Introducing the Quaterion: a framework for fine-tuning similarity learning models
Qdrant (read: quadrant ) is a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage points - vectors with an additional payload. Qdrant is tailored to extended filtering support. It makes it useful for all sorts of neural-network or semantic-based matching, faceted search, and other applications.
Qdrant is written in Rust 🦀, which makes it fast and reliable even under high load.
With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!
Qdrant team shared the result of the work they’ve been into during the last months - Quaterion. It is a framework for fine-tuning similarity learning models that streamlines the training process to make it significantly faster and cost-efficient.
To develop Quaterion, Qdrant team utilized PyTorch Lightning, leveraging a high-performing AI research approach to constructing training loops for ML models.
This framework empowers vector search solutions, such as semantic search, anomaly detection, and others, by advanced coaching mechanism, specially designed head layers for pre-trained models, and high flexibility in terms of customization according to large-scale training pipelines and other features.
