 0) {
-                await queryRunner.manager.query(`ALTER TABLE \`${tableName}\` ADD COLUMN \`doc_id\` longtext;`)
-            }
-
-            const columns = [`updated_at`, `key`, `namespace`, `group_id`, `doc_id`]
             for (const column of columns) {
                 // MySQL does not support 'IF NOT EXISTS' function for Index
                 const Check = await queryRunner.manager.query(
@@ -269,7 +261,7 @@ class MySQLRecordManager implements RecordManagerInterface {
         }
     }
 
-    async update(keys: Array<{ uid: string; docId: string }> | string[], updateOptions?: UpdateOptions): Promise<void> {
+    async update(keys: string[], updateOptions?: UpdateOptions): Promise<void> {
         if (keys.length === 0) {
             return
         }
@@ -285,23 +277,23 @@ class MySQLRecordManager implements RecordManagerInterface {
             throw new Error(`Time sync issue with database ${updatedAt} < ${timeAtLeast}`)
         }
 
-        // Handle both new format (objects with uid and docId) and old format (strings)
+        const groupIds = _groupIds ?? keys.map(() => null)
-        const isNewFormat = keys.length > 0 && typeof keys[0] === 'object' && 'uid' in keys[0]
-        const keyStrings = isNewFormat ? (keys as Array<{ uid: string; docId: string }>).map((k) => k.uid) : (keys as string[])
-        const docIds = isNewFormat ? (keys as Array<{ uid: string; docId: string }>).map((k) => k.docId) : keys.map(() => null)
 
-        const groupIds = _groupIds ?? keyStrings.map(() => null)
+        if (groupIds.length !== keys.length) {
-
+            throw new Error(`Number of keys (${keys.length}) does not match number of group_ids (${groupIds.length})`)
-        if (groupIds.length !== keyStrings.length) {
-            throw new Error(`Number of keys (${keyStrings.length}) does not match number of group_ids (${groupIds.length})`)
         }
 
-        const recordsToUpsert = keyStrings.map((key, i) => [key, this.namespace, updatedAt, groupIds[i] ?? null, docIds[i] ?? null])
+        const recordsToUpsert = keys.map((key, i) => [
+            key,
+            this.namespace,
+            updatedAt,
+            groupIds[i] ?? null // Ensure groupIds[i] is null if undefined
+        ])
 
         const query = `
-            INSERT INTO \`${tableName}\` (\`key\`, \`namespace\`, \`updated_at\`, \`group_id\`, \`doc_id\`)
+            INSERT INTO \`${tableName}\` (\`key\`, \`namespace\`, \`updated_at\`, \`group_id\`)
-            VALUES (?, ?, ?, ?, ?)
+            VALUES (?, ?, ?, ?)
-            ON DUPLICATE KEY UPDATE \`updated_at\` = VALUES(\`updated_at\`), \`doc_id\` = VALUES(\`doc_id\`)`
+            ON DUPLICATE KEY UPDATE \`updated_at\` = VALUES(\`updated_at\`)`
 
         // To handle multiple files upsert
         try {
@@ -357,13 +349,13 @@ class MySQLRecordManager implements RecordManagerInterface {
         }
     }
 
-    async listKeys(options?: ListKeyOptions & { docId?: string }): Promise<string[]> {
+    async listKeys(options?: ListKeyOptions): Promise<string[]> {
         const dataSource = await this.getDataSource()
         const queryRunner = dataSource.createQueryRunner()
         const tableName = this.sanitizeTableName(this.tableName)
 
         try {
-            const { before, after, limit, groupIds, docId } = options ?? {}
+            const { before, after, limit, groupIds } = options ?? {}
             let query = `SELECT \`key\` FROM \`${tableName}\` WHERE \`namespace\` = ?`
             const values: (string | number | string[])[] = [this.namespace]
 
@@ -390,11 +382,6 @@ class MySQLRecordManager implements RecordManagerInterface {
                 values.push(...groupIds.filter((gid): gid is string => gid !== null))
             }
 
-            if (docId) {
-                query += ` AND \`doc_id\` = ?`
-                values.push(docId)
-            }
-
             query += ';'
 
             // Directly using try/catch with async/await for cleaner flow

packages/components/nodes/recordmanager/PostgresRecordManager/PostgresRecordManager.ts

@@ -78,6 +78,7 @@ class PostgresRecordManager_RecordManager implements INode {
                 label: 'Namespace',
                 name: 'namespace',
                 type: 'string',
+                description: 'If not specified, chatflowid will be used',
                 additionalParams: true,
                 optional: true
             },
@@ -240,19 +241,6 @@ class PostgresRecordManager implements RecordManagerInterface {
   CREATE INDEX IF NOT EXISTS namespace_index ON "${tableName}" (namespace);
   CREATE INDEX IF NOT EXISTS group_id_index ON "${tableName}" (group_id);`)
 
-            // Add doc_id column if it doesn't exist (migration for existing tables)
-            await queryRunner.manager.query(`
-  DO $$
-  BEGIN
-    IF NOT EXISTS (
-      SELECT 1 FROM information_schema.columns 
-      WHERE table_name = '${tableName}' AND column_name = 'doc_id'
-    ) THEN
-      ALTER TABLE "${tableName}" ADD COLUMN doc_id TEXT;
-      CREATE INDEX IF NOT EXISTS doc_id_index ON "${tableName}" (doc_id);
-    END IF;
-  END $$;`)
-
             await queryRunner.release()
         } catch (e: any) {
             // This error indicates that the table already exists
@@ -298,7 +286,7 @@ class PostgresRecordManager implements RecordManagerInterface {
         return `(${placeholders.join(', ')})`
     }
 
-    async update(keys: Array<{ uid: string; docId: string }> | string[], updateOptions?: UpdateOptions): Promise<void> {
+    async update(keys: string[], updateOptions?: UpdateOptions): Promise<void> {
         if (keys.length === 0) {
             return
         }
@@ -314,22 +302,17 @@ class PostgresRecordManager implements RecordManagerInterface {
             throw new Error(`Time sync issue with database ${updatedAt} < ${timeAtLeast}`)
         }
 
-        // Handle both new format (objects with uid and docId) and old format (strings)
+        const groupIds = _groupIds ?? keys.map(() => null)
-        const isNewFormat = keys.length > 0 && typeof keys[0] === 'object' && 'uid' in keys[0]
-        const keyStrings = isNewFormat ? (keys as Array<{ uid: string; docId: string }>).map((k) => k.uid) : (keys as string[])
-        const docIds = isNewFormat ? (keys as Array<{ uid: string; docId: string }>).map((k) => k.docId) : keys.map(() => null)
 
-        const groupIds = _groupIds ?? keyStrings.map(() => null)
+        if (groupIds.length !== keys.length) {
-
+            throw new Error(`Number of keys (${keys.length}) does not match number of group_ids ${groupIds.length})`)
-        if (groupIds.length !== keyStrings.length) {
-            throw new Error(`Number of keys (${keyStrings.length}) does not match number of group_ids ${groupIds.length})`)
         }
 
-        const recordsToUpsert = keyStrings.map((key, i) => [key, this.namespace, updatedAt, groupIds[i], docIds[i]])
+        const recordsToUpsert = keys.map((key, i) => [key, this.namespace, updatedAt, groupIds[i]])
 
         const valuesPlaceholders = recordsToUpsert.map((_, j) => this.generatePlaceholderForRowAt(j, recordsToUpsert[0].length)).join(', ')
 
-        const query = `INSERT INTO "${tableName}" (key, namespace, updated_at, group_id, doc_id) VALUES ${valuesPlaceholders} ON CONFLICT (key, namespace) DO UPDATE SET updated_at = EXCLUDED.updated_at, doc_id = EXCLUDED.doc_id;`
+        const query = `INSERT INTO "${tableName}" (key, namespace, updated_at, group_id) VALUES ${valuesPlaceholders} ON CONFLICT (key, namespace) DO UPDATE SET updated_at = EXCLUDED.updated_at;`
         try {
             await queryRunner.manager.query(query, recordsToUpsert.flat())
             await queryRunner.release()
@@ -368,8 +351,8 @@ class PostgresRecordManager implements RecordManagerInterface {
         }
     }
 
-    async listKeys(options?: ListKeyOptions & { docId?: string }): Promise<string[]> {
+    async listKeys(options?: ListKeyOptions): Promise<string[]> {
-        const { before, after, limit, groupIds, docId } = options ?? {}
+        const { before, after, limit, groupIds } = options ?? {}
         const tableName = this.sanitizeTableName(this.tableName)
 
         let query = `SELECT key FROM "${tableName}" WHERE namespace = $1`
@@ -400,12 +383,6 @@ class PostgresRecordManager implements RecordManagerInterface {
             index += 1
         }
 
-        if (docId) {
-            values.push(docId)
-            query += ` AND doc_id = $${index}`
-            index += 1
-        }
-
         query += ';'
 
         const dataSource = await this.getDataSource()

packages/components/nodes/recordmanager/SQLiteRecordManager/SQLiteRecordManager.ts

@@ -51,6 +51,7 @@ class SQLiteRecordManager_RecordManager implements INode {
                 label: 'Namespace',
                 name: 'namespace',
                 type: 'string',
+                description: 'If not specified, chatflowid will be used',
                 additionalParams: true,
                 optional: true
             },
@@ -197,15 +198,6 @@ CREATE INDEX IF NOT EXISTS key_index ON "${tableName}" (key);
 CREATE INDEX IF NOT EXISTS namespace_index ON "${tableName}" (namespace);
 CREATE INDEX IF NOT EXISTS group_id_index ON "${tableName}" (group_id);`)
 
-            // Add doc_id column if it doesn't exist (migration for existing tables)
-            const checkColumn = await queryRunner.manager.query(
-                `SELECT COUNT(*) as count FROM pragma_table_info('${tableName}') WHERE name='doc_id';`
-            )
-            if (checkColumn[0].count === 0) {
-                await queryRunner.manager.query(`ALTER TABLE "${tableName}" ADD COLUMN doc_id TEXT;`)
-                await queryRunner.manager.query(`CREATE INDEX IF NOT EXISTS doc_id_index ON "${tableName}" (doc_id);`)
-            }
-
             await queryRunner.release()
         } catch (e: any) {
             // This error indicates that the table already exists
@@ -236,7 +228,7 @@ CREATE INDEX IF NOT EXISTS group_id_index ON "${tableName}" (group_id);`)
         }
     }
 
-    async update(keys: Array<{ uid: string; docId: string }> | string[], updateOptions?: UpdateOptions): Promise<void> {
+    async update(keys: string[], updateOptions?: UpdateOptions): Promise<void> {
         if (keys.length === 0) {
             return
         }
@@ -251,23 +243,23 @@ CREATE INDEX IF NOT EXISTS group_id_index ON "${tableName}" (group_id);`)
             throw new Error(`Time sync issue with database ${updatedAt} < ${timeAtLeast}`)
         }
 
-        // Handle both new format (objects with uid and docId) and old format (strings)
+        const groupIds = _groupIds ?? keys.map(() => null)
-        const isNewFormat = keys.length > 0 && typeof keys[0] === 'object' && 'uid' in keys[0]
-        const keyStrings = isNewFormat ? (keys as Array<{ uid: string; docId: string }>).map((k) => k.uid) : (keys as string[])
-        const docIds = isNewFormat ? (keys as Array<{ uid: string; docId: string }>).map((k) => k.docId) : keys.map(() => null)
 
-        const groupIds = _groupIds ?? keyStrings.map(() => null)
+        if (groupIds.length !== keys.length) {
-
+            throw new Error(`Number of keys (${keys.length}) does not match number of group_ids (${groupIds.length})`)
-        if (groupIds.length !== keyStrings.length) {
-            throw new Error(`Number of keys (${keyStrings.length}) does not match number of group_ids (${groupIds.length})`)
         }
 
-        const recordsToUpsert = keyStrings.map((key, i) => [key, this.namespace, updatedAt, groupIds[i] ?? null, docIds[i] ?? null])
+        const recordsToUpsert = keys.map((key, i) => [
+            key,
+            this.namespace,
+            updatedAt,
+            groupIds[i] ?? null // Ensure groupIds[i] is null if undefined
+        ])
 
         const query = `
-        INSERT INTO "${tableName}" (key, namespace, updated_at, group_id, doc_id)
+        INSERT INTO "${tableName}" (key, namespace, updated_at, group_id)
-        VALUES (?, ?, ?, ?, ?)
+        VALUES (?, ?, ?, ?)
-        ON CONFLICT (key, namespace) DO UPDATE SET updated_at = excluded.updated_at, doc_id = excluded.doc_id`
+        ON CONFLICT (key, namespace) DO UPDATE SET updated_at = excluded.updated_at`
 
         try {
             // To handle multiple files upsert
@@ -322,8 +314,8 @@ CREATE INDEX IF NOT EXISTS group_id_index ON "${tableName}" (group_id);`)
         }
     }
 
-    async listKeys(options?: ListKeyOptions & { docId?: string }): Promise<string[]> {
+    async listKeys(options?: ListKeyOptions): Promise<string[]> {
-        const { before, after, limit, groupIds, docId } = options ?? {}
+        const { before, after, limit, groupIds } = options ?? {}
         const tableName = this.sanitizeTableName(this.tableName)
 
         let query = `SELECT key FROM "${tableName}" WHERE namespace = ?`
@@ -352,11 +344,6 @@ CREATE INDEX IF NOT EXISTS group_id_index ON "${tableName}" (group_id);`)
             values.push(...groupIds.filter((gid): gid is string => gid !== null))
         }
 
-        if (docId) {
-            query += ` AND doc_id = ?`
-            values.push(docId)
-        }
-
         query += ';'
 
         const dataSource = await this.getDataSource()

packages/components/nodes/tools/MCP/CustomMCP/CustomMCP.ts

@@ -136,17 +136,17 @@ class Custom_MCP implements INode {
         }
 
         let sandbox: ICommonObject = {}
-        const workspaceId = options?.searchOptions?.workspaceId?._value || options?.workspaceId
 
         if (mcpServerConfig.includes('$vars')) {
             const appDataSource = options.appDataSource as DataSource
             const databaseEntities = options.databaseEntities as IDatabaseEntity
-            // If options.workspaceId is not set, create a new options object with the workspaceId for getVars.
+
-            const optionsWithWorkspaceId = options.workspaceId ? options : { ...options, workspaceId }
+            const variables = await getVars(appDataSource, databaseEntities, nodeData, options)
-            const variables = await getVars(appDataSource, databaseEntities, nodeData, optionsWithWorkspaceId)
             sandbox['$vars'] = prepareSandboxVars(variables)
         }
 
