github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-21 14:18:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

langchain: revert "init_chat_model() to support ChatOllama from langchain-ollama" (#24819)

Browse Source 
Reverts langchain-ai/langchain#24818

Overlooked discussion in
https://github.com/langchain-ai/langchain/pull/24801.
This commit is contained in:
ccurme 2024-07-30 10:23:36 -04:00 committed by GitHub
parent 5abfc85fec
commit b7bbfc7c67
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
libs/langchain/langchain/chat_models/base.py
View File

@ -118,7 +118,7 @@ def init_chat_model(
- mistralai (langchain-mistralai) - mistralai (langchain-mistralai)
- huggingface (langchain-huggingface) - huggingface (langchain-huggingface)
- groq (langchain-groq) - groq (langchain-groq)
- ollama (langchain-ollama) - ollama (langchain-community)
Will attempt to infer model_provider from model if not specified. The Will attempt to infer model_provider from model if not specified. The
following providers will be inferred based on these model prefixes: following providers will be inferred based on these model prefixes:
@ -336,8 +336,8 @@ def _init_chat_model_helper(
return ChatFireworks(model=model, **kwargs) return ChatFireworks(model=model, **kwargs)
elif model_provider == "ollama": elif model_provider == "ollama":
_check_pkg("langchain_ollama") _check_pkg("langchain_community")
from langchain_ollama import ChatOllama from langchain_community.chat_models import ChatOllama
return ChatOllama(model=model, **kwargs) return ChatOllama(model=model, **kwargs)
elif model_provider == "together": elif model_provider == "together":