VectorDB

Modular vector database with a FastAPI backend.

Requirements

• Python 3.12+

Setup

python -m venv .venv
.venv\Scripts\activate  # Windows
pip install -e ".[dev]"

Configuration

Copy .env.example to .env and adjust values as needed.

Run

vectordb
# or
uvicorn vectordb.api.app:create_app --factory --reload

Open the demonstration UI at http://localhost:8000/demo.

The demo workflow:

1. Load the sample corpus or ingest your own documents
2. Inspect stored documents and vector index stats
3. Run a question to see retrieval scores and metadata matches
4. Review the thin LLM answer generated from retrieved context

Optional OpenAI integration:

VECTORDB_LLM_PROVIDER=openai
VECTORDB_OPENAI_API_KEY=your-key-here

Test

pytest