+        const workspaceId = options?.searchOptions?.workspaceId?._value || options?.workspaceId
+
         let canonicalConfig
         try {
             canonicalConfig = JSON.parse(mcpServerConfig)

packages/components/nodes/utilities/CustomFunction/CustomFunction.ts

@@ -84,16 +84,11 @@ class CustomFunction_Utilities implements INode {
 
         const variables = await getVars(appDataSource, databaseEntities, nodeData, options)
         const flow = {
-            input,
             chatflowId: options.chatflowid,
             sessionId: options.sessionId,
             chatId: options.chatId,
-            rawOutput: options.postProcessing?.rawOutput || '',
+            rawOutput: options.rawOutput || '',
-            chatHistory: options.postProcessing?.chatHistory || [],
+            input
-            sourceDocuments: options.postProcessing?.sourceDocuments,
-            usedTools: options.postProcessing?.usedTools,
-            artifacts: options.postProcessing?.artifacts,
-            fileAnnotations: options.postProcessing?.fileAnnotations
         }
 
         let inputVars: ICommonObject = {}

packages/components/nodes/vectorstores/Chroma/Chroma.ts

@@ -186,11 +186,7 @@ class Chroma_VectorStores implements INode {
                     const vectorStoreName = collectionName
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     const chromaStore = new ChromaExtended(embeddings, obj)
 

packages/components/nodes/vectorstores/Elasticsearch/Elasticsearch.ts

@@ -198,11 +198,7 @@ class Elasticsearch_VectorStores implements INode {
                     const vectorStoreName = indexName
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     await vectorStore.delete({ ids: keys })
                     await recordManager.deleteKeys(keys)

packages/components/nodes/vectorstores/Pinecone/Pinecone.ts

@@ -212,11 +212,7 @@ class Pinecone_VectorStores implements INode {
                     const vectorStoreName = pineconeNamespace
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     await pineconeStore.delete({ ids: keys })
                     await recordManager.deleteKeys(keys)

packages/components/nodes/vectorstores/Postgres/Postgres.ts

@@ -49,7 +49,7 @@ class Postgres_VectorStores implements INode {
     constructor() {
         this.label = 'Postgres'
         this.name = 'postgres'
-        this.version = 7.1
+        this.version = 7.0
         this.type = 'Postgres'
         this.icon = 'postgres.svg'
         this.category = 'Vector Stores'
@@ -173,15 +173,6 @@ class Postgres_VectorStores implements INode {
                 additionalParams: true,
                 optional: true
             },
-            {
-                label: 'Upsert Batch Size',
-                name: 'batchSize',
-                type: 'number',
-                step: 1,
-                description: 'Upsert in batches of size N',
-                additionalParams: true,
-                optional: true
-            },
             {
                 label: 'Additional Configuration',
                 name: 'additionalConfig',
@@ -241,7 +232,6 @@ class Postgres_VectorStores implements INode {
             const docs = nodeData.inputs?.document as Document[]
             const recordManager = nodeData.inputs?.recordManager
             const isFileUploadEnabled = nodeData.inputs?.fileUpload as boolean
-            const _batchSize = nodeData.inputs?.batchSize
             const vectorStoreDriver: VectorStoreDriver = Postgres_VectorStores.getDriverFromConfig(nodeData, options)
 
             const flattenDocs = docs && docs.length ? flatten(docs) : []
@@ -275,15 +265,7 @@ class Postgres_VectorStores implements INode {
 
                     return res
                 } else {
-                    if (_batchSize) {
+                    await vectorStoreDriver.fromDocuments(finalDocs)
-                        const batchSize = parseInt(_batchSize, 10)
-                        for (let i = 0; i < finalDocs.length; i += batchSize) {
-                            const batch = finalDocs.slice(i, i + batchSize)
-                            await vectorStoreDriver.fromDocuments(batch)
-                        }
-                    } else {
-                        await vectorStoreDriver.fromDocuments(finalDocs)
-                    }
 
                     return { numAdded: finalDocs.length, addedDocs: finalDocs }
                 }
@@ -303,11 +285,7 @@ class Postgres_VectorStores implements INode {
                     const vectorStoreName = tableName
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     await vectorStore.delete({ ids: keys })
                     await recordManager.deleteKeys(keys)

packages/components/nodes/vectorstores/Postgres/driver/TypeORM.ts

@@ -5,11 +5,6 @@ import { TypeORMVectorStore, TypeORMVectorStoreArgs, TypeORMVectorStoreDocument
 import { VectorStore } from '@langchain/core/vectorstores'
 import { Document } from '@langchain/core/documents'
 import { Pool } from 'pg'
-import { v4 as uuid } from 'uuid'
-
-type TypeORMAddDocumentOptions = {
-    ids?: string[]
-}
 
 export class TypeORMDriver extends VectorStoreDriver {
     protected _postgresConnectionOptions: DataSourceOptions
@@ -100,45 +95,15 @@ export class TypeORMDriver extends VectorStoreDriver {
                 try {
                     instance.appDataSource.getRepository(instance.documentEntity).delete(ids)
                 } catch (e) {
-                    console.error('Failed to delete', e)
+                    console.error('Failed to delete')
                 }
             }
         }
 
-        instance.addVectors = async (
+        const baseAddVectorsFn = instance.addVectors.bind(instance)
-            vectors: number[][],
-            documents: Document[],
-            documentOptions?: TypeORMAddDocumentOptions
-        ): Promise<void> => {
-            const rows = vectors.map((embedding, idx) => {
-                const embeddingString = `[${embedding.join(',')}]`
-                const documentRow = {
-                    id: documentOptions?.ids?.length ? documentOptions.ids[idx] : uuid(),
-                    pageContent: documents[idx].pageContent,
-                    embedding: embeddingString,
-                    metadata: documents[idx].metadata
-                }
-                return documentRow
-            })
 
-            const documentRepository = instance.appDataSource.getRepository(instance.documentEntity)
+        instance.addVectors = async (vectors, documents) => {
-            const _batchSize = this.nodeData.inputs?.batchSize
+            return baseAddVectorsFn(vectors, this.sanitizeDocuments(documents))
-            const chunkSize = _batchSize ? parseInt(_batchSize, 10) : 500
-
-            for (let i = 0; i < rows.length; i += chunkSize) {
-                const chunk = rows.slice(i, i + chunkSize)
-                try {
-                    await documentRepository.save(chunk)
-                } catch (e) {
-                    console.error(e)
-                    throw new Error(`Error inserting: ${chunk[0].pageContent}`)
-                }
-            }
-        }
-
-        instance.addDocuments = async (documents: Document[], options?: { ids?: string[] }): Promise<void> => {
-            const texts = documents.map(({ pageContent }) => pageContent)
-            return (instance.addVectors as any)(await this.getEmbeddings().embedDocuments(texts), documents, options)
         }
 
         return instance

packages/components/nodes/vectorstores/Qdrant/Qdrant.ts

@@ -385,11 +385,7 @@ class Qdrant_VectorStores implements INode {
                     const vectorStoreName = collectionName
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     await vectorStore.delete({ ids: keys })
                     await recordManager.deleteKeys(keys)

packages/components/nodes/vectorstores/Supabase/Supabase.ts

@@ -197,11 +197,7 @@ class Supabase_VectorStores implements INode {
                     const vectorStoreName = tableName + '_' + queryName
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     await supabaseStore.delete({ ids: keys })
                     await recordManager.deleteKeys(keys)

packages/components/nodes/vectorstores/Upstash/Upstash.ts

@@ -187,11 +187,7 @@ class Upstash_VectorStores implements INode {
                     const vectorStoreName = UPSTASH_VECTOR_REST_URL
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     await upstashStore.delete({ ids: keys })
                     await recordManager.deleteKeys(keys)

packages/components/nodes/vectorstores/Weaviate/Weaviate.ts

@@ -252,11 +252,7 @@ class Weaviate_VectorStores implements INode {
                     const vectorStoreName = weaviateTextKey ? weaviateIndex + '_' + weaviateTextKey : weaviateIndex
                     await recordManager.createSchema()
                     ;(recordManager as any).namespace = (recordManager as any).namespace + '_' + vectorStoreName
-                    const filterKeys: ICommonObject = {}
+                    const keys: string[] = await recordManager.listKeys({})
-                    if (options.docId) {
-                        filterKeys.docId = options.docId
-                    }
-                    const keys: string[] = await recordManager.listKeys(filterKeys)
 
                     await weaviateStore.delete({ ids: keys })
                     await recordManager.deleteKeys(keys)

packages/components/package.json

@@ -42,8 +42,7 @@
         "@google-ai/generativelanguage": "^2.5.0",
         "@google-cloud/storage": "^7.15.2",
         "@google/generative-ai": "^0.24.0",
-        "@grpc/grpc-js": "^1.10.10",
+        "@huggingface/inference": "^2.6.1",
-        "@huggingface/inference": "^4.13.2",
         "@langchain/anthropic": "0.3.33",
         "@langchain/aws": "^0.1.11",
         "@langchain/baidu-qianfan": "^0.1.0",
@@ -74,20 +73,6 @@
         "@modelcontextprotocol/server-slack": "^2025.1.17",
         "@notionhq/client": "^2.2.8",
         "@opensearch-project/opensearch": "^1.2.0",
-        "@opentelemetry/api": "1.9.0",
-        "@opentelemetry/auto-instrumentations-node": "^0.52.0",
-        "@opentelemetry/core": "1.27.0",
-        "@opentelemetry/exporter-metrics-otlp-grpc": "0.54.0",
-        "@opentelemetry/exporter-metrics-otlp-http": "0.54.0",
-        "@opentelemetry/exporter-metrics-otlp-proto": "0.54.0",
-        "@opentelemetry/exporter-trace-otlp-grpc": "0.54.0",
-        "@opentelemetry/exporter-trace-otlp-http": "0.54.0",
-        "@opentelemetry/exporter-trace-otlp-proto": "0.54.0",
-        "@opentelemetry/resources": "1.27.0",
-        "@opentelemetry/sdk-metrics": "1.27.0",
-        "@opentelemetry/sdk-node": "^0.54.0",
-        "@opentelemetry/sdk-trace-base": "1.27.0",
-        "@opentelemetry/semantic-conventions": "1.27.0",
         "@pinecone-database/pinecone": "4.0.0",
         "@qdrant/js-client-rest": "^1.9.0",
         "@stripe/agent-toolkit": "^0.1.20",

packages/components/src/handler.ts

@@ -1774,7 +1774,7 @@ export class AnalyticHandler {
         }
 
         if (Object.prototype.hasOwnProperty.call(this.handlers, 'lunary')) {
-            const toolEventId: string = this.handlers['lunary'].toolEvent[returnIds['lunary'].toolEvent]
+            const toolEventId: string = this.handlers['lunary'].llmEvent[returnIds['lunary'].toolEvent]
             const monitor = this.handlers['lunary'].client
 
             if (monitor && toolEventId) {

packages/components/src/indexing.ts

@@ -8,10 +8,6 @@ import { IndexingResult } from './Interface'
 
 type Metadata = Record<string, unknown>
 
-export interface ExtendedRecordManagerInterface extends RecordManagerInterface {
-    update(keys: Array<{ uid: string; docId: string }> | string[], updateOptions?: Record<string, any>): Promise<void>
-}
-
 type StringOrDocFunc = string | ((doc: DocumentInterface) => string)
 
 export interface HashedDocumentInterface extends DocumentInterface {
@@ -211,7 +207,7 @@ export const _isBaseDocumentLoader = (arg: any): arg is BaseDocumentLoader => {
 
 interface IndexArgs {
     docsSource: BaseDocumentLoader | DocumentInterface[]
-    recordManager: ExtendedRecordManagerInterface
+    recordManager: RecordManagerInterface
     vectorStore: VectorStore
     options?: IndexOptions
 }
@@ -279,7 +275,7 @@ export async function index(args: IndexArgs): Promise<IndexingResult> {
 
         const uids: string[] = []
         const docsToIndex: DocumentInterface[] = []
-        const docsToUpdate: Array<{ uid: string; docId: string }> = []
+        const docsToUpdate: string[] = []
         const seenDocs = new Set<string>()
         hashedDocs.forEach((hashedDoc, i) => {
             const docExists = batchExists[i]
@@ -287,7 +283,7 @@ export async function index(args: IndexArgs): Promise<IndexingResult> {
                 if (forceUpdate) {
                     seenDocs.add(hashedDoc.uid)
                 } else {
-                    docsToUpdate.push({ uid: hashedDoc.uid, docId: hashedDoc.metadata.docId as string })
+                    docsToUpdate.push(hashedDoc.uid)
                     return
                 }
             }
@@ -312,7 +308,7 @@ export async function index(args: IndexArgs): Promise<IndexingResult> {
         }
 
         await recordManager.update(
-            hashedDocs.map((doc) => ({ uid: doc.uid, docId: doc.metadata.docId as string })),
+            hashedDocs.map((doc) => doc.uid),
             { timeAtLeast: indexStartDt, groupIds: sourceIds }
         )
 

