httpx.ReadTimeout: timed out when running Llama3 model that queries PDF files on Streamlit

Hi. This is my first time creating a post on Streamlit.
I am running a Llama3 model on Streamlit that takes a PDF file and uses llama index to chunk up the text and create vectors. It then creates a vector embedding of the query, finds the best match from the text and gives them to a Llama3 model running in Ollama.

After running the model for around 3 minutes I receive the following message in my terminal “httpx.ReadTimeout: timed out”. I would like to note that the file I have been using is only about 28KB in size.

I have provided a link to the GitHub repo containing the code to operate the model: GitHub - teg-lad/streamlit_rag. No requirements file is provided although I have installed all of the packages included in the file into my venv. To operate the model, use streamlit run .\app.py.

I am not sure if this is also relevant, but when I run python .\app.py I receive this error: “AttributeError: st.session_state has no attribute “id”. Did you forget to initialize it? More info: Add statefulness to apps - Streamlit Docs”.

I am currently using Streamlit version 1.34.0 and Python version 3.12.3.

This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.