Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
Running python src/make_db.py --download_some=True I get the following error
Traceback (most recent call last):
File "/home/jupyter/Desktop/h2ogpt/src/make_db.py", line 9, in <module>
from gpt_langchain import path_to_docs, get_some_dbs_from_hf, all_db_zips, some_db_zips, create_or_update_db, \
File "/home/jupyter/Desktop/h2ogpt/src/gpt_langchain.py", line 2077, in <module>
from langchain_together import ChatTogether
File "/home/jupyter/conda/envs/h2ogpt/lib/python3.10/site-packages/langchain_together/__init__.py", line 1, in <module>
from langchain_together.chat_models import ChatTogether
File "/home/jupyter/conda/envs/h2ogpt/lib/python3.10/site-packages/langchain_together/chat_models.py", line 18, in <module>
from langchain_openai.chat_models.base import BaseChatOpenAI
ModuleNotFoundError: No module named 'langchain_openai.chat_models'; 'langchain_openai' is not a package
the reason is the langchain_openai wrapper src/langchain_openai.py (see a similar issue here). I fixed it by renaming src/langchain_openai.py into src/langchain_openai_wrapper.py and updating related imports. Things work now, but maybe we can think about a cleaner fix for this? I wonder if the other wrappers cause other issues here and there.
Running
python src/make_db.py --download_some=True
I get the following errorthe reason is the langchain_openai wrapper
src/langchain_openai.py
(see a similar issue here). I fixed it by renamingsrc/langchain_openai.py
intosrc/langchain_openai_wrapper.py
and updating related imports. Things work now, but maybe we can think about a cleaner fix for this? I wonder if the other wrappers cause other issues here and there.OS Linux / Debian 11 Python 10.3