Overview
This project demonstrates how to build a Retrieval-Augmented Generation (RAG) assistant—an AI system that can answer questions about your own documents using state-of-the-art language models and vector search. The assistant leverages ChromaDB for vector storage, Sentence Transformers for embeddings, and supports multiple LLM providers (OpenAI, Groq, Google Gemini).

Features

• Document Ingestion: Load and chunk .txt documents from a folder.
• Embeddings: Generate vector embeddings for document chunks using Sentence Transformers.
• Vector Database: Store and search document embeddings with ChromaDB.
• Multi-LLM Support: Query OpenAI, Groq, or Google Gemini models.
• RAG Pipeline: Retrieve relevant context and generate answers grounded in your data.
  -Configurable: Easily switch models and providers via .env file.

Quick Start

1. Clone and Install
   git clone
   cd
   python -m venv .venv
   .venv\Scripts\activate # On Windows
   pip install -r requirements.txt

2. Configure Environment
   Create a .env file in the project root:
   GROQ_API_KEY=your_groq_api_key
   GROQ_MODEL=llama-3.3-70b-versatile
   EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
   CHROMA_COLLECTION_NAME=rag_documents
   You can also use OPENAI_API_KEY or GOOGLE_API_KEY if you prefer those providers.

3. Add Documents
   Place your .txt files in the data/ directory. Example:
   data/quantum_computing.txt

4. Run the Assistant
   cd src
   python app.py

How It Works
Document Loading
Documents are loaded from the data/ directory:

Customization

Change Embedding Model:
Edit EMBEDDING_MODEL in .env to use a different Sentence Transformer.
Switch LLM Provider:
Set the appropriate API key in .env (OPENAI_API_KEY, GROQ_API_KEY, or GOOGLE_API_KEY).
Tune Chunk Size:
Adjust the chunk_size parameter in chunk_text() for your document type.

Troubleshooting

Model Download Slow?
The first run downloads models from HuggingFace. Wait for completion.
Symlink Warning on Windows?
Safe to ignore, or enable Developer Mode for better caching.
Import Errors?
Ensure you run python app.py from the src directory and both app.py and vectordb.py are in src/.

Example Q&A
Enter a question or 'quit' to exit: What is quantum superposition?
AI: Quantum superposition is a fundamental principle of quantum mechanics where a quantum system can exist in multiple states at once until measured...

Conclusion
This project provides a robust, extensible template for building your own RAG-powered AI assistant.
You can easily adapt it to new document types, swap LLMs, or extend the pipeline for more advanced use cases.