github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-20 11:31:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixes iter error in FAISS add_embeddings call (#5367)

Browse Source 
# Remove re-use of iter within add_embeddings causing error

As reported in https://github.com/hwchase17/langchain/issues/5336 there
is an issue currently involving the atempted re-use of an iterator
within the FAISS vectorstore adapter

Fixes # https://github.com/hwchase17/langchain/issues/5336

## Who can review?

Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:

  VectorStores / Retrievers / Memory
  - @dev2049
This commit is contained in:
Matt Wells 2023-05-28 17:59:30 +01:00 committed by GitHub
parent b705f260f4
commit 9a5c9df809
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
langchain/vectorstores/faiss.py
View File

@ -175,9 +175,8 @@ class FAISS(VectorStore):
f"adding items, which {self.docstore} does not" f"adding items, which {self.docstore} does not"
) )
# Embed and create the documents. # Embed and create the documents.
texts, embeddings = zip(*text_embeddings)
texts = [te[0] for te in text_embeddings]
embeddings = [te[1] for te in text_embeddings]
return self.__add(texts, embeddings, metadatas=metadatas, ids=ids, **kwargs) return self.__add(texts, embeddings, metadatas=metadatas, ids=ids, **kwargs)
def similarity_search_with_score_by_vector( def similarity_search_with_score_by_vector(