-
Notifications
You must be signed in to change notification settings - Fork 330
Fixes for MultimodalQnA with the Milvus vector db #1859
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Fixes for MultimodalQnA with the Milvus vector db #1859
Conversation
Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR fixes issues with MultimodalQnA’s integration with the Milvus vector database backend. It updates the docker-compose configuration to include missing environment variables, corrects the collection name in the README, and adds documentation regarding unsupported audio captions.
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| MultimodalQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml | Added missing dataprep endpoints (GET and DELETE) to support file operations |
| MultimodalQnA/docker_compose/intel/cpu/xeon/README.md | Updated the collection name to "LangChainCollection" and added a note about unsupported audio captions |
Dependency Review✅ No vulnerabilities or license issues found.Scanned FilesNone |
Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com>
ashahba
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
mkbhanda
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> (cherry picked from commit e10e6dd)
Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com>
Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com> Signed-off-by: Chingis Yundunov <c.yundunov@datamonsters.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
Description
This PR fixes a few issues when running MultimodalQnA with the Milvus vector database backend:
export COLLECTION_NAME=mm_rag_milvusas the README instructions state does not work. The test script instead usesexport COLLECTION_NAME="LangChainCollection", and this does work, so I updated the README to match.Issues
#1858
Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
None
Tests
Manually tested based on the README instructions. Existing tests did not fail, since the env setup in the script differed from the README.