v0.5.0 — Vector Search

What's New

Vector Search Support

The SDK now provides typed models and convenience methods for the Flux vector search API.

4 search modes:

• vector_search() — semantic search with auto-generated embeddings
• vector_field_search() — search with custom pre-computed embedding vectors
• hybrid_search() — blended text + vector search with configurable weights
• boosted_search() — keyword search boosted by vector similarity

Typed models with validation:

• SearchMode, VectorSearch, VectorFieldSearch, VectorBoostConfig, HybridConfig, SearchRequest
• Cross-field validation catches invalid configurations before the API call
• SearchRequest forwards extra fields (where, sort) via extra="allow"

All methods available on both FluxClient and AsyncFluxClient.

Other Changes

• Fixed examples/flux_client.py search body to use correct find_text/results keys

Links

• Vector Search Guide
• Changelog