langchain/libs
Max Jakob de209af533
community[patch]: ElasticsearchStore: add relevance function selector (#16378)
Implement similarity function selector for ElasticsearchStore. The
scores coming back from Elasticsearch are already similarities (not
distances) and they are already normalized (see
[docs](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params)).
Hence we leave the scores untouched and just forward them.

This fixes #11539.

However, in hybrid mode (when keyword search and vector search are
involved) Elasticsearch currently returns no scores. This PR adds an
error message around this fact. We need to think a bit more to come up
with a solution for this case.

This PR also corrects a small error in the Elasticsearch integration
test.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-01-22 11:52:20 -07:00
..
cli Make packages optional (#15727) 2024-01-08 17:09:21 -08:00
community community[patch]: ElasticsearchStore: add relevance function selector (#16378) 2024-01-22 11:52:20 -07:00
core core[patch]: Release 0.1.14 (#16382) 2024-01-22 08:28:03 -08:00
experimental core[patch]: simple prompt pretty printing (#15968) 2024-01-12 21:08:51 -05:00
langchain langchain[patch]: Release 0.1.2 (#16388) 2024-01-22 09:32:24 -08:00
partners langchain_google_vertexai:Enable the use of langchain's built-in tools in Gemini's function calling (#16341) 2024-01-22 11:16:36 -07:00