packages/components/src/utils.ts

@@ -8,7 +8,6 @@ import { cloneDeep, omit, get } from 'lodash'
 import TurndownService from 'turndown'
 import { DataSource, Equal } from 'typeorm'
 import { ICommonObject, IDatabaseEntity, IFileUpload, IMessage, INodeData, IVariable, MessageContentImageUrl } from './Interface'
-import { BaseChatModel } from '@langchain/core/language_models/chat_models'
 import { AES, enc } from 'crypto-js'
 import { AIMessage, HumanMessage, BaseMessage } from '@langchain/core/messages'
 import { Document } from '@langchain/core/documents'
@@ -1942,160 +1941,3 @@ export async function parseWithTypeConversion<T extends z.ZodTypeAny>(schema: T,
         throw e
     }
 }
-
-/**
- * Configures structured output for the LLM using Zod schema
- * @param {BaseChatModel} llmNodeInstance - The LLM instance to configure
- * @param {any[]} structuredOutput - Array of structured output schema definitions
- * @returns {BaseChatModel} - The configured LLM instance
- */
-export const configureStructuredOutput = (llmNodeInstance: BaseChatModel, structuredOutput: any[]): BaseChatModel => {
-    try {
-        const zodObj: ICommonObject = {}
-        for (const sch of structuredOutput) {
-            if (sch.type === 'string') {
-                zodObj[sch.key] = z.string().describe(sch.description || '')
-            } else if (sch.type === 'stringArray') {
-                zodObj[sch.key] = z.array(z.string()).describe(sch.description || '')
-            } else if (sch.type === 'number') {
-                zodObj[sch.key] = z.number().describe(sch.description || '')
-            } else if (sch.type === 'boolean') {
-                zodObj[sch.key] = z.boolean().describe(sch.description || '')
-            } else if (sch.type === 'enum') {
-                const enumValues = sch.enumValues?.split(',').map((item: string) => item.trim()) || []
-                zodObj[sch.key] = z
-                    .enum(enumValues.length ? (enumValues as [string, ...string[]]) : ['default'])
-                    .describe(sch.description || '')
-            } else if (sch.type === 'jsonArray') {
-                const jsonSchema = sch.jsonSchema
-                if (jsonSchema) {
-                    try {
-                        // Parse the JSON schema
-                        const schemaObj = JSON.parse(jsonSchema)
-
-                        // Create a Zod schema from the JSON schema
-                        const itemSchema = createZodSchemaFromJSON(schemaObj)
-
-                        // Create an array schema of the item schema
-                        zodObj[sch.key] = z.array(itemSchema).describe(sch.description || '')
-                    } catch (err) {
-                        console.error(`Error parsing JSON schema for ${sch.key}:`, err)
-                        // Fallback to generic array of records
-                        zodObj[sch.key] = z.array(z.record(z.any())).describe(sch.description || '')
-                    }
-                } else {
-                    // If no schema provided, use generic array of records
-                    zodObj[sch.key] = z.array(z.record(z.any())).describe(sch.description || '')
-                }
-            }
-        }
-        const structuredOutputSchema = z.object(zodObj)
-
-        // @ts-ignore
-        return llmNodeInstance.withStructuredOutput(structuredOutputSchema)
-    } catch (exception) {
-        console.error(exception)
-        return llmNodeInstance
-    }
-}
-
-/**
- * Creates a Zod schema from a JSON schema object
- * @param {any} jsonSchema - The JSON schema object
- * @returns {z.ZodTypeAny} - A Zod schema
- */
-export const createZodSchemaFromJSON = (jsonSchema: any): z.ZodTypeAny => {
-    // If the schema is an object with properties, create an object schema
-    if (typeof jsonSchema === 'object' && jsonSchema !== null) {
-        const schemaObj: Record<string, z.ZodTypeAny> = {}
-
-        // Process each property in the schema
-        for (const [key, value] of Object.entries(jsonSchema)) {
-            if (value === null) {
-                // Handle null values
-                schemaObj[key] = z.null()
-            } else if (typeof value === 'object' && !Array.isArray(value)) {
-                // Check if the property has a type definition
-                if ('type' in value) {
-                    const type = value.type as string
-                    const description = ('description' in value ? (value.description as string) : '') || ''
-
-                    // Create the appropriate Zod type based on the type property
-                    if (type === 'string') {
-                        schemaObj[key] = z.string().describe(description)
-                    } else if (type === 'number') {
-                        schemaObj[key] = z.number().describe(description)
-                    } else if (type === 'boolean') {
-                        schemaObj[key] = z.boolean().describe(description)
-                    } else if (type === 'array') {
-                        // If it's an array type, check if items is defined
-                        if ('items' in value && value.items) {
-                            const itemSchema = createZodSchemaFromJSON(value.items)
-                            schemaObj[key] = z.array(itemSchema).describe(description)
-                        } else {
-                            // Default to array of any if items not specified
-                            schemaObj[key] = z.array(z.any()).describe(description)
-                        }
-                    } else if (type === 'object') {
-                        // If it's an object type, check if properties is defined
-                        if ('properties' in value && value.properties) {
-                            const nestedSchema = createZodSchemaFromJSON(value.properties)
-                            schemaObj[key] = nestedSchema.describe(description)
-                        } else {
-                            // Default to record of any if properties not specified
-                            schemaObj[key] = z.record(z.any()).describe(description)
-                        }
-                    } else {
-                        // Default to any for unknown types
-                        schemaObj[key] = z.any().describe(description)
-                    }
-
-                    // Check if the property is optional
-                    if ('optional' in value && value.optional === true) {
-                        schemaObj[key] = schemaObj[key].optional()
-                    }
-                } else if (Array.isArray(value)) {
-                    // Array values without a type property
-                    if (value.length > 0) {
-                        // If the array has items, recursively create a schema for the first item
-                        const itemSchema = createZodSchemaFromJSON(value[0])
-                        schemaObj[key] = z.array(itemSchema)
-                    } else {
-                        // Empty array, allow any array
-                        schemaObj[key] = z.array(z.any())
-                    }
-                } else {
-                    // It's a nested object without a type property, recursively create schema
-                    schemaObj[key] = createZodSchemaFromJSON(value)
-                }
-            } else if (Array.isArray(value)) {
-                // Array values
-                if (value.length > 0) {
-                    // If the array has items, recursively create a schema for the first item
-                    const itemSchema = createZodSchemaFromJSON(value[0])
-                    schemaObj[key] = z.array(itemSchema)
-                } else {
-                    // Empty array, allow any array
-                    schemaObj[key] = z.array(z.any())
-                }
-            } else {
-                // For primitive values (which shouldn't be in the schema directly)
-                // Use the corresponding Zod type
-                if (typeof value === 'string') {
-                    schemaObj[key] = z.string()
-                } else if (typeof value === 'number') {
-                    schemaObj[key] = z.number()
-                } else if (typeof value === 'boolean') {
-                    schemaObj[key] = z.boolean()
-                } else {
-                    schemaObj[key] = z.any()
-                }
-            }
-        }
-
-        return z.object(schemaObj)
-    }
-
-    // Fallback to any for unknown types
-    return z.any()
-}

packages/server/package.json

@@ -66,7 +66,7 @@
         "@google-cloud/logging-winston": "^6.0.0",
         "@keyv/redis": "^4.2.0",
         "@oclif/core": "4.0.7",
-        "@opentelemetry/api": "1.9.0",
+        "@opentelemetry/api": "^1.3.0",
         "@opentelemetry/auto-instrumentations-node": "^0.52.0",
         "@opentelemetry/core": "1.27.0",
         "@opentelemetry/exporter-metrics-otlp-grpc": "0.54.0",
@@ -119,12 +119,12 @@
         "lodash": "^4.17.21",
         "moment": "^2.29.3",
         "moment-timezone": "^0.5.34",
-        "multer": "^2.0.2",
+        "multer": "^1.4.5-lts.1",
         "multer-cloud-storage": "^4.0.0",
         "multer-s3": "^3.0.1",
         "mysql2": "^3.11.3",
         "nanoid": "3",
-        "nodemailer": "^7.0.7",
+        "nodemailer": "^6.9.14",
         "openai": "^4.96.0",
         "passport": "^0.7.0",
         "passport-auth0": "^1.4.4",

packages/server/src/UsageCacheManager.ts

@@ -37,19 +37,7 @@ export class UsageCacheManager {
         if (process.env.MODE === MODE.QUEUE) {
             let redisConfig: string | Record<string, any>
             if (process.env.REDIS_URL) {
-                redisConfig = {
+                redisConfig = process.env.REDIS_URL
-                    url: process.env.REDIS_URL,
-                    socket: {
-                        keepAlive:
-                            process.env.REDIS_KEEP_ALIVE && !isNaN(parseInt(process.env.REDIS_KEEP_ALIVE, 10))
-                                ? parseInt(process.env.REDIS_KEEP_ALIVE, 10)
-                                : undefined
-                    },
-                    pingInterval:
-                        process.env.REDIS_KEEP_ALIVE && !isNaN(parseInt(process.env.REDIS_KEEP_ALIVE, 10))
-                            ? parseInt(process.env.REDIS_KEEP_ALIVE, 10)
-                            : undefined
-                }
             } else {
                 redisConfig = {
                     username: process.env.REDIS_USERNAME || undefined,
@@ -60,16 +48,8 @@ export class UsageCacheManager {
                         tls: process.env.REDIS_TLS === 'true',
                         cert: process.env.REDIS_CERT ? Buffer.from(process.env.REDIS_CERT, 'base64') : undefined,
                         key: process.env.REDIS_KEY ? Buffer.from(process.env.REDIS_KEY, 'base64') : undefined,
-                        ca: process.env.REDIS_CA ? Buffer.from(process.env.REDIS_CA, 'base64') : undefined,
+                        ca: process.env.REDIS_CA ? Buffer.from(process.env.REDIS_CA, 'base64') : undefined
-                        keepAlive:
+                    }
-                            process.env.REDIS_KEEP_ALIVE && !isNaN(parseInt(process.env.REDIS_KEEP_ALIVE, 10))
-                                ? parseInt(process.env.REDIS_KEEP_ALIVE, 10)
-                                : undefined
-                    },
-                    pingInterval:
-                        process.env.REDIS_KEEP_ALIVE && !isNaN(parseInt(process.env.REDIS_KEEP_ALIVE, 10))
-                            ? parseInt(process.env.REDIS_KEEP_ALIVE, 10)
-                            : undefined
                 }
             }
             this.cache = createCache({

packages/server/src/controllers/documentstore/index.ts

@@ -465,10 +465,9 @@ const insertIntoVectorStore = async (req: Request, res: Response, next: NextFunc
         }
         const subscriptionId = req.user?.activeOrganizationSubscriptionId || ''
         const body = req.body
-        const isStrictSave = body.isStrictSave ?? false
         const apiResponse = await documentStoreService.insertIntoVectorStoreMiddleware(
             body,
-            isStrictSave,
+            false,
             orgId,
             workspaceId,
             subscriptionId,
@@ -514,11 +513,7 @@ const deleteVectorStoreFromStore = async (req: Request, res: Response, next: Nex
                 `Error: documentStoreController.deleteVectorStoreFromStore - workspaceId not provided!`
             )
         }
-        const apiResponse = await documentStoreService.deleteVectorStoreFromStore(
+        const apiResponse = await documentStoreService.deleteVectorStoreFromStore(req.params.storeId, workspaceId)
-            req.params.storeId,
-            workspaceId,
-            (req.query.docId as string) || undefined
-        )
         return res.json(apiResponse)
     } catch (error) {
         next(error)

packages/server/src/database/migrations/mariadb/1765000000000-FixDocumentStoreFileChunkLongText.ts

@@ -1,14 +0,0 @@
-import { MigrationInterface, QueryRunner } from 'typeorm'
-
-export class FixDocumentStoreFileChunkLongText1765000000000 implements MigrationInterface {
-    public async up(queryRunner: QueryRunner): Promise<void> {
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`pageContent\` LONGTEXT NOT NULL;`)
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`metadata\` LONGTEXT NULL;`)
-    }
-
-    public async down(queryRunner: QueryRunner): Promise<void> {
-        // WARNING: Reverting to TEXT may cause data loss if content exceeds the 64KB limit.
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`pageContent\` TEXT NOT NULL;`)
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`metadata\` TEXT NULL;`)
-    }
-}

packages/server/src/database/migrations/mariadb/index.ts

@@ -40,7 +40,6 @@ import { AddTextToSpeechToChatFlow1754986457485 } from './1754986457485-AddTextT
 import { ModifyChatflowType1755066758601 } from './1755066758601-ModifyChatflowType'
 import { AddTextToSpeechToChatFlow1759419231100 } from './1759419231100-AddTextToSpeechToChatFlow'
 import { AddChatFlowNameIndex1759424809984 } from './1759424809984-AddChatFlowNameIndex'
-import { FixDocumentStoreFileChunkLongText1765000000000 } from './1765000000000-FixDocumentStoreFileChunkLongText'
 
 import { AddAuthTables1720230151482 } from '../../../enterprise/database/migrations/mariadb/1720230151482-AddAuthTables'
 import { AddWorkspace1725437498242 } from '../../../enterprise/database/migrations/mariadb/1725437498242-AddWorkspace'
@@ -107,6 +106,5 @@ export const mariadbMigrations = [
     AddTextToSpeechToChatFlow1754986457485,
     ModifyChatflowType1755066758601,
     AddTextToSpeechToChatFlow1759419231100,
-    AddChatFlowNameIndex1759424809984,
+    AddChatFlowNameIndex1759424809984
-    FixDocumentStoreFileChunkLongText1765000000000
 ]

packages/server/src/database/migrations/mysql/1765000000000-FixDocumentStoreFileChunkLongText.ts

@@ -1,14 +0,0 @@
-import { MigrationInterface, QueryRunner } from 'typeorm'
-
-export class FixDocumentStoreFileChunkLongText1765000000000 implements MigrationInterface {
-    public async up(queryRunner: QueryRunner): Promise<void> {
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`pageContent\` LONGTEXT NOT NULL;`)
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`metadata\` LONGTEXT NULL;`)
-    }
-
-    public async down(queryRunner: QueryRunner): Promise<void> {
-        // WARNING: Reverting to TEXT may cause data loss if content exceeds the 64KB limit.
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`pageContent\` TEXT NOT NULL;`)
-        await queryRunner.query(`ALTER TABLE \`document_store_file_chunk\` MODIFY \`metadata\` TEXT NULL;`)
-    }
-}

packages/server/src/database/migrations/mysql/index.ts

@@ -41,7 +41,6 @@ import { AddTextToSpeechToChatFlow1754986468397 } from './1754986468397-AddTextT
 import { ModifyChatflowType1755066758601 } from './1755066758601-ModifyChatflowType'
 import { AddTextToSpeechToChatFlow1759419216034 } from './1759419216034-AddTextToSpeechToChatFlow'
 import { AddChatFlowNameIndex1759424828558 } from './1759424828558-AddChatFlowNameIndex'
-import { FixDocumentStoreFileChunkLongText1765000000000 } from './1765000000000-FixDocumentStoreFileChunkLongText'
 
 import { AddAuthTables1720230151482 } from '../../../enterprise/database/migrations/mysql/1720230151482-AddAuthTables'
 import { AddWorkspace1720230151484 } from '../../../enterprise/database/migrations/mysql/1720230151484-AddWorkspace'
@@ -109,6 +108,5 @@ export const mysqlMigrations = [
     AddTextToSpeechToChatFlow1754986468397,
     ModifyChatflowType1755066758601,
     AddTextToSpeechToChatFlow1759419216034,
-    AddChatFlowNameIndex1759424828558,
+    AddChatFlowNameIndex1759424828558
-    FixDocumentStoreFileChunkLongText1765000000000
 ]

packages/server/src/services/documentstore/index.ts

@@ -391,7 +391,7 @@ const deleteDocumentStoreFileChunk = async (storeId: string, docId: string, chun
     }
 }
 
-const deleteVectorStoreFromStore = async (storeId: string, workspaceId: string, docId?: string) => {
+const deleteVectorStoreFromStore = async (storeId: string, workspaceId: string) => {
     try {
         const appServer = getRunningExpressApp()
         const componentNodes = appServer.nodesPool.componentNodes
@@ -461,7 +461,7 @@ const deleteVectorStoreFromStore = async (storeId: string, workspaceId: string,
 
