github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-21 14:18:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/namespace pinecone (#581)

Browse Source 
Co-authored-by: mmorzywolek <89693033+mmorzywolek@users.noreply.github.com>
This commit is contained in:
Harrison Chase 2023-01-11 06:05:48 -08:00 committed by GitHub
parent ffc7e04d44
commit 5ba46f6d0c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
langchain/vectorstores/pinecone.py
View File

@ -91,6 +91,7 @@ class Pinecone(VectorStore):
batch_size: int = 32, batch_size: int = 32,
text_key: str = "text", text_key: str = "text",
index_name: Optional[str] = None, index_name: Optional[str] = None,
namespace: Optional[str] = None,
**kwargs: Any, **kwargs: Any,
) -> Pinecone: ) -> Pinecone:
"""Construct Pinecone wrapper from raw documents. """Construct Pinecone wrapper from raw documents.
@ -121,7 +122,11 @@ class Pinecone(VectorStore):
"Please install it with `pip install pinecone-client`." "Please install it with `pip install pinecone-client`."
) )
_index_name = index_name or str(uuid.uuid4()) _index_name = index_name or str(uuid.uuid4())
index = None indexes = pinecone.list_indexes() # checks if provided index exists
if _index_name in indexes:
index = pinecone.Index(_index_name)
else:
index = None
for i in range(0, len(texts), batch_size): for i in range(0, len(texts), batch_size):
# set end position of batch # set end position of batch
i_end = min(i + batch_size, len(texts)) i_end = min(i + batch_size, len(texts))
@ -143,5 +148,5 @@ class Pinecone(VectorStore):
pinecone.create_index(_index_name, dimension=len(embeds[0])) pinecone.create_index(_index_name, dimension=len(embeds[0]))
index = pinecone.Index(_index_name) index = pinecone.Index(_index_name)
# upsert to Pinecone # upsert to Pinecone
index.upsert(vectors=list(to_upsert)) index.upsert(vectors=list(to_upsert), namespace=namespace)
return cls(index, embedding.embed_query, text_key) return cls(index, embedding.embed_query, text_key)