feat: Full support for Astra DB as a backend#1340
Draft
Conversation
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
Brings in latest main changes including FastMCP streamable HTTP server, knn_vector field mapping consolidation, and JWT cookie handling fix. Resolved conflicts in uv.lock and pyproject.toml (deduplicated prometheus-fastapi-instrumentator); restored missing knowledge_backend cleanup filter in _delete_existing_default_docs and removed leftover ensure_embedding_field_exists call in processors.py that the knowledge backend now handles internally.
This comment has been minimized.
This comment has been minimized.
Contributor
|
Build successful! ✅ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces support for Astra DB as an alternative vector backend to OpenSearch, allowing dynamic selection of the knowledge backend and associated flows. The changes include configuration updates across Docker, Helm charts, and Python code to enable backend selection, Astra DB credentials, and flow definitions. The API is updated to expose the selected backend and to use the appropriate flow IDs and files based on the backend.
Key changes include:
Backend Selection and Configuration:
VECTOR_BACKEND,ASTRA_DB_APPLICATION_TOKEN, andASTRA_DB_API_ENDPOINTto support Astra DB as a vector backend, in addition to OpenSearch. (docker-compose.yml[1] [2] [3];kubernetes/helm/openrag/values.yaml[4] [5];kubernetes/helm/openrag/templates/backend/backend-dotenv.yaml[6];kubernetes/helm/openrag/templates/langflow/langflow-dotenv.yaml[7]src/config/config_manager.py[1] [2];src/config/settings.py[3] [4]Flow Definitions and Dynamic Flow Selection:
FlowDefinitiondataclass and dictionaries for OpenSearch and Astra DB flow definitions, including flow IDs, filenames, and vector store node IDs. This enables dynamic flow selection based on the active backend. (src/config/settings.pysrc/config/settings.pyR49-R113)src/api/settings.py[1] [2] [3] [4]API and Model Updates:
src/api/settings.py[1] [2];src/api/v1/settings.py[3] [4] [5]src/api/documents.pysrc/api/documents.pyL120-R127)Helm and Flow File Updates:
kubernetes/helm/openrag/values.yaml[1] [2];kubernetes/helm/openrag/templates/configmaps/app-config-configmap.yaml[3]These changes collectively enable the system to support both OpenSearch and Astra DB as vector backends, with dynamic configuration and flow selection based on the chosen backend.