github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-25 08:03:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

added i_end in batch extraction (#907)

Browse Source 
Fix for issue #906 

Switches `[i : i + batch_size]` to `[i : i_end]` in Pinecone
`from_texts` method
This commit is contained in:
James Briggs 2023-02-06 20:45:56 +00:00 committed by GitHub
parent 82c080c6e6
commit 3aa53b44dd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
langchain/vectorstores/pinecone.py
View File

@ -198,17 +198,17 @@ class Pinecone(VectorStore):
# 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))
# get batch of texts and ids # get batch of texts and ids
lines_batch = texts[i : i + batch_size] lines_batch = texts[i:i_end]
# create ids if not provided # create ids if not provided
if ids: if ids:
ids_batch = ids[i : i + batch_size] ids_batch = ids[i:i_end]
else: else:
ids_batch = [str(uuid.uuid4()) for n in range(i, i_end)] ids_batch = [str(uuid.uuid4()) for n in range(i, i_end)]
# create embeddings # create embeddings
embeds = embedding.embed_documents(lines_batch) embeds = embedding.embed_documents(lines_batch)
# prep metadata and upsert batch # prep metadata and upsert batch
if metadatas: if metadatas:
metadata = metadatas[i : i + batch_size] metadata = metadatas[i:i_end]
else: else:
metadata = [{} for _ in range(i, i_end)] metadata = [{} for _ in range(i, i_end)]
for j, line in enumerate(lines_batch): for j, line in enumerate(lines_batch):