Added a new flow definition for OpenRAG with OpenSearch hybrid search in flows/openrag_url_mcp.json. Updated .gitignore to allow tracked JSON files in the flows directory while ignoring others.
Changed Dockerfile.langflow to use the 'test-openai-responses' branch. Improved file handling in ChatInput, updated ChatOutput to fix source property unpacking, and made AgentComponent use LCToolsAgentComponent._base_inputs. Also updated code hashes, dependency versions, and metadata timestamps in openrag_agent.json.
* changed tooltip stype
* added start on label wrapper
* changed switch to checkbox on openai onboarding and changed copies
* made border be red when api key is invalid
* Added embedding configuration after onboarding
* changed openrag ingest docling to have same embedding model component as other flows
* changed flows service to get flow by id, not by path
* modify reset_langflow to also put right embedding model
* added endpoint and project id to provider config
* added replacing the model with the provider model when resetting
* Moved consts to settings.py
* raise when flow_id is not found
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.
* 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
This commit modifies the ingestion flow JSON by adding support for user-defined metadata through the "docs_metadata" input field, improving the context for document ingestion. Additionally, it updates the selection state of a node and adjusts the viewport settings for better layout. These changes enhance the overall functionality and clarity of the component configurations, aligning with best practices for robust async development.
This commit modifies the ingestion flow JSON by adjusting the position of nodes for better layout, adding a new input field for ingestion metadata, and updating the code hash. These changes improve the clarity and functionality of the component configurations, aligning with best practices for robust async development and enhancing the overall user experience.
This commit updates the ingestion flow JSON by modifying the last updated timestamp, changing the code hash, and adding the "anyio" dependency to the metadata. Additionally, it refines the File component's description and input options for advanced document processing, ensuring better clarity and functionality. These changes align with best practices for robust async development and enhance the overall user experience.
This commit modifies the ingestion flow JSON by adding the "lf_version" field to components, updating the last updated timestamp, and changing the selection state of a node. Additionally, it refines the file path handling and improves the overall clarity of the configuration. These changes align with best practices for robust async development and enhance the functionality of the ingestion flow.
This commit updates the ingestion flow JSON by modifying the SplitText component to include new input options such as "text_key" and "keep_separator", along with a detailed documentation link. Additionally, it refines the File component's description and adds new input fields for advanced document processing, improving clarity and functionality. These changes align with best practices for robust async development and enhance the overall user experience.
This commit refines the ingestion flow JSON by reintroducing an edge connection between the File and SplitText nodes, ensuring proper data flow. It also updates the last updated timestamp and modifies the selection state of a node, contributing to improved functionality and user experience. These changes align with best practices for async development and enhance the overall robustness of the ingestion flow.
This commit modifies the ingestion flow configuration by adding a new input option for file paths and updating the last updated timestamp. It also refines the OpenSearchHybridComponent to enhance authentication handling and input configurations. These changes improve the functionality and user experience of the ingestion flow, aligning with best practices for async development.
This commit updates the ingestion flow JSON configuration, including modifications to the last updated timestamps, dimensions of UI components, and selected output types. Additionally, it enhances the OpenSearchHybridComponent by refining input options and ensuring proper handling of authentication settings. These changes improve the overall functionality and user experience of the ingestion flow.
This commit modifies the ingestion flow JSON by updating the last_updated timestamp, removing the obsolete File Path input field, and adjusting the file_path array to be empty. Additionally, it corrects the height measurement of a UI component and changes the selected state of a node. These updates contribute to a cleaner and more efficient configuration, aligning with best practices for async code development.
This commit updates the ingestion flow JSON configuration to enhance the OpenSearch hybrid component. Key changes include renaming the component to OpenSearchHybrid, updating input fields for better clarity, and improving the handling of JWT authentication. Additionally, the commit introduces new parameters for search configuration, such as engine selection and filter expressions, while ensuring the overall structure adheres to robust async coding practices and well-documented code.
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.
