Installation

Install VectorDB using uv package manager

Prerequisites

Before installing VectorDB, ensure you have:

• Python 3.11 or higher - VectorDB requires Python 3.11+
• uv package manager - VectorDB uses uv for dependency management

VectorDB requires Python 3.11 or later. Check your Python version with python --version

Install uv

VectorDB uses uv for fast, reliable dependency management. If you don’t already have uv installed:

pip

pip install uv

uv is significantly faster than pip and provides better dependency resolution. Learn more at uv documentation.

Install VectorDB

1. Clone the repository

   Clone the VectorDB repository from GitHub:

   git clone https://github.com/avnlp/vectordb.git
   cd vectordb
   
2. Install dependencies

   Use uv to install all project dependencies:

   uv sync
   

   This command will:

   • Create a virtual environment in .venv/
   • Install all production dependencies
   • Install development dependencies (tests, linting, type checking)

   The uv sync command reads from pyproject.toml and ensures all dependencies are installed with the correct versions.

3. Activate the virtual environment

   Activate the virtual environment created by uv:

   Unix/macOS

   source .venv/bin/activate
   

   You should see (.venv) in your terminal prompt when the environment is active.

4. Verify installation

   Verify that VectorDB is installed correctly:

   python -c "import vectordb; print('VectorDB installed successfully!')"
   

Environment variables

VectorDB uses environment variables for API keys and database connections. Create a .env file in your project root:

.env

# Vector Database API Keys
PINECONE_API_KEY=your_pinecone_key
QDRANT_API_KEY=your_qdrant_key
WEAVIATE_API_KEY=your_weaviate_key

# LLM API Keys (for RAG)
GROQ_API_KEY=your_groq_key
OPENAI_API_KEY=your_openai_key

# Database Paths (for local databases)
CHROMA_PATH=./chroma_data
MILVUS_URI=./milvus_data

You only need to configure the vector databases and LLMs you plan to use. VectorDB will work with whatever services you have credentials for.

Optional: Install for production only

If you only need production dependencies (no testing or development tools), you can exclude the dev group:

uv sync --no-dev

Next steps

Quickstart

Build your first RAG pipeline

Configuration

Learn about configuration files