- Upgrade @huggingface/inference from v2.6.1 to v4.13.2
- Update ChatHuggingFace to use InferenceClient with chatCompletion API
- Update HuggingFaceInference (LLM) to use v4 HfInference with Inference Providers
- Update HuggingFaceInferenceEmbedding to use v4 HfInference
- Add endpoint handling logic to ignore custom endpoints for provider-based models
- Add improved error handling and validation for API keys
- Update UI descriptions to guide users on proper configuration
Fixes#5161
Co-authored-by: Henry <hzj94@hotmail.com>
* Feature: Update Loop Agentflow to include fallback message and version increment to 1.1
- Added a new input parameter 'fallbackMessage' to the Loop Agentflow for displaying a message when the loop count is exceeded.
- Incremented the version of Loop Agentflow from 1.0 to 1.1.
- Updated the processing logic to handle the fallback message appropriately when the maximum loop count is reached.
* - Introduced a new input parameter 'loopUpdateState' to allow updating the runtime state during workflow execution.
- Added a method to list runtime state keys for dynamic state management.
- Implemented logic to retrieve and utilize the current loop count in variable resolution.
- Updated the Loop Agentflow output to reflect the new state and final output content.
* fix gsuite tool params
* custom assistant only check for mandatory fields for visible params
* azure chat openai fix for gpt5
* return raw from executeJavaScriptCode
* add json5 for parsing
* azure chatopenai use maxCompletionTokens
* Fixes the lossy-replace when a new state assignment contains the {{ output }} variable
* Replaces replace with replaceAll
---------
Co-authored-by: Corentin <corentin.hoareau@sogeti.com>
* - Added support for built-in OpenAI tools including web search, code interpreter, and image generation.
- Enhanced file handling by extracting artifacts and file annotations from response metadata.
- Implemented download functionality for file annotations in the UI.
- Updated chat history management to include additional kwargs for artifacts, file annotations, and used tools.
- Improved UI components to display used tools and file annotations effectively.
* remove redundant currentContainerId
* update comment
refactor: Update code execution sandbox implementation across components
- Replaced NodeVM usage with a new createCodeExecutionSandbox function for improved sandbox management.
- Enhanced JavaScript code execution with executeJavaScriptCode function, allowing for better handling of libraries and output streaming.
- Updated multiple components to utilize the new sandboxing approach, ensuring consistent execution environment.
- Added validation for UUIDs and URLs in various tools to enhance input safety.
- Refactored input handling in CustomFunction and IfElseFunction to streamline variable management.
Feature/Add remove-markdown dependency and integrate into Condition node for text processing
- Added `remove-markdown` package to `packages/components/package.json`.
- Integrated `removeMarkdown` function in `Condition.ts` to sanitize string inputs by removing markdown formatting.
* Enhancement: Introduce prepended chat history handling in Agent and LLM nodes.
- Added support for `prependedChatHistory` in both `Agent` and `LLM` classes to allow for initial message context.
- Implemented validation for history schema in execution flow to ensure proper format.
- Refactored utility functions to include JSON sanitization and validation methods for improved data handling.
* update prediction swagger
Enhancement: Add JSON sanitization and parsing methods to HTTP agentflow.
- Introduced `sanitizeJsonString` to clean problematic escape sequences and fix common JSON formatting issues.
- Added `parseJsonBody` to attempt parsing JSON directly, with fallback to sanitization if parsing fails, providing clearer error messages for invalid JSON.
- Updated request handling to utilize the new parsing method for JSON and x-www-form-urlencoded body types.
* Enhancement: Update issue templates and add new tools
- Updated bug report template to include a default label of 'bug'.
- Updated feature request template to include a default label of 'enhancement'.
- Added new credential class for Agentflow API.
- Enhanced Agent and HTTP nodes to improve tool management and error handling.
- Added deprecation badges to several agent and chain classes.
- Introduced new tools for handling requests (GET, POST, DELETE, PUT) with improved error handling.
- Added new chatflows and agentflows for various use cases, including document QnA and translation.
- Updated UI components for better handling of agent flows and marketplace interactions.
- Refactored utility functions for improved functionality and clarity.
* Refactor: Remove beta badge and streamline template title assignment
- Removed the 'BETA' badge from the ExtractMetadataRetriever class.
- Simplified the title assignment in the agentflowv2 generator by using a variable instead of inline string manipulation.
* feat: Add configurable system prompt to Condition Agent
* Update system prompt to HTML for UI readability
* fix: Remove invalid default routing and sync hardcoded role-based examples
* Update ConditionAgent.ts
* Update ConditionAgent.ts
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
* add teams, gmail, outlook tools
* update docs link
* update credentials for oauth2
* add jira tool
* add google drive, google calendar, google sheets tools, powerpoint, excel, word doc loader
* update jira logo
* Refactor Gmail and Outlook tools to remove maxOutputLength parameter and enhance request handling. Update response formatting to include parameters in the output. Adjust Google Drive tools to simplify success messages by removing unnecessary parameter details.
* Update pnpm-lock.yaml
* add google docs
* add teams, gmail, outlook tools
* update docs link
* update credentials for oauth2
* add jira tool
* add google drive, google calendar, google sheets tools, powerpoint, excel, word doc loader
* update jira logo
* Refactor Gmail and Outlook tools to remove maxOutputLength parameter and enhance request handling. Update response formatting to include parameters in the output. Adjust Google Drive tools to simplify success messages by removing unnecessary parameter details.