* access chat history and other useful variables in post-processing
* cloning data to prevent mutations in post-processing
* Enhance post-processing capabilities by adding support for additional variables and improving the UI for available variables display. Update CustomFunction implementations to utilize post-processing options consistently across components.
---------
Co-authored-by: Henry <hzj94@hotmail.com>
* feat: Optimize ConversationalRetrievalToolAgent performance and add rephrase model support
- fix duplicate rephrasing bug
- Add optional separate rephrase model
- Enable query normalization on first messages
- Fix returnDirect tool behavior
- Add backward-compatible rephrase prompt support
* fix lint errors
* Fix duplicate streaming and inconsistent chat history format
- 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>
* fix: add missing OpenTelemetry dependencies to components package
- Fixes ModuleLoadError when installing via NPX
- Adds @opentelemetry/* dependencies that were imported but not declared
- Resolves issue #4108
* fix: correct OpenTelemetry package versions
- Change @opentelemetry/api from ^1.3.0 to 1.9.0 (compatible with SDK 1.27.0)
- Change @opentelemetry/instrumentation from 0.54.2 to 0.54.0 (correct version)
- Ensures version consistency and compatibility across all OpenTelemetry packages
* Update package.json
* update opentelemetry api version
* update pnpm lock file
---------
Co-authored-by: KushagraaWadhwa <kushagraa@users.noreply.github.com>
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
Co-authored-by: Henry <hzj94@hotmail.com>
* Updated the executeJavaScriptCode function to automatically detect and install required libraries from import/require statements in the provided code.
* Update utils.ts
* lint-fix
* feat(security): enhance file path validation and implement non-root Docker user
- Validate resolved full file paths including workspace boundaries in SecureFileStore
- Resolve paths before validation in readFile and writeFile operations
- Run Docker container as non-root flowise user (uid/gid 1001)
- Apply proper file ownership and permissions for application files
Prevents path traversal attacks and follows container security best practices
* Add sensitive system directory validation and Flowise internal file protection
* Update Dockerfile to use default node user
* update validation patterns to include additional system binary directories (/usr/bin, /usr/sbin, /usr/local/bin)
* added isSafeBrowserExecutable function to validate browser executable paths for Playwright and Puppeteer loaders
---------
Co-authored-by: taraka-vishnumolakala <taraka.vishnumolakala@workday.com>
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
Co-authored-by: Henry <hzj94@hotmail.com>
* add separate by JSON object
* add file check for Unstructured
* Enhance JSON DocumentLoader: Update label and description for 'Separate by JSON Object' option, and add type check for JSON objects in array processing.
Integrate AzureChatOpenAI into the Supervisor node to handle user requests alongside ChatOpenAI. This enhancement allows for improved multi-agent conversation management.
* implement parseWithTypeConversion - parse a value against a Zod schema with automatic type conversion for common type mismatches
* Enhance parseWithTypeConversion to include maxDepth parameter for recursion control, preventing infinite loops during parsing.
* add tools warning
* Enhance file handling tools with security features
- Introduced new input parameters: workspacePath, enforceWorkspaceBoundaries, maxFileSize, and allowedExtensions for better control over file operations.
- Added validation for file paths and sizes to prevent unsafe operations.
- Implemented workspace boundary checks to restrict file access based on user-defined settings.
* Add tts UI
* Add tts backend
* Add description to eleven labs credentials
* Fix issue with fetching eleven labs voices
* Fix issue with text to speech tab not showing correct saved voice
* Add option to autoplay tts audio after prediction completes
* Fix crash issue when first changing tts provider
* Set up streaming response for text to speech audio
* Update controllers - fix issue with sse client getting removed before tts events are sent
* Use existing sse streamer to stream tts audio before sse client is removed
* Add tts sse to redis publisher
* Fix issues with TTS - openai voices, streaming audio, rate limiting, speed of speech
* Refactor
* Refactor TTS - fix issues with tts loading and stop audio buttons
* Abort TTS SSE when clicking the stop button
* Update SSE handling for TTS
* Fix issue with test voice feature
* Fix issue with tts voices not loading
* Update generate tts endpoint and its usage in internal chat
* Whitelist tts generate endpoint
* Refactor Text-to-Speech Provider Selection and Enhance UI Components
- Updated the text-to-speech controller to select the active provider based on status instead of the first available provider
- Added audio waveform controls and test audio functionality in the TextToSpeech component, allowing users to play and pause test audio
- Integrated Autocomplete for voice selection in the TextToSpeech component
- Implemented TTS action management in ChatMessage to prevent auto-scrolling during TTS actions
* - Implemented stopAllTTS function calls to halt existing TTS audio before playing new audio or starting a new TTS stream
* Updated the condition for enabling TTS providers to exclude the 'none' provider, ensuring only valid providers are considered for text-to-speech functionality.
* Remove unnecessary code
* Add ability to abort audio streaming in TTS and release lock on chat input
* Remove logger
* Fix tts audio not playing when clicking speaker button
* update
* TTS abort controller
* Fix abort not working for TTS autoplay
* Send metadata event when aborting autoplay TTS
* Fix UI issue
* Remove elevenlabs sdk from root package.json
* Remove redundant condition for tts autoplay in chatflow
---------
Co-authored-by: Henry <hzj94@hotmail.com>
feat: enhance OpenAPI Toolkit with input type options and server selection
- Updated OpenAPI Toolkit to support multiple input types: file upload or link.
- Added async options for selecting servers and endpoints from the OpenAPI specification.
- Improved error handling for loading OpenAPI specs and fetching server data.
- Updated version to 2.1.
Co-authored-by: Mehdi Chebbah <MChebbah@aas.com.sa>
Nikitas Papadopoulos
Henry Heng
Siddharth Chauhan
Kushagra Wadhwa
Daniel Moon
mskitroot
Henry
Taraka Vishnumolakala
Lê Nam Khánh
Håvard Homb
Marko
Shashank Shekhar
Bharath
Rostyslav Borovyk
Ilango
Mehdi