         // Call the delete method of the vector store
         if (vectorStoreObj.vectorStoreMethods.delete) {
-            await vectorStoreObj.vectorStoreMethods.delete(vStoreNodeData, idsToDelete, { ...options, docId })
+            await vectorStoreObj.vectorStoreMethods.delete(vStoreNodeData, idsToDelete, options)
         }
     } catch (error) {
         throw new InternalFlowiseError(
@@ -1157,18 +1157,6 @@ const updateVectorStoreConfigOnly = async (data: ICommonObject, workspaceId: str
         )
     }
 }
-/**
- * Saves vector store configuration to the document store entity.
- * Handles embedding, vector store, and record manager configurations.
- *
- * @example
- * // Strict mode: Only save what's provided, clear the rest
- * await saveVectorStoreConfig(ds, { storeId, embeddingName, embeddingConfig }, true, wsId)
- *
- * @example
- * // Lenient mode: Reuse existing configs if not provided
- * await saveVectorStoreConfig(ds, { storeId, vectorStoreName, vectorStoreConfig }, false, wsId)
- */
 const saveVectorStoreConfig = async (appDataSource: DataSource, data: ICommonObject, isStrictSave = true, workspaceId: string) => {
     try {
         const entity = await appDataSource.getRepository(DocumentStore).findOneBy({
@@ -1233,15 +1221,6 @@ const saveVectorStoreConfig = async (appDataSource: DataSource, data: ICommonObj
     }
 }
 
-/**
- * Inserts documents from document store into the configured vector store.
- *
- * Process:
- * 1. Saves vector store configuration (embedding, vector store, record manager)
- * 2. Sets document store status to UPSERTING
- * 3. Performs the actual vector store upsert operation
- * 4. Updates status to UPSERTED upon completion
- */
 export const insertIntoVectorStore = async ({
     appDataSource,
     componentNodes,
@@ -1252,16 +1231,19 @@ export const insertIntoVectorStore = async ({
     workspaceId
 }: IExecuteVectorStoreInsert) => {
     try {
-        // Step 1: Save configuration based on isStrictSave mode
         const entity = await saveVectorStoreConfig(appDataSource, data, isStrictSave, workspaceId)
-
-        // Step 2: Mark as UPSERTING before starting the operation
         entity.status = DocumentStoreStatus.UPSERTING
         await appDataSource.getRepository(DocumentStore).save(entity)
 
-        // Step 3: Perform the actual vector store upsert
+        const indexResult = await _insertIntoVectorStoreWorkerThread(
-        // Note: Configuration already saved above, worker thread just retrieves and uses it
+            appDataSource,
-        const indexResult = await _insertIntoVectorStoreWorkerThread(appDataSource, componentNodes, telemetry, data, orgId, workspaceId)
+            componentNodes,
+            telemetry,
+            data,
+            isStrictSave,
+            orgId,
+            workspaceId
+        )
         return indexResult
     } catch (error) {
         throw new InternalFlowiseError(
@@ -1326,18 +1308,12 @@ const _insertIntoVectorStoreWorkerThread = async (
     componentNodes: IComponentNodes,
     telemetry: Telemetry,
     data: ICommonObject,
+    isStrictSave = true,
     orgId: string,
     workspaceId: string
 ) => {
     try {
-        // Configuration already saved by insertIntoVectorStore, just retrieve the entity
+        const entity = await saveVectorStoreConfig(appDataSource, data, isStrictSave, workspaceId)
-        const entity = await appDataSource.getRepository(DocumentStore).findOneBy({
-            id: data.storeId,
-            workspaceId: workspaceId
-        })
-        if (!entity) {
-            throw new InternalFlowiseError(StatusCodes.NOT_FOUND, `Document store ${data.storeId} not found`)
-        }
         let upsertHistory: Record<string, any> = {}
         const chatflowid = data.storeId // fake chatflowid because this is not tied to any chatflow
 
@@ -1374,10 +1350,7 @@ const _insertIntoVectorStoreWorkerThread = async (
         const docs: Document[] = chunks.map((chunk: DocumentStoreFileChunk) => {
             return new Document({
                 pageContent: chunk.pageContent,
-                metadata: {
+                metadata: JSON.parse(chunk.metadata)
-                    ...JSON.parse(chunk.metadata),
-                    docId: chunk.docId
-                }
             })
         })
         vStoreNodeData.inputs.document = docs
@@ -1938,8 +1911,6 @@ const upsertDocStore = async (
             recordManagerConfig
         }
 
-        // Use isStrictSave: false to preserve existing configurations during upsert
-        // This allows the operation to reuse existing embedding/vector store/record manager configs
         const res = await insertIntoVectorStore({
             appDataSource,
             componentNodes,

packages/server/src/utils/buildAgentflow.ts

@@ -2122,62 +2122,7 @@ export const executeAgentFlow = async ({
 
     // check if last agentFlowExecutedData.data.output contains the key "content"
     const lastNodeOutput = agentFlowExecutedData[agentFlowExecutedData.length - 1].data?.output as ICommonObject | undefined
-    let content = (lastNodeOutput?.content as string) ?? ' '
+    const content = (lastNodeOutput?.content as string) ?? ' '
-
-    /* Check for post-processing settings */
-    let chatflowConfig: ICommonObject = {}
-    try {
-        if (chatflow.chatbotConfig) {
-            chatflowConfig = typeof chatflow.chatbotConfig === 'string' ? JSON.parse(chatflow.chatbotConfig) : chatflow.chatbotConfig
-        }
-    } catch (e) {
-        logger.error('[server]: Error parsing chatflow config:', e)
-    }
-
-    if (chatflowConfig?.postProcessing?.enabled === true && content) {
-        try {
-            const postProcessingFunction = JSON.parse(chatflowConfig?.postProcessing?.customFunction)
-            const nodeInstanceFilePath = componentNodes['customFunctionAgentflow'].filePath as string
-            const nodeModule = await import(nodeInstanceFilePath)
-            //set the outputs.output to EndingNode to prevent json escaping of content...
-            const nodeData = {
-                inputs: { customFunctionJavascriptFunction: postProcessingFunction }
-            }
-            const runtimeChatHistory = agentflowRuntime.chatHistory || []
-            const chatHistory = [...pastChatHistory, ...runtimeChatHistory]
-            const options: ICommonObject = {
-                chatflowid: chatflow.id,
-                sessionId,
-                chatId,
-                input: question || form,
-                postProcessing: {
-                    rawOutput: content,
-                    chatHistory: cloneDeep(chatHistory),
-                    sourceDocuments: lastNodeOutput?.sourceDocuments ? cloneDeep(lastNodeOutput.sourceDocuments) : undefined,
-                    usedTools: lastNodeOutput?.usedTools ? cloneDeep(lastNodeOutput.usedTools) : undefined,
-                    artifacts: lastNodeOutput?.artifacts ? cloneDeep(lastNodeOutput.artifacts) : undefined,
-                    fileAnnotations: lastNodeOutput?.fileAnnotations ? cloneDeep(lastNodeOutput.fileAnnotations) : undefined
-                },
-                appDataSource,
-                databaseEntities,
-                workspaceId,
-                orgId,
-                logger
-            }
-            const customFuncNodeInstance = new nodeModule.nodeClass()
-            const customFunctionResponse = await customFuncNodeInstance.run(nodeData, question || form, options)
-            const moderatedResponse = customFunctionResponse.output.content
-            if (typeof moderatedResponse === 'string') {
-                content = moderatedResponse
-            } else if (typeof moderatedResponse === 'object') {
-                content = '```json\n' + JSON.stringify(moderatedResponse, null, 2) + '\n```'
-            } else {
-                content = moderatedResponse
-            }
-        } catch (e) {
-            logger.error('[server]: Post Processing Error:', e)
-        }
-    }
 
     // remove credentialId from agentFlowExecutedData
     agentFlowExecutedData = agentFlowExecutedData.map((data) => _removeCredentialId(data))

packages/server/src/utils/buildChatflow.ts

@@ -2,7 +2,7 @@ import { Request } from 'express'
 import * as path from 'path'
 import { DataSource } from 'typeorm'
 import { v4 as uuidv4 } from 'uuid'
-import { omit, cloneDeep } from 'lodash'
+import { omit } from 'lodash'
 import {
     IFileUpload,
     convertSpeechToText,
@@ -817,14 +817,7 @@ export const executeFlow = async ({
                         sessionId,
                         chatId,
                         input: question,
-                        postProcessing: {
+                        rawOutput: resultText,
-                            rawOutput: resultText,
-                            chatHistory: cloneDeep(chatHistory),
-                            sourceDocuments: result?.sourceDocuments ? cloneDeep(result.sourceDocuments) : undefined,
-                            usedTools: result?.usedTools ? cloneDeep(result.usedTools) : undefined,
-                            artifacts: result?.artifacts ? cloneDeep(result.artifacts) : undefined,
-                            fileAnnotations: result?.fileAnnotations ? cloneDeep(result.fileAnnotations) : undefined
-                        },
                         appDataSource,
                         databaseEntities,
                         workspaceId,

packages/server/src/utils/quotaUsage.ts

@@ -70,7 +70,7 @@ export const checkUsageLimit = async (
     if (limit === -1) return
 
     if (currentUsage > limit) {
-        throw new InternalFlowiseError(StatusCodes.PAYMENT_REQUIRED, `Limit exceeded: ${type}`)
+        throw new InternalFlowiseError(StatusCodes.TOO_MANY_REQUESTS, `Limit exceeded: ${type}`)
     }
 }
 
@@ -135,7 +135,7 @@ export const checkPredictions = async (orgId: string, subscriptionId: string, us
     if (predictionsLimit === -1) return
 
     if (currentPredictions >= predictionsLimit) {
-        throw new InternalFlowiseError(StatusCodes.PAYMENT_REQUIRED, 'Predictions limit exceeded')
+        throw new InternalFlowiseError(StatusCodes.TOO_MANY_REQUESTS, 'Predictions limit exceeded')
     }
 
     return {
@@ -161,7 +161,7 @@ export const checkStorage = async (orgId: string, subscriptionId: string, usageC
     if (storageLimit === -1) return
 
     if (currentStorageUsage >= storageLimit) {
-        throw new InternalFlowiseError(StatusCodes.PAYMENT_REQUIRED, 'Storage limit exceeded')
+        throw new InternalFlowiseError(StatusCodes.TOO_MANY_REQUESTS, 'Storage limit exceeded')
     }
 
     return {

packages/ui/src/api/documentstore.js

@@ -22,10 +22,7 @@ const refreshLoader = (storeId) => client.post(`/document-store/refresh/${storeI
 const insertIntoVectorStore = (body) => client.post(`/document-store/vectorstore/insert`, body)
 const saveVectorStoreConfig = (body) => client.post(`/document-store/vectorstore/save`, body)
 const updateVectorStoreConfig = (body) => client.post(`/document-store/vectorstore/update`, body)
-const deleteVectorStoreDataFromStore = (storeId, docId) => {
+const deleteVectorStoreDataFromStore = (storeId) => client.delete(`/document-store/vectorstore/${storeId}`)
-    const url = docId ? `/document-store/vectorstore/${storeId}?docId=${docId}` : `/document-store/vectorstore/${storeId}`
-    return client.delete(url)
-}
 const queryVectorStore = (body) => client.post(`/document-store/vectorstore/query`, body)
 const getVectorStoreProviders = () => client.get('/document-store/components/vectorstore')
 const getEmbeddingProviders = () => client.get('/document-store/components/embeddings')

packages/ui/src/routes/AuthRoutes.jsx

@@ -10,7 +10,6 @@ const VerifyEmailPage = Loadable(lazy(() => import('@/views/auth/verify-email'))
 const ForgotPasswordPage = Loadable(lazy(() => import('@/views/auth/forgotPassword')))
 const ResetPasswordPage = Loadable(lazy(() => import('@/views/auth/resetPassword')))
 const UnauthorizedPage = Loadable(lazy(() => import('@/views/auth/unauthorized')))
-const RateLimitedPage = Loadable(lazy(() => import('@/views/auth/rateLimited')))
 const OrganizationSetupPage = Loadable(lazy(() => import('@/views/organization/index')))
 const LicenseExpiredPage = Loadable(lazy(() => import('@/views/auth/expired')))
 
@@ -46,10 +45,6 @@ const AuthRoutes = {
             path: '/unauthorized',
             element: <UnauthorizedPage />
         },
-        {
-            path: '/rate-limited',
-            element: <RateLimitedPage />
-        },
         {
             path: '/organization-setup',
             element: <OrganizationSetupPage />

packages/ui/src/store/context/ErrorContext.jsx

@@ -10,29 +10,11 @@ const ErrorContext = createContext()
 
 export const ErrorProvider = ({ children }) => {
     const [error, setError] = useState(null)
-    const [authRateLimitError, setAuthRateLimitError] = useState(null)
     const navigate = useNavigate()
 
     const handleError = async (err) => {
         console.error(err)
-        if (err?.response?.status === 429 && err?.response?.data?.type === 'authentication_rate_limit') {
+        if (err?.response?.status === 403) {
-            setAuthRateLimitError("You're making a lot of requests. Please wait and try again later.")
-        } else if (err?.response?.status === 429 && err?.response?.data?.type !== 'authentication_rate_limit') {
-            const retryAfterHeader = err?.response?.headers?.['retry-after']
-            let retryAfter = 60 // Default in seconds
-            if (retryAfterHeader) {
-                const parsedSeconds = parseInt(retryAfterHeader, 10)
-                if (Number.isNaN(parsedSeconds)) {
-                    const retryDate = new Date(retryAfterHeader)
-                    if (!Number.isNaN(retryDate.getTime())) {
-                        retryAfter = Math.max(0, Math.ceil((retryDate.getTime() - Date.now()) / 1000))
-                    }
-                } else {
-                    retryAfter = parsedSeconds
-                }
-            }
-            navigate('/rate-limited', { state: { retryAfter } })
-        } else if (err?.response?.status === 403) {
             navigate('/unauthorized')
         } else if (err?.response?.status === 401) {
             if (ErrorMessage.INVALID_MISSING_TOKEN === err?.response?.data?.message) {
@@ -62,9 +44,7 @@ export const ErrorProvider = ({ children }) => {
             value={{
                 error,
                 setError,
-                handleError,
+                handleError
-                authRateLimitError,
-                setAuthRateLimitError
             }}
         >
             {children}

packages/ui/src/ui-component/button/FlowListMenu.jsx

@@ -74,7 +74,7 @@ const StyledMenu = styled((props) => (
     }
 }))
 
