This is my first time asking a question on Stack Overflow. I am trying to run a Llama3 model that queries a PDF file on Streamlit. It uses llama index to chunk up the text and create a vector for each chunk. When you type a query, it creates a vector embedding for the query, finds the best match from the text pieces and gives them a Llama3 model running in Ollama. A link to the GitHub repo for this application can be found here:...
Originally asked by e.francis19 on Stack Exchange (stackoverflow) (CC BY-SA 4.0).
