search

tonykipkemboi / ollama_pdf_rag

A demo Jupyter Notebook showcasing a simple local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.
MIT License
180 stars 85 forks source link

README is misleading for setting up the streamlit app #9

Closed hesreallyhim closed 3 months ago

hesreallyhim commented 3 months ago

The README.md for this (very nice) project states the following:

Running the Streamlit application
Clone repo: Run this in your terminal

git clone https://github.com/tonykipkemboi/ollama_pdf_rag.git

Install Dependencies: Execute to install dependencies

pip install -r requirements.txt

Launch the App: Run to start the Streamlit interface on localhost

streamlit run streamlit_app.py

The problem is the requirements.txt does not really contain all the necessary dependencies to run the app (e.g. unstructured). I decided I wanted to see the demo before I went though the notebook. So i installed from requirements.txt, but when I ran streamlit run streamlit_app.py there were a ton of missing dependencies. These dependencies are installed as you go through the notebook. After going through the notebook, the demo app worked great.

You might consider (a) moving the pip install commands out of the notebook and into the requirements.txt (b) modifying the README to note this issue, and not suggest that the streamlit app will work just by running pip install -r requirements.txt.

tonykipkemboi commented 3 months ago

Thanks for catching them and letting me know @hesreallyhim. I uploaded the files from my phone at the airport and haven't had time to revisit them since. I appreciate your feedback. I've update the dependecies list.