-export default function FlowListMenu({ chatflow, isAgentCanvas, isAgentflowV2, setError, updateFlowsApi, currentPage, pageLimit }) {
+export default function FlowListMenu({ chatflow, isAgentCanvas, isAgentflowV2, setError, updateFlowsApi }) {
     const { confirm } = useConfirm()
     const dispatch = useDispatch()
     const updateChatflowApi = useApi(chatflowsApi.updateChatflow)
@@ -166,16 +166,10 @@ export default function FlowListMenu({ chatflow, isAgentCanvas, isAgentflowV2, s
         }
         try {
             await updateChatflowApi.request(chatflow.id, updateBody)
-            const params = {
-                page: currentPage,
-                limit: pageLimit
-            }
             if (isAgentCanvas && isAgentflowV2) {
-                await updateFlowsApi.request('AGENTFLOW', params)
+                await updateFlowsApi.request('AGENTFLOW')
-            } else if (isAgentCanvas) {
-                await updateFlowsApi.request('MULTIAGENT', params)
             } else {
-                await updateFlowsApi.request(params)
+                await updateFlowsApi.request(isAgentCanvas ? 'MULTIAGENT' : undefined)
             }
         } catch (error) {
             if (setError) setError(error)
@@ -215,15 +209,7 @@ export default function FlowListMenu({ chatflow, isAgentCanvas, isAgentflowV2, s
         }
         try {
             await updateChatflowApi.request(chatflow.id, updateBody)
-            const params = {
+            await updateFlowsApi.request(isAgentCanvas ? 'AGENTFLOW' : undefined)
-                page: currentPage,
-                limit: pageLimit
-            }
-            if (isAgentCanvas) {
-                await updateFlowsApi.request('AGENTFLOW', params)
-            } else {
-                await updateFlowsApi.request(params)
-            }
         } catch (error) {
             if (setError) setError(error)
             enqueueSnackbar({
@@ -255,16 +241,10 @@ export default function FlowListMenu({ chatflow, isAgentCanvas, isAgentflowV2, s
         if (isConfirmed) {
             try {
                 await chatflowsApi.deleteChatflow(chatflow.id)
-                const params = {
-                    page: currentPage,
-                    limit: pageLimit
-                }
                 if (isAgentCanvas && isAgentflowV2) {
-                    await updateFlowsApi.request('AGENTFLOW', params)
+                    await updateFlowsApi.request('AGENTFLOW')
-                } else if (isAgentCanvas) {
-                    await updateFlowsApi.request('MULTIAGENT', params)
                 } else {
-                    await updateFlowsApi.request(params)
+                    await updateFlowsApi.request(isAgentCanvas ? 'MULTIAGENT' : undefined)
                 }
             } catch (error) {
                 if (setError) setError(error)
@@ -474,7 +454,5 @@ FlowListMenu.propTypes = {
     isAgentCanvas: PropTypes.bool,
     isAgentflowV2: PropTypes.bool,
     setError: PropTypes.func,
-    updateFlowsApi: PropTypes.object,
+    updateFlowsApi: PropTypes.object
-    currentPage: PropTypes.number,
-    pageLimit: PropTypes.number
 }

packages/ui/src/ui-component/dialog/ChatflowConfigurationDialog.jsx

@@ -53,7 +53,8 @@ const CHATFLOW_CONFIGURATION_TABS = [
     },
     {
         label: 'Post Processing',
-        id: 'postProcessing'
+        id: 'postProcessing',
+        hideInAgentFlow: true
     }
 ]
 

packages/ui/src/ui-component/dialog/ExpandRichInputDialog.jsx

@@ -16,11 +16,11 @@ import { useEditor, EditorContent } from '@tiptap/react'
 import Placeholder from '@tiptap/extension-placeholder'
 import { mergeAttributes } from '@tiptap/core'
 import StarterKit from '@tiptap/starter-kit'
+import Mention from '@tiptap/extension-mention'
 import CodeBlockLowlight from '@tiptap/extension-code-block-lowlight'
 import { common, createLowlight } from 'lowlight'
 import { suggestionOptions } from '@/ui-component/input/suggestionOption'
 import { getAvailableNodesForVariable } from '@/utils/genericHelper'
-import { CustomMention } from '@/utils/customMention'
 
 const lowlight = createLowlight(common)
 
@@ -78,7 +78,7 @@ const extensions = (availableNodesForVariable, availableState, acceptNodeOutputA
     StarterKit.configure({
         codeBlock: false
     }),
-    CustomMention.configure({
+    Mention.configure({
         HTMLAttributes: {
             class: 'variable'
         },

packages/ui/src/ui-component/extended/PostProcessing.jsx

@@ -4,25 +4,8 @@ import PropTypes from 'prop-types'
 import { useSelector } from 'react-redux'
 
 // material-ui
-import {
+import { IconButton, Button, Box, Typography } from '@mui/material'
-    IconButton,
+import { IconArrowsMaximize, IconBulb, IconX } from '@tabler/icons-react'
-    Button,
-    Box,
-    Typography,
-    TableContainer,
-    Table,
-    TableHead,
-    TableBody,
-    TableRow,
-    TableCell,
-    Paper,
-    Accordion,
-    AccordionSummary,
-    AccordionDetails,
-    Card
-} from '@mui/material'
-import { IconArrowsMaximize, IconX } from '@tabler/icons-react'
-import ExpandMoreIcon from '@mui/icons-material/ExpandMore'
 import { useTheme } from '@mui/material/styles'
 
 // Project import
@@ -38,11 +21,7 @@ import useNotifier from '@/utils/useNotifier'
 // API
 import chatflowsApi from '@/api/chatflows'
 
-const sampleFunction = `// Access chat history as a string
+const sampleFunction = `return $flow.rawOutput + " This is a post processed response!";`
-const chatHistory = JSON.stringify($flow.chatHistory, null, 2); 
-
-// Return a modified response
-return $flow.rawOutput + " This is a post processed response!";`
 
 const PostProcessing = ({ dialogProps }) => {
     const dispatch = useDispatch()
@@ -196,105 +175,31 @@ const PostProcessing = ({ dialogProps }) => {
                     />
                 </div>
             </Box>
-            <Card sx={{ borderColor: theme.palette.primary[200] + 75, mt: 2, mb: 2 }} variant='outlined'>
+            <div
-                <Accordion
+                style={{
-                    disableGutters
+                    display: 'flex',
-                    sx={{
+                    flexDirection: 'column',
-                        '&:before': {
+                    borderRadius: 10,
-                            display: 'none'
+                    background: '#d8f3dc',
-                        }
+                    padding: 10,
+                    marginTop: 10
+                }}
+            >
+                <div
+                    style={{
+                        display: 'flex',
+                        flexDirection: 'row',
+                        alignItems: 'center',
+                        paddingTop: 10
                     }}
                 >
-                    <AccordionSummary expandIcon={<ExpandMoreIcon />}>
+                    <IconBulb size={30} color='#2d6a4f' />
-                        <Typography>Available Variables</Typography>
+                    <span style={{ color: '#2d6a4f', marginLeft: 10, fontWeight: 500 }}>
-                    </AccordionSummary>
+                        The following variables are available to use in the custom function:{' '}
-                    <AccordionDetails sx={{ p: 0 }}>
+                        <pre>$flow.rawOutput, $flow.input, $flow.chatflowId, $flow.sessionId, $flow.chatId</pre>
-                        <TableContainer component={Paper}>
+                    </span>
-                            <Table aria-label='available variables table'>
+                </div>
-                                <TableHead>
+            </div>
-                                    <TableRow>
-                                        <TableCell sx={{ width: '30%' }}>Variable</TableCell>
-                                        <TableCell sx={{ width: '15%' }}>Type</TableCell>
-                                        <TableCell sx={{ width: '55%' }}>Description</TableCell>
-                                    </TableRow>
-                                </TableHead>
-                                <TableBody>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.rawOutput</code>
-                                        </TableCell>
-                                        <TableCell>string</TableCell>
-                                        <TableCell>The raw output response from the flow</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.input</code>
-                                        </TableCell>
-                                        <TableCell>string</TableCell>
-                                        <TableCell>The user input message</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.chatHistory</code>
-                                        </TableCell>
-                                        <TableCell>array</TableCell>
-                                        <TableCell>Array of previous messages in the conversation</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.chatflowId</code>
-                                        </TableCell>
-                                        <TableCell>string</TableCell>
-                                        <TableCell>Unique identifier for the chatflow</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.sessionId</code>
-                                        </TableCell>
-                                        <TableCell>string</TableCell>
-                                        <TableCell>Current session identifier</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.chatId</code>
-                                        </TableCell>
-                                        <TableCell>string</TableCell>
-                                        <TableCell>Current chat identifier</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.sourceDocuments</code>
-                                        </TableCell>
-                                        <TableCell>array</TableCell>
-                                        <TableCell>Source documents used in retrieval (if applicable)</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.usedTools</code>
-                                        </TableCell>
-                                        <TableCell>array</TableCell>
-                                        <TableCell>List of tools used during execution</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell>
-                                            <code>$flow.artifacts</code>
-                                        </TableCell>
-                                        <TableCell>array</TableCell>
-                                        <TableCell>List of artifacts generated during execution</TableCell>
-                                    </TableRow>
-                                    <TableRow>
-                                        <TableCell sx={{ borderBottom: 'none' }}>
-                                            <code>$flow.fileAnnotations</code>
-                                        </TableCell>
-                                        <TableCell sx={{ borderBottom: 'none' }}>array</TableCell>
-                                        <TableCell sx={{ borderBottom: 'none' }}>File annotations associated with the response</TableCell>
-                                    </TableRow>
-                                </TableBody>
-                            </Table>
-                        </TableContainer>
-                    </AccordionDetails>
-                </Accordion>
-            </Card>
             <StyledButton
                 style={{ marginBottom: 10, marginTop: 10 }}
                 variant='contained'

packages/ui/src/ui-component/input/RichInput.jsx

@@ -7,11 +7,11 @@ import { mergeAttributes } from '@tiptap/core'
 import StarterKit from '@tiptap/starter-kit'
 import { styled } from '@mui/material/styles'
 import { Box } from '@mui/material'
+import Mention from '@tiptap/extension-mention'
 import CodeBlockLowlight from '@tiptap/extension-code-block-lowlight'
 import { common, createLowlight } from 'lowlight'
 import { suggestionOptions } from './suggestionOption'
 import { getAvailableNodesForVariable } from '@/utils/genericHelper'
-import { CustomMention } from '@/utils/customMention'
 
 const lowlight = createLowlight(common)
 
@@ -20,7 +20,7 @@ const extensions = (availableNodesForVariable, availableState, acceptNodeOutputA
     StarterKit.configure({
         codeBlock: false
     }),
-    CustomMention.configure({
+    Mention.configure({
         HTMLAttributes: {
             class: 'variable'
         },

packages/ui/src/ui-component/input/suggestionOption.js

@@ -112,7 +112,7 @@ export const suggestionOptions = (
                 category: 'Node Outputs'
             })
 
-            const structuredOutputs = nodeData?.inputs?.llmStructuredOutput ?? nodeData?.inputs?.agentStructuredOutput ?? []
+            const structuredOutputs = nodeData?.inputs?.llmStructuredOutput ?? []
             if (structuredOutputs && structuredOutputs.length > 0) {
                 structuredOutputs.forEach((item) => {
                     defaultItems.unshift({

packages/ui/src/ui-component/table/FlowListTable.jsx

@@ -59,9 +59,7 @@ export const FlowListTable = ({
     updateFlowsApi,
     setError,
     isAgentCanvas,
-    isAgentflowV2,
+    isAgentflowV2
-    currentPage,
-    pageLimit
 }) => {
     const { hasPermission } = useAuth()
     const isActionsAvailable = isAgentCanvas
@@ -333,8 +331,6 @@ export const FlowListTable = ({
                                                         chatflow={row}
                                                         setError={setError}
                                                         updateFlowsApi={updateFlowsApi}
-                                                        currentPage={currentPage}
-                                                        pageLimit={pageLimit}
                                                     />
                                                 </Stack>
                                             </StyledTableCell>
@@ -359,7 +355,5 @@ FlowListTable.propTypes = {
     updateFlowsApi: PropTypes.object,
     setError: PropTypes.func,
     isAgentCanvas: PropTypes.bool,
-    isAgentflowV2: PropTypes.bool,
+    isAgentflowV2: PropTypes.bool
-    currentPage: PropTypes.number,
-    pageLimit: PropTypes.number
 }

packages/ui/src/utils/customMention.js

@@ -1,26 +0,0 @@
-import Mention from '@tiptap/extension-mention'
-import { PasteRule } from '@tiptap/core'
-
-export const CustomMention = Mention.extend({
-    renderText({ node }) {
-        return `{{${node.attrs.label ?? node.attrs.id}}}`
-    },
-    addPasteRules() {
-        return [
-            new PasteRule({
-                find: /\{\{([^{}]+)\}\}/g,
-                handler: ({ match, chain, range }) => {
-                    const label = match[1].trim()
-                    if (label) {
-                        chain()
-                            .deleteRange(range)
-                            .insertContentAt(range.from, {
-                                type: this.name,
-                                attrs: { id: label, label: label }
-                            })
-                    }
-                }
-            })
-        ]
-    }
-})

packages/ui/src/views/agentflows/index.jsx

@@ -325,8 +325,6 @@ const Agentflows = () => {
                                     filterFunction={filterFlows}
                                     updateFlowsApi={getAllAgentflows}
                                     setError={setError}
-                                    currentPage={currentPage}
-                                    pageLimit={pageLimit}
                                 />
                             )}
                             {/* Pagination and Page Size Controls */}

packages/ui/src/views/agentflowsv2/AgentFlowNode.jsx

@@ -150,8 +150,6 @@ const AgentFlowNode = ({ data }) => {
                 return <IconWorldWww size={14} color={'white'} />
             case 'googleSearch':
                 return <IconBrandGoogle size={14} color={'white'} />
-            case 'codeExecution':
-                return <IconCode size={14} color={'white'} />
             default:
                 return null
         }

packages/ui/src/views/auth/forgotPassword.jsx

@@ -16,7 +16,6 @@ import accountApi from '@/api/account.api'
 // Hooks
 import useApi from '@/hooks/useApi'
 import { useConfig } from '@/store/context/ConfigContext'
-import { useError } from '@/store/context/ErrorContext'
 
 // utils
 import useNotifier from '@/utils/useNotifier'
@@ -42,13 +41,10 @@ const ForgotPasswordPage = () => {
     const [isLoading, setLoading] = useState(false)
     const [responseMsg, setResponseMsg] = useState(undefined)
 
-    const { authRateLimitError, setAuthRateLimitError } = useError()
-
     const forgotPasswordApi = useApi(accountApi.forgotPassword)
 
     const sendResetRequest = async (event) => {
         event.preventDefault()
-        setAuthRateLimitError(null)
         const body = {
             user: {
                 email: usernameVal
@@ -58,11 +54,6 @@ const ForgotPasswordPage = () => {
         await forgotPasswordApi.request(body)
     }
 
