github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-22 14:49:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

[OpenSearch] Pass ids using from_texts and indexname in add_texts and search (#10969)

Browse Source 
### Description
This PR makes the following changes to OpenSearch:
1. Pass optional ids with `from_texts`
2. Pass an optional index name with `add_texts` and `search` instead of
using the same index name that was used during `from_texts`

### Issue
https://github.com/langchain-ai/langchain/issues/10967

### Maintainers
@rlancemartin, @eyurtsev, @navneet1v

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
This commit is contained in:
Naveen Tatikonda 2023-09-23 18:12:51 -05:00 committed by GitHub
parent f945426874
commit b0f21e2b50
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
libs/langchain/langchain/vectorstores/opensearch_vector_search.py
View File

@ -374,6 +374,7 @@ class OpenSearchVectorSearch(VectorStore):
"""
embeddings = self.embedding_function.embed_documents(list(texts))
_validate_embeddings_and_bulk_size(len(embeddings), bulk_size)
index_name = _get_kwargs_value(kwargs, "index_name", self.index_name)
text_field = _get_kwargs_value(kwargs, "text_field", "text")
dim = len(embeddings[0])
engine = _get_kwargs_value(kwargs, "engine", "nmslib")
@ -392,7 +393,7 @@ class OpenSearchVectorSearch(VectorStore):
return _bulk_ingest_embeddings(
self.client,
self.index_name,
index_name,
embeddings,
texts,
metadatas=metadatas,
@ -526,6 +527,7 @@ class OpenSearchVectorSearch(VectorStore):
embedding = self.embedding_function.embed_query(query)
search_type = _get_kwargs_value(kwargs, "search_type", "approximate_search")
vector_field = _get_kwargs_value(kwargs, "vector_field", "vector_field")
index_name = _get_kwargs_value(kwargs, "index_name", self.index_name)
if (
self.is_aoss
@ -601,7 +603,7 @@ class OpenSearchVectorSearch(VectorStore):
else:
raise ValueError("Invalid `search_type` provided as an argument")
response = self.client.search(index=self.index_name, body=search_query)
response = self.client.search(index=index_name, body=search_query)
return [hit for hit in response["hits"]["hits"]]
@ -663,6 +665,7 @@ class OpenSearchVectorSearch(VectorStore):
embedding: Embeddings,
metadatas: Optional[List[dict]] = None,
bulk_size: int = 500,
ids: Optional[List[str]] = None,
**kwargs: Any,
) -> OpenSearchVectorSearch:
"""Construct OpenSearchVectorSearch wrapper from raw documents.
@ -772,6 +775,7 @@ class OpenSearchVectorSearch(VectorStore):
embeddings,
texts,
metadatas=metadatas,
ids=ids,
vector_field=vector_field,
text_field=text_field,
mapping=mapping,