postgresml/korvus

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1472 stars · 48 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Korvus is an open-source search SDK that unifies the entire RAG pipeline—embedding generation, vector search, reranking, summarization, and LLM inference—into a single Postgres query. It provides client bindings for Python, JavaScript, Rust, and C on top of the PostgresML Postgres extension.

Use cases

• build a rag pipeline in a single sql query
• semantic search over documents in postgres
• generate embeddings inside the database
• replace separate vector database and embedding service
• add llm inference to a postgres-backed app
• build a search engine with reranking and summarization

When to choose

• you already use Postgres and want RAG without extra infrastructure
• you want to minimize latency by avoiding external API calls
• you need SDKs for Python, JavaScript, or Rust
• you prefer keeping data in one database for security and compliance

When to avoid

• you don't use Postgres or can't run the PostgresML extension
• you need a fully managed service without self-hosting or cloud commitment
• your workload requires a specialized vector database beyond pgvector

Facets

library · maturity active

rag search-engine vector-database llm-inference sdk database-driver large-language-models databases machine-learning developer-tools python rust self-hosted cloud postgres pgvector embeddings single-query-rag multi-language-sdk sql retrieval-augmented-generation search nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="postgresml/korvus")