github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-04 04:07:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make tqdm for OpenAIEmbeddings optional (#7247)

Browse Source 
- Description: I have added a `show_progress_bar` parameter (defaults.to
`False`) to the `OpenAIEmbeddings`. If the user sets `show_progress_bar`
to `True`, a progress bar will be displayed.
  - Issue: #7246
  - Dependencies: N/A
  - Tag maintainer: @hwchase17, @baskaryan
  - Twitter handle: N/A
This commit is contained in:
Myeongseop Kim 2023-07-06 12:36:01 +09:00 committed by GitHub
parent c36f852846
commit 57d8a3d1e8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
langchain/embeddings/openai.py
View File

@ -191,6 +191,8 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
when using one of the many model providers that expose an OpenAI-like when using one of the many model providers that expose an OpenAI-like
API but with different models. In those cases, in order to avoid erroring API but with different models. In those cases, in order to avoid erroring
when tiktoken is called, you can specify a model name to use here.""" when tiktoken is called, you can specify a model name to use here."""
show_progress_bar: bool = False
"""Whether to show a progress bar when embedding."""
class Config: class Config:
"""Configuration for this pydantic object.""" """Configuration for this pydantic object."""
@ -309,12 +311,17 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
batched_embeddings = [] batched_embeddings = []
_chunk_size = chunk_size or self.chunk_size _chunk_size = chunk_size or self.chunk_size
try:
import tqdm
_iter = tqdm.tqdm(range(0, len(tokens), _chunk_size)) if self.show_progress_bar:
except ImportError: try:
import tqdm
_iter = tqdm.tqdm(range(0, len(tokens), _chunk_size))
except ImportError:
_iter = range(0, len(tokens), _chunk_size)
else:
_iter = range(0, len(tokens), _chunk_size) _iter = range(0, len(tokens), _chunk_size)
for i in _iter: for i in _iter:
response = embed_with_retry( response = embed_with_retry(
self, self,