Semantic search (all vector stores)
Search a vector store using natural language. One endpoint serves every supported store — the {store} path segment selects it. Generates an embedding from the query and returns the most similar document chunks. Connection and embedding secrets are always resolved server-side from the server’s configuration; any client-supplied secret names are ignored. Request fields vary slightly per store — qdrant, milvus, and chroma name their container with collection, weaviate with className, pgvector with table (plus an optional schema).
Authorizations
Optional API key for authentication (enabled via application.yaml)
Path Parameters
Vector store to search
qdrant, weaviate, milvus, chroma, pgvector Body
Natural language search query
Collection name (qdrant, milvus, and chroma only)
Weaviate class name, PascalCase (weaviate only)
PostgreSQL table name (pgvector only)
PostgreSQL schema (pgvector only)
Number of results to return
