💬 RAG chatbot

A simple streamlit app that does RAG

How to run it on your own machine

1. Install the requirements

   $ pip install -r requirements.txt
   

2. Run the app

   $ streamlit run src/app.py
   

Salesman Chatbot

this project is a step by step development project of an insurance salesman chatbot,
the chatbot should be trained on a corpus of data related to a product it is selling,
the bot is setup using open source options, no free trials from providers required,

Tech/AI stack

POLM Python version 3.12 (langchain) Ollama for edge device language model hosting LlamaIndex for DAQ and indexing MongoDB Atlas for general info storage

concepts

RAG

Further Improvements

• pdf processing pipeline
• structured data corpus fetch
• chatlog analysis
• health conditions dictionary
• model training via unsloth

Acknowledgement

Thanks for sharing these demos and blogs
using streamlit with ollama for prototyping
demo of streamlit with ollama

using llamaparse with ollama
the repo
the blog article

using ollama as a freemium backend service
run ollama with modal

setting up response streaming via fastAPI(compatible with modal labs) FastAPI Streaming Response: Error: Did not receive done or success response in stream

using structured outputs on ollama Structured outputs