github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-26 00:23:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

openai[patch]: run _tokenize in background thread in async embedding invocations (#31312)

Browse Source
This commit is contained in:
ccurme 2025-05-22 10:27:33 -04:00 committed by GitHub
parent f16456139b
commit 1b5ffe4107
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
libs/partners/openai/langchain_openai/embeddings/base.py
View File

@ -8,6 +8,7 @@ from typing import Any, Literal, Optional, Union, cast
import openai import openai
import tiktoken import tiktoken
from langchain_core.embeddings import Embeddings from langchain_core.embeddings import Embeddings
from langchain_core.runnables.config import run_in_executor
from langchain_core.utils import from_env, get_pydantic_field_names, secret_from_env from langchain_core.utils import from_env, get_pydantic_field_names, secret_from_env
from pydantic import BaseModel, ConfigDict, Field, SecretStr, model_validator from pydantic import BaseModel, ConfigDict, Field, SecretStr, model_validator
from typing_extensions import Self from typing_extensions import Self
@ -525,7 +526,9 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
_chunk_size = chunk_size or self.chunk_size _chunk_size = chunk_size or self.chunk_size
client_kwargs = {**self._invocation_params, **kwargs} client_kwargs = {**self._invocation_params, **kwargs}
_iter, tokens, indices = self._tokenize(texts, _chunk_size) _iter, tokens, indices = await run_in_executor(
None, self._tokenize, texts, _chunk_size
)
batched_embeddings: list[list[float]] = [] batched_embeddings: list[list[float]] = []
for i in range(0, len(tokens), _chunk_size): for i in range(0, len(tokens), _chunk_size):
response = await self.async_client.create( response = await self.async_client.create(