-
Notifications
You must be signed in to change notification settings - Fork 103
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Can't download models anymore, not sure why. Used to work perfectly #100
Comments
So far, I've determined that this doesn't seem to be an issue with chatdocs, as I've seen it in similar projects (I forget if I saw the exact same error in PrivateGPT or LocalGPT, I think it was Local). I'm pretty sure this is specifically an issue with LangChain, but I don't understand the error well enough to properly report it. Hopefully someone else can figure it out. So far I do have a "working" (still some warnings with LangChain) build on my less powerful laptop, solely because I haven't installed any other user made python programs on it. I'm just gonna not touch it on my laptop until the next update of Langchain, PrivateGPT, and/or ChatDocs brings stability back. I've tried pip freeze > requirements.txt on my laptop, then pip install -r requirements.txt to my desktop, but that also didn't work. I was getting an error that some of the packages required python < 3.11, even though I only installed 3.11.7 on my laptop (only other version I've ever installed on my laptop was 3.11.5). For reference I almost never code in Python, only Java, so there's a lot about python I really don't know about. I've pretty much given up on trying to make it work on my desktop right now since I have it working on my laptop. Fortunately small language models have become a lot more powerful. Thanks again for the work you've given over the last year. |
Yes, I also met same problem. |
Just to give an update, this is still the traceback after running chatdocs download please let me know if there's a better way to format this from the terminal ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ During handling of the above exception, another exception occurred: ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ During handling of the above exception, another exception occurred: ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ |
For the time being, this might fix the issue you all have noted (at least for GGUF models):
Here's a turnkey demo script you can try as well that's working as of right now: |
I got this warning and I'm having trouble understanding what to do. I recently reset my windows 11 pc running an i7-12700, 3060 ti, and 32gb ddr5 ram, and reinstalled python 3.11.7, Visual studio (including build tools), and CUDA toolkit 12.2
This happens after I run "chatdocs download"
C:\Users\j\AppData\Local\Programs\Python\Python311\Lib\site-packages\langchain\embeddings_init_.py:29: LangChainDeprecationWarning: Importing embeddings from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
.To install langchain-community run
pip install -U langchain-community
.warnings.warn(
C:\Users\j\AppData\Local\Programs\Python\Python311\Lib\site-packages\langchain\embeddings_init_.py:29: LangChainDeprecationWarning: Importing embeddings from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:
from langchain_community.embeddings import HuggingFaceEmbeddings
.To install langchain-community run
pip install -U langchain-community
.warnings.warn(
C:\Users\j\AppData\Local\Programs\Python\Python311\Lib\site-packages\langchain\llms_init_.py:548: LangChainDeprecationWarning: Importing LLMs from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:
from langchain_community.llms import CTransformers
.To install langchain-community run
pip install -U langchain-community
.warnings.warn(
C:\Users\j\AppData\Local\Programs\Python\Python311\Lib\site-packages\langchain\llms_init_.py:548: LangChainDeprecationWarning: Importing LLMs from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:
from langchain_community.llms import HuggingFacePipeline
.To install langchain-community run
pip install -U langchain-community
.warnings.warn(
The traceback is really long, but it ends with this:
ConnectionError: (ProtocolError('Connection aborted.', ConnectionResetError(10054, 'An existing
connection was forcibly closed by the remote host', None, 10054, None)), '(Request ID:
31c0ce51-239b-4d01-83db-b2fb46516f05)')
Any help or advice is greatly appreciated. I've had this project working in the past with amazing results and I'm extremely grateful for the work put into this and it's open source nature. I'm hoping to continue using it as I have in the past. I'm also open to work arounds such as downloading the models manually from huggingface, but would also appreciate being told where I should put them.
The text was updated successfully, but these errors were encountered: