This commit introduces a new JSON configuration file for the OpenSearch ingestion flow, detailing the data processing pipeline. The flow includes components for splitting text, generating embeddings, and ingesting data into OpenSearch, enhancing the capabilities for Retrieval Augmented Generation (RAG) tasks. The configuration is designed to support various input types and provides detailed metadata for each component, ensuring robust and well-documented integration.
🚀 (frontend): Implement support for process.env.PORT to run app on a configurable port
🔧 (frontend): Change port variable case from lowercase 'port' to uppercase 'PORT' for better semantics
📝 (frontend): Add comments to clarify the purpose of loading conversation data only when user explicitly selects a conversation
📝 (frontend): Add comments to explain the logic for loading conversation data based on certain conditions
📝 (frontend): Add comments to describe the purpose of handling new conversation creation and resetting messages
📝 (frontend): Add comments to explain the logic for loading conversation data when conversationData changes
📝 (frontend): Add comments to clarify the purpose of loading conversations from the backend
📝 (frontend): Add comments to describe the logic for silent refresh to update data without loading states
📝 (frontend): Add comments to explain the purpose of starting a new conversation and creating a placeholder conversation
📝 (frontend): Add comments to clarify the logic for forking from a response and starting a new conversation
📝 (frontend): Add comments to describe the purpose of adding a conversation document and clearing conversation documents
📝 (frontend): Add comments to explain the logic for using a timeout to debounce multiple rapid refresh calls
📝 (frontend): Add comments to clarify the purpose of cleaning up timeout on unmount
📝 (frontend): Add comments to describe the logic for handling new conversation creation and resetting state
📝 (frontend): Add comments to explain the logic for forking from a response and starting a new conversation
📝 (frontend): Add comments to clarify the purpose of using useMemo for optimizing performance in ChatProvider
📝 (frontend): Add comments to describe the logic for using useMemo in the ChatProvider component
📝 (frontend): Add comments to explain the purpose of the useChat custom hook
📝 (frontend): Add comments to clarify the error message when useChat is not used within a ChatProvider
📝 (services): Update ChatService to fetch Langflow history with flow_id parameter for better control
This commit modifies both docker-compose.yml and docker-compose-cpu.yml to update the environment variable from FLOW_ID to LANGFLOW_CHAT_FLOW_ID, ensuring consistency across configurations. These changes contribute to a more robust and well-documented codebase.
This commit enhances the KnowledgeDropdown component by integrating a complete file handling process that includes uploading files to Langflow, running an ingestion flow, and deleting the uploaded files. It introduces error handling for each step and dispatches appropriate events to notify the UI of the upload and ingestion results. These changes improve the robustness and maintainability of the component, contributing to a well-documented codebase.
This commit introduces state management for ingest flow IDs and corresponding edit URLs in the KnowledgeSourcesPage component. It enhances the user interface by adding a new section for file ingestion, allowing users to customize their file processing pipeline. The changes improve the overall functionality and maintainability of the settings page, contributing to a more robust and well-documented codebase.
This commit updates the settings retrieval function to include new flow IDs for chat and ingestion, replacing the deprecated FLOW_ID. It also improves the logic for exposing edit URLs based on the availability of public URLs, contributing to a more robust and well-documented codebase.
This commit adds detailed debug and error logging to the upload_user_file endpoint, facilitating better tracking of file upload processes and issues. It includes checks for the presence of a file and JWT token, and captures exceptions with traceback information for enhanced debugging. These changes contribute to a more robust and well-documented codebase.
This commit introduces backwards compatibility for the flow ID by allowing the use of the deprecated FLOW_ID environment variable while issuing deprecation warnings. Additionally, the API key generation process has been improved with validation checks for cached keys and enhanced error handling. The Langflow client initialization has been updated to ensure proper handling of environment variables, contributing to a more robust and well-documented codebase.
This commit refactors the LangflowFileService to include asynchronous API key retrieval and updates the file upload and deletion methods to use the new v2 endpoints. The flow ID constant has been renamed for clarity, and additional logging has been added for better debugging and error handling. The payload structure for the ingestion flow has also been modified to improve functionality and maintainability.
This commit modifies both docker-compose.yml and docker-compose-cpu.yml to add OPENSEARCH_PASSWORD to the LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT. Additionally, unnecessary whitespace has been removed for improved readability.
This commit enhances the TaskService class by reorganizing import statements, updating type hints to use `dict` instead of `Dict`, and improving the formatting of method definitions for better clarity. Additionally, minor adjustments were made to comments and error handling, contributing to a more robust and well-documented codebase.
