A Retrieval-Augmented Generation (RAG) powered conversational assistant that answers questions based on a custom knowledge base using LangChain and vector storage.
This project demonstrates a complete RAG pipeline that:
rag-assistant/
├── src/
│ ├── __init__.py
│ ├── document_loader.py # Document ingestion utilities
│ ├── vector_store.py # Vector store management
│ ├── rag_chain.py # Core RAG pipeline
│ ├── memory.py # Conversation memory
│ └── utils.py # Utility functions
├── data/ # Sample documents and datasets
├── examples/ # Example queries and outputs
├── cli.py # Command-line interface
├── app.py # Streamlit web application
├── config.py # Configuration management
├── requirements.txt # Python dependencies
└── README.md # This file
Clone the repository:
git clone <your-repo-url> cd rag-assistant
Create a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
Install dependencies:
pip install -r requirements.txt
Set up environment variables:
cp .env.example .env # Edit .env with your OpenAI API key
Create a .env file with your configuration:
OPENAI_API_KEY=your_openai_api_key_here VECTOR_STORE_TYPE=faiss # or chroma MODEL_NAME=gpt-3.5-turbo TEMPERATURE=0.7 MAX_TOKENS=1000
from src.document_loader import DocumentLoader from src.vector_store import VectorStore # Load documents loader = DocumentLoader() documents = loader.load_documents("data/") # Create and populate vector store vector_store = VectorStore(store_type="faiss") vector_store.add_documents(documents)
from src.rag_chain import RAGChain # Initialize RAG chain rag = RAGChain(vector_store) # Ask a question response = rag.query("What is this document about?") print(response)
python cli.py --query "Your question here"
streamlit run app.py
Here are some sample questions to test your RAG assistant:
The project includes sample datasets for testing:
This project is submitted for the Agentic AI Developer Certification Program and demonstrates:
Run the certification evaluation script:
python certification_evaluation.py
Run the certification demo:
python examples/certification_demo.py
The assistant is evaluated on:
This is a certification project, but feel free to:
This project is created for educational purposes as part of the Agentic AI Developer Certification Program.
Built with ❤️ for the Agentic AI Developer Certification Program