github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-09 14:35:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ElasticsearchStore] Improve migration text to ElasticsearchStore (#11158)

Browse Source 
We noticed that as we have been moving developers to the new
`ElasticsearchStore` implementation, we want to keep the
ElasticVectorSearch class still available as developers transition
slowly to the new store.

To speed up this process, I updated the blurb giving them a better
recommendation of why they should use ElasticsearchStore.
This commit is contained in:
Joseph McElroy 2023-09-28 20:40:18 +01:00 committed by GitHub
parent 9b0029b9c2
commit 822fc590d9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
libs/langchain/langchain/vectorstores/elastic_vector_search.py
View File

@ -1,4 +1,3 @@
"""[DEPRECATED] Please use ElasticsearchStore instead."""
from __future__ import annotations from __future__ import annotations
import uuid import uuid
@ -51,9 +50,19 @@ def _default_script_query(query_vector: List[float], filter: Optional[dict]) ->
} }
@deprecated("0.0.265", alternative="ElasticsearchStore class.", pending=True)
class ElasticVectorSearch(VectorStore): class ElasticVectorSearch(VectorStore):
"""[DEPRECATED] `Elasticsearch` vector store. """
ElasticVectorSearch uses the brute force method of searching on vectors.
Recommended to use ElasticsearchStore instead, which gives you the option
to uses the approx HNSW algorithm which performs better on large datasets.
ElasticsearchStore also supports metadata filtering, customising the
query retriever and much more!
You can read more on ElasticsearchStore:
https://python.langchain.com/docs/integrations/vectorstores/elasticsearch
To connect to an `Elasticsearch` instance that does not require To connect to an `Elasticsearch` instance that does not require
login credentials, pass the Elasticsearch URL and index name along with the login credentials, pass the Elasticsearch URL and index name along with the
@ -339,10 +348,17 @@ class ElasticVectorSearch(VectorStore):
self.client.delete(index=self.index_name, id=id) self.client.delete(index=self.index_name, id=id)
@deprecated("0.0.265", alternative="ElasticsearchStore class.", pending=True)
class ElasticKnnSearch(VectorStore): class ElasticKnnSearch(VectorStore):
"""[DEPRECATED] `Elasticsearch` with k-nearest neighbor search """[DEPRECATED] `Elasticsearch` with k-nearest neighbor search
(`k-NN`) vector store. (`k-NN`) vector store.
Recommended to use ElasticsearchStore instead, which supports
metadata filtering, customising the query retriever and much more!
You can read more on ElasticsearchStore:
https://python.langchain.com/docs/integrations/vectorstores/elasticsearch
It creates an Elasticsearch index of text data that It creates an Elasticsearch index of text data that
can be searched using k-NN search. The text data is transformed into can be searched using k-NN search. The text data is transformed into
vector embeddings using a provided embedding model, and these embeddings vector embeddings using a provided embedding model, and these embeddings