This update adds support for Opik tracer in Flowise. It includes new
credential components, analytic nodes, and UI assets for both tracers. The
changes enhance observability by allowing users to integrate Opik for better
model monitoring, analysis and evaluation.
* fix: udpate label to "NVIDIA NIM API Key"
* test: update tag from ":latest" to ":1.8.0-rtx"
* test: add image URL path "nvcr.io/nim/"
* fix/nvidia-nim-2 (#4208)
* fix: update nim-container-manager
* feat: add "DeepSeek R1 Distill Llama 8B"
* fix/nidia-nim-3 (#4209)
* chore: add error message NVIDIA NIM is not installed.
* chore: standardize NVIDIA NGC API Key
* chore: capitalize Nvidia to NVIDIA
* chore: generalize error message for chat models
* fix/nvidia-nim-4-yau (#4212)
* test: nimRelaxMemConstraints and hostPort
* test: add logger for hostPort and nimRelaxMemConstraints
* test: nim-container-manager version 1.0.9
* test: parseInt nimRelaxMemConstraints
* test: update nim-container-manager version to 1.0.10
* chore: update nim-container-manager version to 1.0.11
* Update start container behaviour - show existing containers and give users the choice
* Go back to previous step when clicking start new so user can change port number
* Update condition for showing existing container dialog
* Fix start new in different port not working
* Update get container controller
* Update again
* fix: generalize error message for chat models
* Update getContainer controller
* Fix incorrect image check in getContainer controller
* Update existing container dialog text
* Fix styles in container exists dialog for nvidia nim
---------
Co-authored-by: chungyau97 <chungyau97@gmail.com>
Co-authored-by: Ong Chung Yau <33013947+chungyau97@users.noreply.github.com>
* add nim container setup
* check if image or container exist before pulling
* update NIM dialog
* update chat nvidia api key
* update nim container version
* update nim container version
* New Feature: Add post postprocessing of response from LLM using custom Javascript functions
* Disable Save when there is no content
* add post processing ui changes, disable streaming
---------
Co-authored-by: Henry <hzj94@hotmail.com>
* now user can name each document loader for ease of tracking
* Update LoaderConfigPreviewChunks.jsx
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
Added clarification that data will also be removed from the record manager.
Before:
"Remove data from vector store"
After:
"Remove data from vector store and record manager"
Note: this dialog box only appears when a record manager exists in the doc store. If it's intended to be shown regardless of whether a record manager exists, updates will be needed.
* Get ChatMessage based on startDateTime / endDateTime - supplements existing startDate / endDate fields
* Proper query handling for between case
* Return 0 result rather than error
* lint fix
* update start date and end date query
---------
Co-authored-by: Henry <hzj94@hotmail.com>
fix: artifacts key in object does not have messages property, which gives 'Cannot read properties of undefined (reading reverse) error. So, do not add it to obj variable. Instead, add it to msg object.
* feat: Add Azure Cognitive Services integration for speech-to-text functionality
- Introduced a new credential class for Azure Cognitive Services.
- Updated speech-to-text processing to support Azure Cognitive Services as a provider.
- Enhanced UI components to include Azure Cognitive Services options and inputs for configuration.
- Added necessary imports and error handling for Azure API requests.
* Update SpeechToText.jsx linting
* refactor: Update audio file handling in SpeechToText component
- Removed the dependency on 'form-data' and replaced it with a Blob for audio file uploads.
- Simplified the audio file appending process to the form data.
- Cleaned up the headers in the Axios request by removing unnecessary form data headers.
This change enhances the efficiency of audio file processing in the speech-to-text functionality.
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
Co-authored-by: Henry <hzj94@hotmail.com>
* feat: Add Groq Whisper support to SpeechToText component
- Introduced a new speech-to-text provider, Groq Whisper, in both the backend and UI components.
- Updated SpeechToTextType to include GROQ_WHISPER.
- Implemented Groq client integration for audio transcription with customizable model, language, and temperature options.
- Added UI elements for Groq Whisper configuration, including input fields for model, language, and temperature settings.