-    useEffect(() => {
-        setAuthRateLimitError(null)
-        // eslint-disable-next-line react-hooks/exhaustive-deps
-    }, [setAuthRateLimitError])
-
     useEffect(() => {
         if (forgotPasswordApi.error) {
             const errMessage =
@@ -98,11 +89,6 @@ const ForgotPasswordPage = () => {
                             {responseMsg.msg}
                         </Alert>
                     )}
-                    {authRateLimitError && (
-                        <Alert icon={<IconExclamationCircle />} variant='filled' severity='error'>
-                            {authRateLimitError}
-                        </Alert>
-                    )}
                     {responseMsg && responseMsg?.type !== 'error' && (
                         <Alert icon={<IconCircleCheck />} variant='filled' severity='success'>
                             {responseMsg.msg}

packages/ui/src/views/auth/rateLimited.jsx

@@ -1,51 +0,0 @@
-import { Box, Button, Stack, Typography } from '@mui/material'
-import { Link, useLocation } from 'react-router-dom'
-import unauthorizedSVG from '@/assets/images/unauthorized.svg'
-import MainCard from '@/ui-component/cards/MainCard'
-
-// ==============================|| RateLimitedPage ||============================== //
-
-const RateLimitedPage = () => {
-    const location = useLocation()
-
-    const retryAfter = location.state?.retryAfter || 60
-
-    return (
-        <MainCard>
-            <Box
-                sx={{
-                    display: 'flex',
-                    justifyContent: 'center',
-                    alignItems: 'center',
-                    height: 'calc(100vh - 210px)'
-                }}
-            >
-                <Stack
-                    sx={{
-                        alignItems: 'center',
-                        justifyContent: 'center',
-                        maxWidth: '500px'
-                    }}
-                    flexDirection='column'
-                >
-                    <Box sx={{ p: 2, height: 'auto' }}>
-                        <img style={{ objectFit: 'cover', height: '20vh', width: 'auto' }} src={unauthorizedSVG} alt='rateLimitedSVG' />
-                    </Box>
-                    <Typography sx={{ mb: 2 }} variant='h4' component='div' fontWeight='bold'>
-                        429 Too Many Requests
-                    </Typography>
-                    <Typography variant='body1' component='div' sx={{ mb: 2, textAlign: 'center' }}>
-                        {`You have made too many requests in a short period of time. Please wait ${retryAfter}s before trying again.`}
-                    </Typography>
-                    <Link to='/'>
-                        <Button variant='contained' color='primary'>
-                            Back to Home
-                        </Button>
-                    </Link>
-                </Stack>
-            </Box>
-        </MainCard>
-    )
-}
-
-export default RateLimitedPage

packages/ui/src/views/auth/register.jsx

@@ -18,7 +18,6 @@ import ssoApi from '@/api/sso'
 // Hooks
 import useApi from '@/hooks/useApi'
 import { useConfig } from '@/store/context/ConfigContext'
-import { useError } from '@/store/context/ErrorContext'
 
 // utils
 import useNotifier from '@/utils/useNotifier'
@@ -112,9 +111,7 @@ const RegisterPage = () => {
 
     const [loading, setLoading] = useState(false)
     const [authError, setAuthError] = useState('')
-    const [successMsg, setSuccessMsg] = useState('')
+    const [successMsg, setSuccessMsg] = useState(undefined)
-
-    const { authRateLimitError, setAuthRateLimitError } = useError()
 
     const registerApi = useApi(accountApi.registerAccount)
     const ssoLoginApi = useApi(ssoApi.ssoLogin)
@@ -123,7 +120,6 @@ const RegisterPage = () => {
 
     const register = async (event) => {
         event.preventDefault()
-        setAuthRateLimitError(null)
         if (isEnterpriseLicensed) {
             const result = RegisterEnterpriseUserSchema.safeParse({
                 username,
@@ -196,7 +192,6 @@ const RegisterPage = () => {
     }, [registerApi.error])
 
     useEffect(() => {
-        setAuthRateLimitError(null)
         if (!isOpenSource) {
             getDefaultProvidersApi.request()
         }
@@ -279,11 +274,6 @@ const RegisterPage = () => {
                             )}
                         </Alert>
                     )}
-                    {authRateLimitError && (
-                        <Alert icon={<IconExclamationCircle />} variant='filled' severity='error'>
-                            {authRateLimitError}
-                        </Alert>
-                    )}
                     {successMsg && (
                         <Alert icon={<IconCircleCheck />} variant='filled' severity='success'>
                             {successMsg}

packages/ui/src/views/auth/resetPassword.jsx

@@ -1,4 +1,4 @@
-import { useEffect, useState } from 'react'
+import { useState } from 'react'
 import { useDispatch } from 'react-redux'
 import { Link, useNavigate, useSearchParams } from 'react-router-dom'
 
@@ -19,9 +19,6 @@ import accountApi from '@/api/account.api'
 import useNotifier from '@/utils/useNotifier'
 import { validatePassword } from '@/utils/validation'
 
-// Hooks
-import { useError } from '@/store/context/ErrorContext'
-
 // Icons
 import { IconExclamationCircle, IconX } from '@tabler/icons-react'
 
@@ -73,8 +70,6 @@ const ResetPasswordPage = () => {
     const [loading, setLoading] = useState(false)
     const [authErrors, setAuthErrors] = useState([])
 
-    const { authRateLimitError, setAuthRateLimitError } = useError()
-
     const goLogin = () => {
         navigate('/signin', { replace: true })
     }
@@ -83,7 +78,6 @@ const ResetPasswordPage = () => {
         event.preventDefault()
         const validationErrors = []
         setAuthErrors([])
-        setAuthRateLimitError(null)
         if (!tokenVal) {
             validationErrors.push('Token cannot be left blank!')
         }
@@ -148,11 +142,6 @@ const ResetPasswordPage = () => {
         }
     }
 
-    useEffect(() => {
-        setAuthRateLimitError(null)
-        // eslint-disable-next-line react-hooks/exhaustive-deps
-    }, [])
-
     return (
         <>
             <MainCard>
@@ -166,11 +155,6 @@ const ResetPasswordPage = () => {
                             </ul>
                         </Alert>
                     )}
-                    {authRateLimitError && (
-                        <Alert icon={<IconExclamationCircle />} variant='filled' severity='error'>
-                            {authRateLimitError}
-                        </Alert>
-                    )}
                     <Stack sx={{ gap: 1 }}>
                         <Typography variant='h1'>Reset Password</Typography>
                         <Typography variant='body2' sx={{ color: theme.palette.grey[600] }}>

packages/ui/src/views/auth/signIn.jsx

@@ -14,7 +14,6 @@ import { Input } from '@/ui-component/input/Input'
 // Hooks
 import useApi from '@/hooks/useApi'
 import { useConfig } from '@/store/context/ConfigContext'
-import { useError } from '@/store/context/ErrorContext'
 
 // API
 import authApi from '@/api/auth'
@@ -63,8 +62,6 @@ const SignInPage = () => {
     const [showResendButton, setShowResendButton] = useState(false)
     const [successMessage, setSuccessMessage] = useState('')
 
-    const { authRateLimitError, setAuthRateLimitError } = useError()
-
     const loginApi = useApi(authApi.login)
     const ssoLoginApi = useApi(ssoApi.ssoLogin)
     const getDefaultProvidersApi = useApi(loginMethodApi.getDefaultLoginMethods)
@@ -74,7 +71,6 @@ const SignInPage = () => {
 
     const doLogin = (event) => {
         event.preventDefault()
-        setAuthRateLimitError(null)
         setLoading(true)
         const body = {
             email: usernameVal,
@@ -96,12 +92,11 @@ const SignInPage = () => {
 
     useEffect(() => {
         store.dispatch(logoutSuccess())
-        setAuthRateLimitError(null)
         if (!isOpenSource) {
             getDefaultProvidersApi.request()
         }
         // eslint-disable-next-line react-hooks/exhaustive-deps
-    }, [setAuthRateLimitError, isOpenSource])
+    }, [])
 
     useEffect(() => {
         // Parse the "user" query parameter from the URL
@@ -184,11 +179,6 @@ const SignInPage = () => {
                             {successMessage}
                         </Alert>
                     )}
-                    {authRateLimitError && (
-                        <Alert icon={<IconExclamationCircle />} variant='filled' severity='error'>
-                            {authRateLimitError}
-                        </Alert>
-                    )}
                     {authError && (
                         <Alert icon={<IconExclamationCircle />} variant='filled' severity='error'>
                             {authError}

packages/ui/src/views/chatflows/index.jsx

@@ -208,8 +208,6 @@ const Chatflows = () => {
                                     filterFunction={filterFlows}
                                     updateFlowsApi={getAllChatflowsApi}
                                     setError={setError}
-                                    currentPage={currentPage}
-                                    pageLimit={pageLimit}
                                 />
                             )}
                             {/* Pagination and Page Size Controls */}

packages/ui/src/views/docstore/DeleteDocStoreDialog.jsx

@@ -18,15 +18,11 @@ import {
     TableContainer,
     TableRow,
     TableCell,
-    DialogActions,
+    Checkbox,
-    Card,
+    FormControlLabel,
-    Stack,
+    DialogActions
-    Link
 } from '@mui/material'
-import { useTheme } from '@mui/material/styles'
 import ExpandMoreIcon from '@mui/icons-material/ExpandMore'
-import SettingsIcon from '@mui/icons-material/Settings'
-import { IconAlertTriangle } from '@tabler/icons-react'
 import { TableViewOnly } from '@/ui-component/table/Table'
 import { v4 as uuidv4 } from 'uuid'
 
@@ -40,13 +36,12 @@ import { initNode } from '@/utils/genericHelper'
 
 const DeleteDocStoreDialog = ({ show, dialogProps, onCancel, onDelete }) => {
     const portalElement = document.getElementById('portal')
-    const theme = useTheme()
     const [nodeConfigExpanded, setNodeConfigExpanded] = useState({})
+    const [removeFromVS, setRemoveFromVS] = useState(false)
     const [vsFlowData, setVSFlowData] = useState([])
     const [rmFlowData, setRMFlowData] = useState([])
 
-    const getVectorStoreNodeApi = useApi(nodesApi.getSpecificNode)
+    const getSpecificNodeApi = useApi(nodesApi.getSpecificNode)
-    const getRecordManagerNodeApi = useApi(nodesApi.getSpecificNode)
 
     const handleAccordionChange = (nodeName) => (event, isExpanded) => {
         const accordianNodes = { ...nodeConfigExpanded }
@@ -57,37 +52,42 @@ const DeleteDocStoreDialog = ({ show, dialogProps, onCancel, onDelete }) => {
     useEffect(() => {
         if (dialogProps.recordManagerConfig) {
             const nodeName = dialogProps.recordManagerConfig.name
-            if (nodeName) getRecordManagerNodeApi.request(nodeName)
+            if (nodeName) getSpecificNodeApi.request(nodeName)
-        }
 
-        if (dialogProps.vectorStoreConfig) {
+            if (dialogProps.vectorStoreConfig) {
-            const nodeName = dialogProps.vectorStoreConfig.name
+                const nodeName = dialogProps.vectorStoreConfig.name
-            if (nodeName) getVectorStoreNodeApi.request(nodeName)
+                if (nodeName) getSpecificNodeApi.request(nodeName)
+            }
         }
 
         return () => {
             setNodeConfigExpanded({})
+            setRemoveFromVS(false)
             setVSFlowData([])
             setRMFlowData([])
         }
         // eslint-disable-next-line react-hooks/exhaustive-deps
     }, [dialogProps])
 
-    // Process Vector Store node data
     useEffect(() => {
-        if (getVectorStoreNodeApi.data && dialogProps.vectorStoreConfig) {
+        if (getSpecificNodeApi.data) {
-            const nodeData = cloneDeep(initNode(getVectorStoreNodeApi.data, uuidv4()))
+            const nodeData = cloneDeep(initNode(getSpecificNodeApi.data, uuidv4()))
+
+            let config = 'vectorStoreConfig'
+            if (nodeData.category === 'Record Manager') config = 'recordManagerConfig'
 
             const paramValues = []
 
-            for (const inputName in dialogProps.vectorStoreConfig.config) {
+            for (const inputName in dialogProps[config].config) {
                 const inputParam = nodeData.inputParams.find((inp) => inp.name === inputName)
 
                 if (!inputParam) continue
 
                 if (inputParam.type === 'credential') continue
 
-                const inputValue = dialogProps.vectorStoreConfig.config[inputName]
+                let paramValue = {}
+
+                const inputValue = dialogProps[config].config[inputName]
 
                 if (!inputValue) continue
 
@@ -95,71 +95,40 @@ const DeleteDocStoreDialog = ({ show, dialogProps, onCancel, onDelete }) => {
                     continue
                 }
 
-                paramValues.push({
+                paramValue = {
                     label: inputParam?.label,
                     name: inputParam?.name,
                     type: inputParam?.type,
                     value: inputValue
-                })
+                }
+                paramValues.push(paramValue)
             }
 
-            setVSFlowData([
+            if (config === 'vectorStoreConfig') {
-                {
+                setVSFlowData([
-                    label: nodeData.label,
+                    {
-                    name: nodeData.name,
+                        label: nodeData.label,
-                    category: nodeData.category,
+                        name: nodeData.name,
-                    id: nodeData.id,
+                        category: nodeData.category,
-                    paramValues
+                        id: nodeData.id,
-                }
+                        paramValues
-            ])
+                    }
+                ])
+            } else if (config === 'recordManagerConfig') {
+                setRMFlowData([
+                    {
+                        label: nodeData.label,
+                        name: nodeData.name,
+                        category: nodeData.category,
+                        id: nodeData.id,
+                        paramValues
+                    }
+                ])
+            }
         }
 
