This commit introduces support for the DISKANN index type in the Milvus vector database integration.
Changes include:
- Added `MILVUS_DISKANN_MAX_DEGREE` and `MILVUS_DISKANN_SEARCH_LIST_SIZE` configuration variables.
- Updated the Milvus client to recognize and configure the DISKANN index type during collection creation.
Replace direct CREATE EXTENSION commands with conditional checks to avoid
permission errors on Azure PostgreSQL Flexible Server where only
azure_pg_admin members can create extensions.
- Check pg_extension table before attempting to create vector extension
- Apply same fix to pgcrypto extension for consistency
- Allows following least privilege principle for database users
Fixes#12453
All fieldnames which are part of a query should
have an index for performance reasons. This is
even enforced on some qdrant cluster like those
on qdrant.io, and queries using a unindexed column
fail with an error.
The prefix string for qdrant collection is now
configurable, which means the same qdrant cluster
can be used to host more open webui instances and
to be able to separate the collections between the
different owui instances.
I've improved the pinecone.py file by:
Updated from the deprecated PineconeGRPC client to the newer Pinecone client
Modified the client initialization code to match the new API requirements
Added better response handling with getattr() to safely access attributes from response objects
Removed the streaming_upsert method which is not available in the newer client
Added safer attribute access with fallbacks throughout the code
Updated the close method to reflect that the newer client doesn't need explicit closing
These changes ensure the code is compatible with the latest Pinecone Python SDK and will be more robust against future changes. The key improvement is migrating away from the deprecated gRPC client which will eventually stop working.