* turn speech to text none status to false when other was selected
---------
Co-authored-by: Henry <hzj94@hotmail.com>
* Changes Made to Embed Chat Configuration
1. Consolidated multiple configuration functions into a single `defaultThemeConfig` object
2. Added full theme configuration support for both popup and fullpage modes
3. Fixed fullpage chat window sizing to use 100% height and width
4. Improved code formatting and readability
* fix: replace empty customCSS quotes with backticks in theme configuration output
* refactor: improve script output formatting for embed chat code
* Fixed incorrect spacing in React component theme prop string templates.
* Add ability to enable/disable which variables can be overriden during external predictions
* Remove duplicated code
* Remove rate limit and allowed domains tab from chatflow configuration
* Show tooltip in api code dialog for override config properties
* Fix server crash when override config is not available
* update UI for chatflow config security, file upload
* Fix UI issues in security tab of chatflow configuration dialog
* Fix override config options not updating when nodes change
* Fix crash in api code dialog when overrideConfig is not available for a chatflow/agentflow. Also fix input config in api code dialog not updating when nodes change.
* Refactor override config and add override config for variables
* Update api code dialog - update how override config is read and show variable overrides
* Update how node and variable overrides are read and resolved
* Prevent api code dialog mounting on page load and only mount when api code dialog button is clicked. this should fix loading incorrect data.
* Fix variables list not showing when overrideConfig is not available
* add overrideconfig to agentflow and upsert vector
* temporarily removed enable overrideconfig on upsert, fix linting issues
---------
Co-authored-by: Henry <hzj94@hotmail.com>
* Add Up and Down arrow functionality to chat messages
- Works like Linux shell
- History limited to 10 messages
* Fix linting errors
* Update EmbedChat.jsx
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
* add functionality for full file uploads, add remove messages from view dialog and API
* add attachments swagger
* update question to include uploadedFilesContent
* make config dialog modal lg size
* Add migrations - add follow up prompts column to chatflow and chat message
* Add configuration tab for follow-up prompts
* Add follow up prompts functionality
* Pin zod version in components - this was causing a type error with structured outputs
* Generate follow up prompts if enabled and return it in stream, response, and save to database
* Show follow up prompts after getting response
* Add google gen ai for generating follow up prompts and fix issues
* Add config for google gen ai and update model options
* Update follow-up prompts ui and styles
* Release/2.1.0 (#3204)
flowise@2.1.0 release
* Chore/update flowise embed version to 2.0.0 (#3205)
* update flowise-embed version on lock file
* add agent messages to share chatbot
* Update pnpm-lock.yaml
* update flowise-embed version
* update flowise-embed to 1.3.9
* update embed version to 2.0
* Bugfix/CodeInterpreter E2B Credential (#3206)
* Base changes for ServerSide Events (instead of socket.io)
* lint fixes
* adding of interface and separate methods for streaming events
* lint
* first draft, handles both internal and external prediction end points.
* lint fixes
* additional internal end point for streaming and associated changes
* return streamresponse as true to build agent flow
* 1) JSON formatting for internal events
2) other fixes
* 1) convert internal event to metadata to maintain consistency with external response
* fix action and metadata streaming
* fix for error when agent flow is aborted
* prevent subflows from streaming and other code cleanup
* prevent streaming from enclosed tools
* add fix for preventing chaintool streaming
* update lock file
* add open when hidden to sse
* Streaming errors
* Streaming errors
* add fix for showing error message
* add code interpreter
* add artifacts to view message dialog
* Update pnpm-lock.yaml
* uncomment e2b credential
---------
Co-authored-by: Vinod Paidimarry <vinodkiran@outlook.in>
* Release/2.1.0 (#3207)
* flowise@2.1.0 release
* update flowise-components@2.1.1
* Bugfix/Add artifacts migration script to other database types (#3210)
add artifacts migration script to other database types
* Release/2.1.1 (#3213)
release @2.1.1
* Bugfix/Add header to allow sse on nginx (#3214)
