Compression
Uncompressed vectors can be large. Compressed vectors lose some information, but they use fewer resources and can be very cost effective.
Vector quantization
To balance resource costs and system performance, consider one of these options:
- Rotational Quantization (RQ) (recommended)
- Product Quantization (PQ)
- Binary Quantization (BQ)
- Scalar Quantization (SQ)
You can also disable quantization for a collection.
Starting with v1.33, you can set a default quantization for new collections using the DEFAULT_QUANTIZATION environment variable. This variable is not set by default, meaning no quantization is applied unless you explicitly configure it. When set (e.g., to 8-bit RQ quantization), all newly created collections will use that quantization setting. Note that once set on a collection, quantization can't be disabled. Default quantization won't be applied to a collection if the index type isn't supported (for example PQ and SQ aren't supported for the flat index).
Multi-vector encoding
Aside from quantization, Weaviate also offers encodings for multi-vector embeddings: