Switched OpenRAG backend and frontend in docker-compose.yml to use local Dockerfile builds instead of remote images. Updated environment variables for better clarity and system integration. In flows/openrag_agent.json and langflow_file_service, improved handling of docs_metadata to support Data objects and added logging for metadata ingestion. Added agent_llm edge to agent node in flow definition.
Added OWNER, OWNER_NAME, OWNER_EMAIL, and CONNECTOR_TYPE environment variables to docker-compose.yml and updated LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT accordingly. Modified ingestion_flow.json to adjust node selection and className, and cleared a sensitive value. Added logging for metadata tweaks in langflow_file_service.py for better traceability.
Updated the OpenSearchVectorStoreComponent to improve document metadata ingestion, including support for Data objects in docs_metadata. Added new edges and nodes to ingestion_flow.json for dynamic metadata input. Changed Dockerfile.langflow to use the fix-file-component branch.
Introduces custom headers containing JWT and owner information to the Langflow ingestion API requests for improved authentication and traceability. Also refactors debug logging and formatting for better readability and error handling in the combined upload, ingest, and delete operation.
* implement delete user conversation on agent
* format
* implement delete session endpoint
* implement delete session on persistence services
* added deletion of sessions and added fetch sessions with query instead of with useEffect
* removed unused texts
* implemented dropdown menu on conversations
* feat: add status handling and visual indicators for file statuses
* refactor: comment out status field and related rendering logic in SearchPage
* format
* add timeout on mutation delete document
* make file fields be optional
* fetch task files and display them on knowledge page
* add tasks to files inside task context
* added failed to status badge
* added files on get all tasks on backend
* Changed models to get parameters by settings if not existent
* changed settings page to get models when is no ajth mode
* fixed openai allowing validation even when value is not present
* removed unused console log
---------
Co-authored-by: Lucas Oliveira <lucas.edu.oli@hotmail.com>
Co-authored-by: Mike Fortman <michael.fortman@datastax.com>
* Changed flows and components to support different models
* Changed onboarding to redirect automatically
* Added new components and ids to settings
* Changed flows service to change llm text components as well
* changed models service to not remove : on ollama
* fix edge not connecting on nudges flow
Extend AuthService and LangflowMCPService to support updating MCP servers with multiple global variable headers (JWT, OWNER, OWNER_NAME, OWNER_EMAIL) during login. This enables passing user context to MCP servers via custom headers, improving downstream identification and authorization.
Added LangflowMCPService to update MCP servers with the user's JWT header after authentication. AuthService now triggers a background update to MCP servers on successful login, ensuring JWT propagation for downstream services.
- Added a new `DeleteConfirmationDialog` component for confirming deletions.
- Updated `KnowledgeDropdown` to include a loading state and improved user feedback during file operations.
- Enhanced the search page to support bulk deletion of documents with confirmation dialog.
- Integrated event dispatching for knowledge updates after file operations.
- Refactored various components for better readability and maintainability.