add header to allow sse on nginx
* Bugfix/remove invalid markdown (#3219)
remove invalid markdown
* Correct "as" casing (#3216)
* Correct "as" casing
* Remove "version" line from docker compose file
* Update docker-compose.yml
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
* chore: update unstructured API url and doc reference (#3224)
chore: udpate unstructured API url and doc reference
* Feature/add ability to specify dynamic metadata to jsonlines (#3238)
* add ability to specify dynamic metadata to jsonlines
* fix additional metadata
* Bugfix/Buffer Memory for Anthropic (#3242)
fix buffer memory
* Added env vars to ui and api URL (#3141)
* feat: add environment vars to split application in different deployments for better scalability
* update: package.json
added start script ui
---------
Co-authored-by: patrick <patrick.alves@br.experian.com>
* Added 1-click deployment link for Alibaba Cloud. (#3251)
* Added a link for Alibaba Cloud Deployment
* change service name
---------
Co-authored-by: yehan <gn398171@alibaba-inc.com>
* Chore/Groq Llama3.2 (#3255)
* add gemini flash
* add gemin flash to vertex
* add gemin-1.5-flash-preview to vertex
* add azure gpt 4o
* add claude 3.5 sonnet
* add mistral nemo
* add groq llama3.1
* add gpt4o-mini to azure
* o1 mini
* add groq llama 3.2
* Bugfix/Prevent streaming of chatflow tool and chain tool (#3257)
prevent streaming of chatflow tool and chain tool
* Bugfix/Enable Custom Tool Optional Input Schema (#3258)
* prevent streaming of chatflow tool and chain tool
* enable optional input schema
* Bugfix/Searxng tool not working (#3263)
fix searxng tool not working
* LunaryAI automatic Thread and User tracking (#3233)
* Lunary Thread/User tracking
* Clean console logs
* Clean
* Remove commented lines
* Remove commented line
* feat: enable autofocus to the `new chatflow title` to improve usability (#3260)
This dialog has only one input and it is the primary one, there is no need for an extra click to be able to set the title
* feat: save a new Chatflow when the `ENTER` key is pressed (#3261)
This simple event handler improve the usability of the UI by avoiding having to use the mouse or having to tab twice and then hit enter to save a flow
* feat: save Chatflow title when the `ENTER` key is pressed or discard upon `ESC` is pressed (#3265)
This simple event handler improves the usability of the UI by avoiding having to use the mouse to save or dicard title changes
* feat: enable autofocus to the `edit chatflow title` field to improve UI usability (#3264)
feat: enable autofocus to the `edit chatflow title` field to improve usability
The canvas header has only one input and it is the primary one, there is no need for an extra click to be able to edit the title
* feat: add search keyboard shortcut based on the current platform (#3267)
* feat: highlight valid/invalid connection between nodes (#3266)
Change the inputs background to green/red to hint compatible connections, in adition to the `not-allowed` mouse cursor for incompatible connections
* Bugfix/add fixes for search of view header (#3271)
add fixes for search of view header
* fix: warning when passing a boolean to border property of a Card (#3275)
By default MainCard wrappers like NodeCardWrapper and CardWrapper add a a solid border of 1px, but if the `MainCard.border` prop is used (`false`) the border prop was wrongly set to a boolean instead of string
* feat: add shortcut text hint to the search field (#3269)
* feat: add shortcut text hint to the search field
* fix: search box width to fit the shortcut hint text
* fix: error when not running on Mac due to an undefined `os` variable
* fix: warning when a non-boolean values was used to set `checked` prop of a SwitchInput component (#3276)
fix: warning when a non-boolean values was used to set`checked` prop of SwitchInput component
The problem was that in the useEffect hook the plain value was used without validation like in useState
* Bugfix/Throw error to prevent SSE from retrying (#3281)
throw error to prevent SSE from retrying
* Pin zod version in components - this was causing a type error with structured outputs
* Fix conflicts in pnpm lock
* fix ui changes for follow up prompts
* Fix button disable state in follow-up prompts configuration
* Fix follow-up prompts not showing up for agent flows
* Show follow up prompts if last message is apiMessage and follow up prompts are available
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
Co-authored-by: Vinod Paidimarry <vinodkiran@outlook.in>
Co-authored-by: Cross <github@dillfrescott.com>
