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
Expected:
When I enable hybrid and im using Elasticsearch v8.14+, I should be able to retrieve documents from both a bm25 based search and NN search using dense/sparse.
Actual:
Cannot perform the search as RRF is not supported
Reason:
Hybrid performs two retrieval searches and relies on RRF to balance the different result scores. In 8.14+, top level rank was removed and now the only way to do RRF is through retrievers query.
This is the code that builds the query that retrieves results from different methods and balances with RRF. link
suggested untested code change to equilivent retriever is:
RRF works well for Elasticsearch Cloud and self-hosted but uses a now deprecated query format.
For Elasticsearch Serverless only the new style of RRF based on retrievers is supported.
We will migrate to the new style to enable support for Serverless.
pquentin
changed the title
[Bug] Vectorstore Helper: Hybrid does not work in 8.14+
[Bug] Vectorstore Helper: Hybrid does not work in Elasticsearch Serverless
Sep 25, 2024
miguelgrinberg
added a commit
to miguelgrinberg/elasticsearch-py
that referenced
this issue
Sep 30, 2024
Expected:
When I enable hybrid and im using Elasticsearch v8.14+, I should be able to retrieve documents from both a bm25 based search and NN search using dense/sparse.
Actual:
Cannot perform the search as RRF is not supported
Reason:
Hybrid performs two retrieval searches and relies on RRF to balance the different result scores. In 8.14+, top level rank was removed and now the only way to do RRF is through retrievers query.
This is the code that builds the query that retrieves results from different methods and balances with RRF. link
suggested untested code change to equilivent retriever is:
Full example of a query:
The text was updated successfully, but these errors were encountered: