A Rust vector engine with genuinely good payload filtering.
Qdrant's distinguishing feature is that metadata filters are applied inside the HNSW traversal rather than before or after it, so a filtered search stays both fast and accurate — the case where simpler engines either scan too much or miss results. Quantisation options cut memory substantially on large collections.
The embedding database that gets out of your way.
A distributed vector database built for billion-scale collections.
Visual builder for agents and RAG flows, deployable as an API.
Fair-code workflow automation with AI steps built in.
Track the experiments, register the models, ship the good one.
Fine-tuning driven entirely by a YAML config.
No reviews yet — be the first to review this project.
Sign in to write a review.
Sign In