         // eslint-disable-next-line react-hooks/exhaustive-deps
-    }, [getVectorStoreNodeApi.data])
+    }, [getSpecificNodeApi.data])
-
-    // Process Record Manager node data
-    useEffect(() => {
-        if (getRecordManagerNodeApi.data && dialogProps.recordManagerConfig) {
-            const nodeData = cloneDeep(initNode(getRecordManagerNodeApi.data, uuidv4()))
-
-            const paramValues = []
-
-            for (const inputName in dialogProps.recordManagerConfig.config) {
-                const inputParam = nodeData.inputParams.find((inp) => inp.name === inputName)
-
-                if (!inputParam) continue
-
-                if (inputParam.type === 'credential') continue
-
-                const inputValue = dialogProps.recordManagerConfig.config[inputName]
-
-                if (!inputValue) continue
-
-                if (typeof inputValue === 'string' && inputValue.startsWith('{{') && inputValue.endsWith('}}')) {
-                    continue
-                }
-
-                paramValues.push({
-                    label: inputParam?.label,
-                    name: inputParam?.name,
-                    type: inputParam?.type,
-                    value: inputValue
-                })
-            }
-
-            setRMFlowData([
-                {
-                    label: nodeData.label,
-                    name: nodeData.name,
-                    category: nodeData.category,
-                    id: nodeData.id,
-                    paramValues
-                }
-            ])
-        }
-
-        // eslint-disable-next-line react-hooks/exhaustive-deps
-    }, [getRecordManagerNodeApi.data])
 
     const component = show ? (
         <Dialog
@@ -173,130 +142,91 @@ const DeleteDocStoreDialog = ({ show, dialogProps, onCancel, onDelete }) => {
             <DialogTitle sx={{ fontSize: '1rem', p: 3, pb: 0 }} id='alert-dialog-title'>
                 {dialogProps.title}
             </DialogTitle>
-            <DialogContent
+            <DialogContent sx={{ display: 'flex', flexDirection: 'column', gap: 2, maxHeight: '75vh', position: 'relative', px: 3, pb: 3 }}>
-                sx={{
-                    display: 'flex',
-                    flexDirection: 'column',
-                    gap: 2,
-                    maxHeight: '75vh',
-                    position: 'relative',
-                    px: 3,
-                    pb: 3,
-                    overflow: 'auto'
-                }}
-            >
                 <span style={{ marginTop: '20px' }}>{dialogProps.description}</span>
-                {dialogProps.vectorStoreConfig && !dialogProps.recordManagerConfig && (
+                {dialogProps.type === 'STORE' && dialogProps.recordManagerConfig && (
-                    <div
+                    <FormControlLabel
-                        style={{
+                        control={<Checkbox checked={removeFromVS} onChange={(event) => setRemoveFromVS(event.target.checked)} />}
-                            display: 'flex',
+                        label='Remove data from vector store and record manager'
-                            flexDirection: 'row',
+                    />
-                            alignItems: 'center',
-                            borderRadius: 10,
-                            background: 'rgb(254,252,191)',
-                            padding: 10
-                        }}
-                    >
-                        <IconAlertTriangle size={70} color='orange' />
-                        <span style={{ color: 'rgb(116,66,16)', marginLeft: 10 }}>
-                            <strong>Note:</strong> Without a Record Manager configured, only the document chunks will be removed from the
-                            document store. The actual vector embeddings in your vector store database will remain unchanged. To enable
-                            automatic cleanup of vector store data, please configure a Record Manager.{' '}
-                            <Link
-                                href='https://docs.flowiseai.com/integrations/langchain/record-managers'
-                                target='_blank'
-                                rel='noopener noreferrer'
-                                sx={{ fontWeight: 500, color: 'rgb(116,66,16)', textDecoration: 'underline' }}
-                            >
-                                Learn more
-                            </Link>
-                        </span>
-                    </div>
                 )}
-                {vsFlowData && vsFlowData.length > 0 && rmFlowData && rmFlowData.length > 0 && (
+                {removeFromVS && (
-                    <Card sx={{ borderColor: theme.palette.primary[200] + 75, p: 2 }} variant='outlined'>
+                    <div>
-                        <Stack sx={{ mt: 1, mb: 2, ml: 1, alignItems: 'center' }} direction='row' spacing={2}>
+                        <TableContainer component={Paper}>
-                            <SettingsIcon />
+                            <Table sx={{ minWidth: 650 }} aria-label='simple table'>
-                            <Typography variant='h4'>Configuration</Typography>
+                                <TableBody>
-                        </Stack>
+                                    <TableRow sx={{ '& td': { border: 0 } }}>
-                        <Stack direction='column'>
+                                        <TableCell sx={{ pb: 0, pt: 0 }} colSpan={6}>
-                            <TableContainer component={Paper} sx={{ maxHeight: '400px', overflow: 'auto' }}>
+                                            <Box>
-                                <Table sx={{ minWidth: 650 }} aria-label='simple table'>
+                                                {([...vsFlowData, ...rmFlowData] || []).map((node, index) => {
-                                    <TableBody>
+                                                    return (
-                                        <TableRow sx={{ '& td': { border: 0 } }}>
+                                                        <Accordion
-                                            <TableCell sx={{ pb: 0, pt: 0 }} colSpan={6}>
+                                                            expanded={nodeConfigExpanded[node.name] || true}
-                                                <Box>
+                                                            onChange={handleAccordionChange(node.name)}
-                                                    {([...vsFlowData, ...rmFlowData] || []).map((node, index) => {
+                                                            key={index}
-                                                        return (
+                                                            disableGutters
-                                                            <Accordion
+                                                        >
-                                                                expanded={nodeConfigExpanded[node.name] || false}
+                                                            <AccordionSummary
-                                                                onChange={handleAccordionChange(node.name)}
+                                                                expandIcon={<ExpandMoreIcon />}
-                                                                key={index}
+                                                                aria-controls={`nodes-accordian-${node.name}`}
-                                                                disableGutters
+                                                                id={`nodes-accordian-header-${node.name}`}
                                                             >
-                                                                <AccordionSummary
+                                                                <div
-                                                                    expandIcon={<ExpandMoreIcon />}
+                                                                    style={{ display: 'flex', flexDirection: 'row', alignItems: 'center' }}
-                                                                    aria-controls={`nodes-accordian-${node.name}`}
-                                                                    id={`nodes-accordian-header-${node.name}`}
                                                                 >
                                                                     <div
                                                                         style={{
-                                                                            display: 'flex',
+                                                                            width: 40,
-                                                                            flexDirection: 'row',
+                                                                            height: 40,
-                                                                            alignItems: 'center'
+                                                                            marginRight: 10,
+                                                                            borderRadius: '50%',
+                                                                            backgroundColor: 'white'
                                                                         }}
                                                                     >
-                                                                        <div
+                                                                        <img
                                                                             style={{
-                                                                                width: 40,
+                                                                                width: '100%',
-                                                                                height: 40,
+                                                                                height: '100%',
-                                                                                marginRight: 10,
+                                                                                padding: 7,
                                                                                 borderRadius: '50%',
-                                                                                backgroundColor: 'white'
+                                                                                objectFit: 'contain'
                                                                             }}
-                                                                        >
+                                                                            alt={node.name}
-                                                                            <img
+                                                                            src={`${baseURL}/api/v1/node-icon/${node.name}`}
-                                                                                style={{
-                                                                                    width: '100%',
-                                                                                    height: '100%',
-                                                                                    padding: 7,
-                                                                                    borderRadius: '50%',
-                                                                                    objectFit: 'contain'
-                                                                                }}
-                                                                                alt={node.name}
-                                                                                src={`${baseURL}/api/v1/node-icon/${node.name}`}
-                                                                            />
-                                                                        </div>
-                                                                        <Typography variant='h5'>{node.label}</Typography>
-                                                                    </div>
-                                                                </AccordionSummary>
-                                                                <AccordionDetails sx={{ p: 0 }}>
-                                                                    {node.paramValues[0] && (
-                                                                        <TableViewOnly
-                                                                            sx={{ minWidth: 150 }}
-                                                                            rows={node.paramValues}
-                                                                            columns={Object.keys(node.paramValues[0])}
                                                                         />
-                                                                    )}
+                                                                    </div>
-                                                                </AccordionDetails>
+                                                                    <Typography variant='h5'>{node.label}</Typography>
-                                                            </Accordion>
+                                                                </div>
-                                                        )
+                                                            </AccordionSummary>
-                                                    })}
+                                                            <AccordionDetails>
-                                                </Box>
+                                                                {node.paramValues[0] && (
-                                            </TableCell>
+                                                                    <TableViewOnly
-                                        </TableRow>
+                                                                        sx={{ minWidth: 150 }}
-                                    </TableBody>
+                                                                        rows={node.paramValues}
-                                </Table>
+                                                                        columns={Object.keys(node.paramValues[0])}
-                            </TableContainer>
+                                                                    />
-                        </Stack>
+                                                                )}
-                    </Card>
+                                                            </AccordionDetails>
+                                                        </Accordion>
+                                                    )
+                                                })}
+                                            </Box>
+                                        </TableCell>
+                                    </TableRow>
+                                </TableBody>
+                            </Table>
+                        </TableContainer>
+                        <span style={{ marginTop: '30px', fontStyle: 'italic', color: '#b35702' }}>
+                            * Only data that were upserted with Record Manager will be deleted from vector store
+                        </span>
+                    </div>
                 )}
             </DialogContent>
             <DialogActions sx={{ pr: 3, pb: 3 }}>
                 <Button onClick={onCancel} color='primary'>
                     Cancel
                 </Button>
-                <Button variant='contained' onClick={() => onDelete(dialogProps.type, dialogProps.file)} color='error'>
+                <Button variant='contained' onClick={() => onDelete(dialogProps.type, dialogProps.file, removeFromVS)} color='error'>
                     Delete
                 </Button>
             </DialogActions>

packages/ui/src/views/docstore/DocumentStoreDetail.jsx

@@ -186,19 +186,19 @@ const DocumentStoreDetails = () => {
         setShowDocumentLoaderListDialog(true)
     }
 
-    const deleteVectorStoreDataFromStore = async (storeId, docId) => {
+    const deleteVectorStoreDataFromStore = async (storeId) => {
         try {
-            await documentsApi.deleteVectorStoreDataFromStore(storeId, docId)
+            await documentsApi.deleteVectorStoreDataFromStore(storeId)
         } catch (error) {
             console.error(error)
         }
     }
 
-    const onDocStoreDelete = async (type, file) => {
+    const onDocStoreDelete = async (type, file, removeFromVectorStore) => {
         setBackdropLoading(true)
         setShowDeleteDocStoreDialog(false)
         if (type === 'STORE') {
-            if (documentStore.recordManagerConfig) {
+            if (removeFromVectorStore) {
                 await deleteVectorStoreDataFromStore(storeId)
             }
             try {
@@ -239,9 +239,6 @@ const DocumentStoreDetails = () => {
                 })
             }
         } else if (type === 'LOADER') {
-            if (documentStore.recordManagerConfig) {
-                await deleteVectorStoreDataFromStore(storeId, file.id)
-            }
             try {
                 const deleteResp = await documentsApi.deleteLoaderFromStore(storeId, file.id)
                 setBackdropLoading(false)
@@ -283,40 +280,9 @@ const DocumentStoreDetails = () => {
     }
 
     const onLoaderDelete = (file, vectorStoreConfig, recordManagerConfig) => {
-        // Get the display name in the format "LoaderName (sourceName)"
-        const loaderName = file.loaderName || 'Unknown'
-        let sourceName = ''
-
-        // Prefer files.name when files array exists and has items
-        if (file.files && Array.isArray(file.files) && file.files.length > 0) {
-            sourceName = file.files.map((f) => f.name).join(', ')
-        } else if (file.source) {
-            // Fallback to source logic
-            if (typeof file.source === 'string' && file.source.includes('base64')) {
-                sourceName = getFileName(file.source)
-            } else if (typeof file.source === 'string' && file.source.startsWith('[') && file.source.endsWith(']')) {
-                sourceName = JSON.parse(file.source).join(', ')
-            } else if (typeof file.source === 'string') {
-                sourceName = file.source
-            }
-        }
-
-        const displayName = sourceName ? `${loaderName} (${sourceName})` : loaderName
-
-        let description = `Delete "${displayName}"? This will delete all the associated document chunks from the document store.`
-
-        if (
-            recordManagerConfig &&
-            vectorStoreConfig &&
-            Object.keys(recordManagerConfig).length > 0 &&
-            Object.keys(vectorStoreConfig).length > 0
-        ) {
-            description = `Delete "${displayName}"? This will delete all the associated document chunks from the document store and remove the actual data from the vector store database.`
-        }
-
         const props = {
             title: `Delete`,
-            description,
+            description: `Delete Loader ${file.loaderName} ? This will delete all the associated document chunks.`,
             vectorStoreConfig,
             recordManagerConfig,
             type: 'LOADER',
@@ -328,20 +294,9 @@ const DocumentStoreDetails = () => {
     }
 
     const onStoreDelete = (vectorStoreConfig, recordManagerConfig) => {
-        let description = `Delete Store ${getSpecificDocumentStore.data?.name}? This will delete all the associated loaders and document chunks from the document store.`
-
-        if (
-            recordManagerConfig &&
-            vectorStoreConfig &&
-            Object.keys(recordManagerConfig).length > 0 &&
-            Object.keys(vectorStoreConfig).length > 0
-        ) {
-            description = `Delete Store ${getSpecificDocumentStore.data?.name}? This will delete all the associated loaders and document chunks from the document store, and remove the actual data from the vector store database.`
-        }
-
         const props = {
             title: `Delete`,
-            description,
+            description: `Delete Store ${getSpecificDocumentStore.data?.name} ? This will delete all the associated loaders and document chunks.`,
             vectorStoreConfig,
             recordManagerConfig,
             type: 'STORE'
@@ -526,10 +481,7 @@ const DocumentStoreDetails = () => {
                             >
                                 <MenuItem
                                     disabled={documentStore?.totalChunks <= 0 || documentStore?.status === 'UPSERTING'}
-                                    onClick={() => {
+                                    onClick={() => showStoredChunks('all')}
-                                        handleClose()
-                                        showStoredChunks('all')
-                                    }}
                                     disableRipple
                                 >
                                     <FileChunksIcon />
@@ -538,10 +490,7 @@ const DocumentStoreDetails = () => {
                                 <Available permission={'documentStores:upsert-config'}>
                                     <MenuItem
                                         disabled={documentStore?.totalChunks <= 0 || documentStore?.status === 'UPSERTING'}
-                                        onClick={() => {
+                                        onClick={() => showVectorStore(documentStore.id)}
-                                            handleClose()
-                                            showVectorStore(documentStore.id)
-                                        }}
                                         disableRipple
                                     >
                                         <NoteAddIcon />
@@ -550,10 +499,7 @@ const DocumentStoreDetails = () => {
                                 </Available>
                                 <MenuItem
                                     disabled={documentStore?.totalChunks <= 0 || documentStore?.status !== 'UPSERTED'}
-                                    onClick={() => {
+                                    onClick={() => showVectorStoreQuery(documentStore.id)}
-                                        handleClose()
-                                        showVectorStoreQuery(documentStore.id)
-                                    }}
                                     disableRipple
                                 >
                                     <SearchIcon />
@@ -572,10 +518,7 @@ const DocumentStoreDetails = () => {
                                 </Available>
                                 <Divider sx={{ my: 0.5 }} />
                                 <MenuItem
-                                    onClick={() => {
+                                    onClick={() => onStoreDelete(documentStore.vectorStoreConfig, documentStore.recordManagerConfig)}
-                                        handleClose()
-                                        onStoreDelete(documentStore.vectorStoreConfig, documentStore.recordManagerConfig)
-                                    }}
                                     disableRipple
                                 >
                                     <FileDeleteIcon />
@@ -813,26 +756,20 @@ function LoaderRow(props) {
         setAnchorEl(null)
     }
 
