Replaces all references to 'OpenSearchHybrid-Ve6bS' with 'OpenSearchVectorStoreComponentMultimodalMultiEmbedding-By9U4' in main.py, processors, and file service. Adds a utility for injecting provider credentials into Langflow request headers and integrates it into chat and file services for improved credential handling.
Replaced imports from config_manager with settings in chat_service.py and langflow_file_service.py to use get_openrag_config from config.settings. This change ensures consistency with the updated configuration structure.
Introduces SELECTED_EMBEDDING_MODEL as a global environment variable in docker-compose files and ensures it is passed in API headers for Langflow-related services. Updates settings and onboarding logic to set this variable without triggering flow updates, improving embedding model configuration consistency across services.
Replaces the File component with a new OpenSearch hybrid search component in the ingestion flow, adds support for document metadata, and updates flow edges for DataFrame operations. Updates OpenSearch component implementation with advanced authentication, metadata handling, and vector store features. Docker Compose files and related service references are also updated to support the new OpenSearch integration.
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.
This commit updates the ingestion flow to include user metadata such as owner ID, name, and email, enhancing the context for downstream services. It also refines the handling of tweaks in the LangflowFileService to incorporate this metadata, ensuring better tracking and clarity in the ingestion process. These changes align with best practices for robust async development and improve the overall functionality of the ingestion flow.
This commit modifies the key for file paths in the tweaks dictionary from "file_path" to "path" within the LangflowFileService class. This change improves code clarity and consistency, aligning with best practices for robust async development while maintaining existing functionality.
This commit updates the LangflowFileService class by changing the key for file paths in the tweaks dictionary from "path" to "file_path". This modification enhances code clarity and aligns with best practices for maintaining robust async code. Additionally, it simplifies the logging statement for better readability while preserving the functionality related to JWT token handling.
This commit refactors the LangflowFileService to utilize a centralized logger instead of instance-specific logging. It also improves the handling of the JWT token in the run_ingestion_flow method, ensuring it is correctly passed to downstream services and logged appropriately. These changes enhance code readability and maintainability while adhering to robust async coding practices.
This commit introduces a new combined endpoint for uploading files and running ingestion in Langflow. The frontend component is updated to utilize this endpoint, streamlining the process by eliminating separate upload and ingestion calls. The response structure is adjusted to include deletion status and other relevant information, enhancing error handling and logging practices throughout the codebase.
This commit streamlines the LangflowFileService by removing direct HTTP client usage in favor of a centralized API client for handling requests. It enhances the upload and delete file methods to improve code organization and maintainability. Additionally, it updates logging practices for better error visibility, ensuring adherence to robust async coding standards and documentation practices.
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 introduces the LangflowFileService class, which provides methods for uploading user files, deleting user files, and triggering an ingestion flow using the Langflow Files API. The service is designed to handle asynchronous operations and includes error handling for API requests. Documentation for each method is included to ensure clarity on usage.
