Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-10 01:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

partners: fix of issue #24880 (#25229)

Browse Source 
- Description: As described in the related issue: There is an error
occuring when using langchain-openai>=0.1.17 which can be attributed to
the following PR: #23691
Here, the parameter logprobs is added to requests per default.
However, AzureOpenAI takes issue with this parameter as stated here:
https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/chatgpt?tabs=python-new&pivots=programming-language-chat-completions
-> "If you set any of these parameters, you get an error."
Therefore, this PR changes the default value of logprobs parameter to
None instead of False. This results in it being filtered before the
request is sent.
- Issue: #24880
- Dependencies: /

Co-authored-by: blaufink <sebastian.brueckner@outlook.de>
This commit is contained in:
blaufink 2024-08-09 15:21:37 +02:00 committed by GitHub
parent 3b7437d184
commit c81c77b465
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
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/partners/openai/langchain_openai/chat_models/base.py
View File

@ -332,7 +332,7 @@ class BaseChatOpenAI(BaseChatModel):
"""Penalizes repeated tokens according to frequency."""
seed: Optional[int] = None
"""Seed for generation"""
logprobs: Optional[bool] = False
logprobs: Optional[bool] = None
"""Whether to return logprobs."""
top_logprobs: Optional[int] = None
"""Number of most likely tokens to return at each token position, each with