Rag Knowledge Chat Boot

# rag-qa-self RAG based application on question and answer about myself I wrote about this in this article: [How I Built a RAG-based AI Chatbot from My Personal Data](https://medium.com/keeping-up-with-ai/how-i-built-a-rag-based-ai-chatbot-from-my-personal-data-88eec0d3483c) **Overview** This AI-powered app, built with Streamlit, uses a Large Language Model (LLM) to answer questions based on PDF data about Ana. Key technologies include: - Langchain as the framework, - GPT4All for embedding generation, - Gemini 1.5 as the LLM, - Streamlit for the user interface, and - Chroma DB as the vector database. create the .pdf datasets before very vector db creation delete chroma folder **Instructions** 1. run pip install -r requirements.txt 2. generate your own GEMINI API KEY from https://aistudio.google.com/ and put it in .env file as GEMINI_API_KEY = "YOUR_KEY" 3. run `python create_db.py` in the terminal to create the vector database from the documents. 4. run `streamlit run main.py` to launch streamlit UI in the browser #rag This project implements a Retrieval-Augmented Generation (RAG) chatbot designed to provide accurate, context-aware responses by combining Large Language Models (LLMs) with a domain-specific knowledge base. It leverages retrieval mechanisms to fetch relevant documents or information snippets and uses an LLM to generate natural, coherent answers grounded in the retrieved data. #road map A phased approach to build the RAG Knowledge Base Chatbot: Phase 1 — Setup and Data Preparation Phase 2 — Retrieval Pipeline Phase 3 — Generation and Integration Phase 4 — API and UI Development Phase 5 — Testing, Polish, and Deployment