-    const formatSources = (files, source, loaderName) => {
+    const formatSources = (files, source) => {
-        let sourceName = ''
-
         // Prefer files.name when files array exists and has items
         if (files && Array.isArray(files) && files.length > 0) {
-            sourceName = files.map((file) => file.name).join(', ')
+            return files.map((file) => file.name).join(', ')
-        } else if (source && typeof source === 'string' && source.includes('base64')) {
-            // Fallback to original source logic
-            sourceName = getFileName(source)
-        } else if (source && typeof source === 'string' && source.startsWith('[') && source.endsWith(']')) {
-            sourceName = JSON.parse(source).join(', ')
-        } else if (source) {
-            sourceName = source
         }
 
-        // Return format: "LoaderName (sourceName)" or just "LoaderName" if no source
+        // Fallback to original source logic
-        if (!sourceName) {
+        if (source && typeof source === 'string' && source.includes('base64')) {
-            return loaderName || 'No source'
+            return getFileName(source)
         }
-        return loaderName ? `${loaderName} (${sourceName})` : sourceName
+        if (source && typeof source === 'string' && source.startsWith('[') && source.endsWith(']')) {
+            return JSON.parse(source).join(', ')
+        }
+        return source || 'No source'
     }
 
     return (
@@ -886,62 +823,32 @@ function LoaderRow(props) {
                                 onClose={handleClose}
                             >
                                 <Available permission={'documentStores:preview-process'}>
-                                    <MenuItem
+                                    <MenuItem onClick={props.onEditClick} disableRipple>
-                                        onClick={() => {
-                                            handleClose()
-                                            props.onEditClick()
-                                        }}
-                                        disableRipple
-                                    >
                                         <FileEditIcon />
                                         Preview & Process
                                     </MenuItem>
                                 </Available>
                                 <Available permission={'documentStores:preview-process'}>
-                                    <MenuItem
+                                    <MenuItem onClick={props.onViewChunksClick} disableRipple>
-                                        onClick={() => {
-                                            handleClose()
-                                            props.onViewChunksClick()
-                                        }}
-                                        disableRipple
-                                    >
                                         <FileChunksIcon />
                                         View & Edit Chunks
                                     </MenuItem>
                                 </Available>
                                 <Available permission={'documentStores:preview-process'}>
-                                    <MenuItem
+                                    <MenuItem onClick={props.onChunkUpsert} disableRipple>
-                                        onClick={() => {
-                                            handleClose()
-                                            props.onChunkUpsert()
-                                        }}
-                                        disableRipple
-                                    >
                                         <NoteAddIcon />
                                         Upsert Chunks
                                     </MenuItem>
                                 </Available>
                                 <Available permission={'documentStores:preview-process'}>
-                                    <MenuItem
+                                    <MenuItem onClick={props.onViewUpsertAPI} disableRipple>
-                                        onClick={() => {
-                                            handleClose()
-                                            props.onViewUpsertAPI()
-                                        }}
-                                        disableRipple
-                                    >
                                         <CodeIcon />
                                         View API
                                     </MenuItem>
                                 </Available>
                                 <Divider sx={{ my: 0.5 }} />
                                 <Available permission={'documentStores:delete-loader'}>
-                                    <MenuItem
+                                    <MenuItem onClick={props.onDeleteClick} disableRipple>
-                                        onClick={() => {
-                                            handleClose()
-                                            props.onDeleteClick()
-                                        }}
-                                        disableRipple
-                                    >
                                         <FileDeleteIcon />
                                         Delete
                                     </MenuItem>

packages/ui/src/views/docstore/ShowStoredChunks.jsx

@@ -26,7 +26,6 @@ import useApi from '@/hooks/useApi'
 import useConfirm from '@/hooks/useConfirm'
 import useNotifier from '@/utils/useNotifier'
 import { useAuth } from '@/hooks/useAuth'
-import { getFileName } from '@/utils/genericHelper'
 
 // store
 import { closeSnackbar as closeSnackbarAction, enqueueSnackbar as enqueueSnackbarAction } from '@/store/actions'
@@ -77,7 +76,6 @@ const ShowStoredChunks = () => {
     const [showExpandedChunkDialog, setShowExpandedChunkDialog] = useState(false)
     const [expandedChunkDialogProps, setExpandedChunkDialogProps] = useState({})
     const [fileNames, setFileNames] = useState([])
-    const [loaderDisplayName, setLoaderDisplayName] = useState('')
 
     const chunkSelected = (chunkId) => {
         const selectedChunk = documentChunks.find((chunk) => chunk.id === chunkId)
@@ -214,32 +212,13 @@ const ShowStoredChunks = () => {
             setCurrentPage(data.currentPage)
             setStart(data.currentPage * 50 - 49)
             setEnd(data.currentPage * 50 > data.count ? data.count : data.currentPage * 50)
-
-            // Build the loader display name in format "LoaderName (sourceName)"
-            const loaderName = data.file?.loaderName || data.storeName || ''
-            let sourceName = ''
-
             if (data.file?.files && data.file.files.length > 0) {
                 const fileNames = []
                 for (const attachedFile of data.file.files) {
                     fileNames.push(attachedFile.name)
                 }
                 setFileNames(fileNames)
-                sourceName = fileNames.join(', ')
-            } else if (data.file?.source) {
-                const source = data.file.source
-                if (typeof source === 'string' && source.includes('base64')) {
-                    sourceName = getFileName(source)
-                } else if (typeof source === 'string' && source.startsWith('[') && source.endsWith(']')) {
-                    sourceName = JSON.parse(source).join(', ')
-                } else if (typeof source === 'string') {
-                    sourceName = source
-                }
             }
-
-            // Set display name in format "LoaderName (sourceName)" or just "LoaderName"
-            const displayName = sourceName ? `${loaderName} (${sourceName})` : loaderName
-            setLoaderDisplayName(displayName)
         }
 
         // eslint-disable-next-line react-hooks/exhaustive-deps
@@ -255,7 +234,7 @@ const ShowStoredChunks = () => {
                         <ViewHeader
                             isBackButton={true}
                             search={false}
-                            title={loaderDisplayName}
+                            title={getChunksApi.data?.file?.loaderName || getChunksApi.data?.storeName}
                             description={getChunksApi.data?.file?.splitterName || getChunksApi.data?.description}
                             onBack={() => navigate(-1)}
                         ></ViewHeader>

packages/ui/src/views/docstore/VectorStoreConfigure.jsx

@@ -40,7 +40,7 @@ import Storage from '@mui/icons-material/Storage'
 import DynamicFeed from '@mui/icons-material/Filter1'
 
 // utils
-import { initNode, showHideInputParams, getFileName } from '@/utils/genericHelper'
+import { initNode, showHideInputParams } from '@/utils/genericHelper'
 import useNotifier from '@/utils/useNotifier'
 
 // const
@@ -69,7 +69,6 @@ const VectorStoreConfigure = () => {
     const [loading, setLoading] = useState(true)
     const [documentStore, setDocumentStore] = useState({})
     const [dialogProps, setDialogProps] = useState({})
-    const [currentLoader, setCurrentLoader] = useState(null)
 
     const [showEmbeddingsListDialog, setShowEmbeddingsListDialog] = useState(false)
     const [selectedEmbeddingsProvider, setSelectedEmbeddingsProvider] = useState({})
@@ -246,8 +245,7 @@ const VectorStoreConfigure = () => {
     const prepareConfigData = () => {
         const data = {
             storeId: storeId,
-            docId: docId,
+            docId: docId
-            isStrictSave: true
         }
         // Set embedding config
         if (selectedEmbeddingsProvider.inputs) {
@@ -355,39 +353,6 @@ const VectorStoreConfigure = () => {
         return Object.keys(selectedEmbeddingsProvider).length === 0
     }
 
-    const getLoaderDisplayName = (loader) => {
-        if (!loader) return ''
-
-        const loaderName = loader.loaderName || 'Unknown'
-        let sourceName = ''
-
-        // Prefer files.name when files array exists and has items
-        if (loader.files && Array.isArray(loader.files) && loader.files.length > 0) {
-            sourceName = loader.files.map((file) => file.name).join(', ')
-        } else if (loader.source) {
-            // Fallback to source logic
-            if (typeof loader.source === 'string' && loader.source.includes('base64')) {
-                sourceName = getFileName(loader.source)
-            } else if (typeof loader.source === 'string' && loader.source.startsWith('[') && loader.source.endsWith(']')) {
-                sourceName = JSON.parse(loader.source).join(', ')
-            } else if (typeof loader.source === 'string') {
-                sourceName = loader.source
-            }
-        }
-
-        // Return format: "LoaderName (sourceName)" or just "LoaderName" if no source
-        return sourceName ? `${loaderName} (${sourceName})` : loaderName
-    }
-
-    const getViewHeaderTitle = () => {
-        const storeName = getSpecificDocumentStoreApi.data?.name || ''
-        if (docId && currentLoader) {
-            const loaderName = getLoaderDisplayName(currentLoader)
-            return `${storeName} / ${loaderName}`
-        }
-        return storeName
-    }
-
     useEffect(() => {
         if (saveVectorStoreConfigApi.data) {
             setLoading(false)
@@ -446,15 +411,6 @@ const VectorStoreConfigure = () => {
                 return
             }
             setDocumentStore(docStore)
-
-            // Find the current loader if docId is provided
-            if (docId && docStore.loaders) {
-                const loader = docStore.loaders.find((l) => l.id === docId)
-                if (loader) {
-                    setCurrentLoader(loader)
-                }
-            }
-
             if (docStore.embeddingConfig) {
                 getEmbeddingNodeDetailsApi.request(docStore.embeddingConfig.name)
             }
@@ -517,7 +473,7 @@ const VectorStoreConfigure = () => {
                                 <ViewHeader
                                     isBackButton={true}
                                     search={false}
-                                    title={getViewHeaderTitle()}
+                                    title={getSpecificDocumentStoreApi.data?.name}
                                     description='Configure Embeddings, Vector Store and Record Manager'
                                     onBack={() => navigate(-1)}
                                 >

packages/ui/src/views/roles/index.jsx

@@ -21,8 +21,7 @@ import {
     useTheme,
     Typography,
     Button,
-    Drawer,
+    Drawer
-    TableSortLabel
 } from '@mui/material'
 
 // project imports
@@ -186,8 +185,6 @@ function ShowRoleRow(props) {
     const [openViewPermissionsDrawer, setOpenViewPermissionsDrawer] = useState(false)
     const [selectedRoleId, setSelectedRoleId] = useState('')
     const [assignedUsers, setAssignedUsers] = useState([])
-    const [order, setOrder] = useState('asc')
-    const [orderBy, setOrderBy] = useState('workspace')
 
     const theme = useTheme()
     const customization = useSelector((state) => state.customization)
@@ -199,38 +196,6 @@ function ShowRoleRow(props) {
         setSelectedRoleId(roleId)
     }
 
-    const handleRequestSort = (property) => {
-        const isAsc = orderBy === property && order === 'asc'
-        setOrder(isAsc ? 'desc' : 'asc')
-        setOrderBy(property)
-    }
-
-    const sortedAssignedUsers = [...assignedUsers].sort((a, b) => {
-        let comparison = 0
-
-        if (orderBy === 'workspace') {
-            const workspaceA = (a.workspace?.name || '').toLowerCase()
-            const workspaceB = (b.workspace?.name || '').toLowerCase()
-            comparison = workspaceA.localeCompare(workspaceB)
-            if (comparison === 0) {
-                const userA = (a.user?.name || a.user?.email || '').toLowerCase()
-                const userB = (b.user?.name || b.user?.email || '').toLowerCase()
-                comparison = userA.localeCompare(userB)
-            }
-        } else if (orderBy === 'user') {
-            const userA = (a.user?.name || a.user?.email || '').toLowerCase()
-            const userB = (b.user?.name || b.user?.email || '').toLowerCase()
-            comparison = userA.localeCompare(userB)
-            if (comparison === 0) {
-                const workspaceA = (a.workspace?.name || '').toLowerCase()
-                const workspaceB = (b.workspace?.name || '').toLowerCase()
-                comparison = workspaceA.localeCompare(workspaceB)
-            }
-        }
-
-        return order === 'asc' ? comparison : -comparison
-    })
-
     useEffect(() => {
         if (getAllUsersByRoleIdApi.data) {
             setAssignedUsers(getAllUsersByRoleIdApi.data)
@@ -238,14 +203,12 @@ function ShowRoleRow(props) {
     }, [getAllUsersByRoleIdApi.data])
 
     useEffect(() => {
-        if (openAssignedUsersDrawer && selectedRoleId) {
+        if (open && selectedRoleId) {
             getAllUsersByRoleIdApi.request(selectedRoleId)
         } else {
             setOpenAssignedUsersDrawer(false)
             setSelectedRoleId('')
             setAssignedUsers([])
-            setOrder('asc')
-            setOrderBy('workspace')
         }
         // eslint-disable-next-line react-hooks/exhaustive-deps
     }, [openAssignedUsersDrawer])
@@ -338,28 +301,12 @@ function ShowRoleRow(props) {
                                 }}
                             >
                                 <TableRow>
-                                    <StyledTableCell sx={{ width: '50%' }}>
+                                    <StyledTableCell sx={{ width: '50%' }}>User</StyledTableCell>
-                                        <TableSortLabel
+                                    <StyledTableCell sx={{ width: '50%' }}>Workspace</StyledTableCell>
-                                            active={orderBy === 'user'}
-                                            direction={orderBy === 'user' ? order : 'asc'}
-                                            onClick={() => handleRequestSort('user')}
-                                        >
-                                            User
-                                        </TableSortLabel>
-                                    </StyledTableCell>
-                                    <StyledTableCell sx={{ width: '50%' }}>
-                                        <TableSortLabel
-                                            active={orderBy === 'workspace'}
-                                            direction={orderBy === 'workspace' ? order : 'asc'}
-                                            onClick={() => handleRequestSort('workspace')}
-                                        >
-                                            Workspace
-                                        </TableSortLabel>
-                                    </StyledTableCell>
                                 </TableRow>
                             </TableHead>
                             <TableBody>
-                                {sortedAssignedUsers.map((item, index) => (
+                                {assignedUsers.map((item, index) => (
                                     <TableRow key={index}>
                                         <StyledTableCell>{item.user.name || item.user.email}</StyledTableCell>
                                         <StyledTableCell>{item.workspace.name}</StyledTableCell>

packages/ui/src/views/tools/index.jsx

@@ -245,11 +245,7 @@ const Tools = () => {
                                         ))}
                                     </Box>
                                 ) : (
-                                    <ToolsTable
+                                    <ToolsTable data={getAllToolsApi.data.data} isLoading={isLoading} onSelect={edit} />
-                                        data={getAllToolsApi.data?.data?.filter(filterTools) || []}
-                                        isLoading={isLoading}
-                                        onSelect={edit}
-                                    />
                                 )}
                                 {/* Pagination and Page Size Controls */}
                                 <TablePagination currentPage={currentPage} limit={pageLimit} total={total} onChange={onChange} />