A Retrieval Augmented Generation (RAG) system built with LangChain and Anthropic's Claude.

rag-project/
├── src/
│   └── rag_system/
│       ├── __init__.py
│       ├── llm.py
│       └── document_loader.py
├── tests/
│   ├── __init__.py
│   └── test_llm.py
├── setup.py
├── requirements.txt
├── .env.example
├── .cursorignore
└── README.md

• Python 3.9+
• OpenAI API key (or other LLM provider)

1. Clone the repository:

git clone <repository-url>
cd rag_system

2. Create and activate a virtual environment:

python -m venv venv

3. Activate the virtual environment:

• On macOS/Linux:

source venv/bin/activate

• On Windows:

venv\Scripts\activate

4. Install the package in development mode:

pip install -e .

4. Copy .env.example to .env and add your Anthropic API key:

cp .env.example .env
# Edit .env and add your ANTHROPIC_API_KEY

1. Ingest documents:

python -m rag_system.cli ingest documents/your_file.pdf

2. Query the system:

python -m rag_system.cli query "Your question here"

3. Interactive mode:

python -m rag_system.cli interactive

1. Run tests:

python -m pytest

2. Run specific test file:

python -m pytest tests/test_llm.py

• Document ingestion from various formats (PDF, TXT, HTML)
• Web content ingestion
• Semantic search using embeddings
• RAG implementation with Anthropic's Claude
• Interactive query interface
• Vector database storage with ChromaDB

• langchain
• langchain-community
• langchain-anthropic
• chromadb
• python-dotenv
• sentence-transformers
• beautifulsoup4
• requests
• pypdf
• pytest

MIT License