Co-authored-by: cragwolfe <cragcw@gmail.com>
Co-authored-by: patrickreinan <patrickreinan@gmail.com>
Co-authored-by: patrick <patrick.alves@br.experian.com>
Co-authored-by: yehan <34835250+yehanyh@users.noreply.github.com>
Co-authored-by: yehan <gn398171@alibaba-inc.com>
Co-authored-by: Vincelwt <vincelwt@users.noreply.github.com>
Co-authored-by: Humberto Rodríguez A. <rhumbertgz@users.noreply.github.com>
Co-authored-by: Henry <hzj94@hotmail.com>
fix: warning when a non-boolean values was used to set`checked` prop of SwitchInput component
The problem was that in the useEffect hook the plain value was used without validation like in useState
* feat: add shortcut text hint to the search field
* fix: search box width to fit the shortcut hint text
* fix: error when not running on Mac due to an undefined `os` variable
By default MainCard wrappers like NodeCardWrapper and CardWrapper add a a solid border of 1px, but if the `MainCard.border` prop is used (`false`) the border prop was wrongly set to a boolean instead of string
feat: enable autofocus to the `edit chatflow title` field to improve usability
The canvas header has only one input and it is the primary one, there is no need for an extra click to be able to edit the title
* feat: add environment vars to split application in different deployments for better scalability
* update: package.json
added start script ui
---------
Co-authored-by: patrick <patrick.alves@br.experian.com>
* Base changes for ServerSide Events (instead of socket.io)
* lint fixes
* adding of interface and separate methods for streaming events
* lint
* first draft, handles both internal and external prediction end points.
* lint fixes
* additional internal end point for streaming and associated changes
* return streamresponse as true to build agent flow
* 1) JSON formatting for internal events
2) other fixes
* 1) convert internal event to metadata to maintain consistency with external response
* fix action and metadata streaming
* fix for error when agent flow is aborted
* prevent subflows from streaming and other code cleanup
* prevent streaming from enclosed tools
* add fix for preventing chaintool streaming
* update lock file
* add open when hidden to sse
* Streaming errors
* Streaming errors
* add fix for showing error message
* add code interpreter
* add artifacts to view message dialog
* Update pnpm-lock.yaml
---------
Co-authored-by: Vinod Paidimarry <vinodkiran@outlook.in>
* Base changes for ServerSide Events (instead of socket.io)
* lint fixes
* adding of interface and separate methods for streaming events
* lint
* first draft, handles both internal and external prediction end points.
* lint fixes
* additional internal end point for streaming and associated changes
* return streamresponse as true to build agent flow
* 1) JSON formatting for internal events
2) other fixes
* 1) convert internal event to metadata to maintain consistency with external response
* fix action and metadata streaming
* fix for error when agent flow is aborted
* prevent subflows from streaming and other code cleanup
* prevent streaming from enclosed tools
* add fix for preventing chaintool streaming
* update lock file
* add open when hidden to sse
* Streaming errors
* Streaming errors
* add fix for showing error message
---------
Co-authored-by: Henry <hzj94@hotmail.com>
* New Feature: Custom Templates in the marketplace.
* New Feature: Custom Templates in the marketplace.
* Custom Template Delete and Shortcut in the dropdown menu
* auto detect framework
* minor ui fixes
* adding custom template feature for tools
* ui tool dialog save template
---------
Co-authored-by: Henry <hzj94@hotmail.com>
* add export all function
* modify exportAll to reuse existing code from other services
* modify routes of export-import
* add exportAll function into UI
* add errorhandler
* add importAll Function into UI for ChatFlow
* modify importAll Function to import tools
* remove appServer variable
* modify exportAll to exportData for new requirement in backend
* chore modify type camelCase to PascalCase in exportImportService
* add import export for variables, assistants, and checkboxes for UI
---------
Co-authored-by: Henry <hzj94@hotmail.com>
Boris Feld
Ong Chung Yau
Ilango
Henry Heng
Sarge Joseph
Asharib Ali
Vinod Kiran
Matt Smith
Ali Saleh
ritvikPuranik
saatchi-david
Light
Ryan Halliday
Ahmed Rowaihi
Tomoki Yokoyama
Sunny Modi
Aaron
Danila
Abhishek Patil
richersoon
Anthony Bryan Gavilan Vinces
Henry
Danilo Ferreira
toi500
Tyler
khakanali
Prajwal Pai
Prateek Jakhar
Humberto Rodríguez A.
Vincelwt
patrickreinan
Aman Soni