You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is this a new feature, an improvement, or a change to existing functionality?
New Feature
How would you describe the priority of this feature request
Significant improvement
Please provide a clear description of problem this feature solves
This PR will add bm25 support provided by Milvus to the VDBTask sink. This will unlock hybrid search where we can query against both BM25 and model embeddings.
Describe the feature, and optionally a solution or implementation and any alternatives
We would allow the user to activate this feature using a boolean when they create the vdb task for their pipeline.
i.e.
VDBTask(bm25=True), This will load both the model embedding index and a bm25 index.
Additional context
No response
The text was updated successfully, but these errors were encountered:
Is this a new feature, an improvement, or a change to existing functionality?
New Feature
How would you describe the priority of this feature request
Significant improvement
Please provide a clear description of problem this feature solves
This PR will add bm25 support provided by Milvus to the VDBTask sink. This will unlock hybrid search where we can query against both BM25 and model embeddings.
Describe the feature, and optionally a solution or implementation and any alternatives
We would allow the user to activate this feature using a boolean when they create the vdb task for their pipeline.
i.e.
VDBTask(bm25=True), This will load both the model embedding index and a bm25 index.
Additional context
No response
The text was updated successfully, but these errors were encountered: