github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-04 20:28:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

langchain[patch]: use async_embed_with_retry in _aget_len_safe_embeddings (#14110)

Browse Source 
**Description**

`embed_with_retry` is for sync operations and not for async operations.
Use `async_embed_with_retry` for appropriate async operations.


I'm using `OpenAIEmbedding(http_client=httpx.AsyncClient())` with only
async operations.
However, I got an error when I use `embedding.aembed_documents` because
`embed_with_retry` uses sync OpenAI client with async http client.
This commit is contained in:
Devin Dahoon Kim 2023-12-02 03:47:07 +09:00 committed by GitHub
parent 371bcb7580
commit 32da0a4d71
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libs/langchain/langchain/embeddings/openai.py
View File

@ -523,7 +523,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
for i in range(len(texts)):
_result = results[i]
if len(_result) == 0:
average_embedded = embed_with_retry(
average_embedded = await async_embed_with_retry(
self,
input="",
**self._invocation_params,