# postgresml/korvus

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

Repository: https://github.com/postgresml/korvus
Canonical: https://ross.abutalabs.com/products/korvus
Homepage: https://postgresml.org
Language: Rust
License: MIT
License Family: permissive
Topics: ai, embeddings, javascript, llm, ml, python, rag, search, sql
Last push: 2025-01-31T00:00:07+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 4, release rhythm 35, longevity 57
- inputs: {"age_days": 800, "days_push": 580, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1472, forks 48 (observed 2026-08-28T04:04:49.386380+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: rag, search-engine, vector-database, llm-inference, sdk, database-driver
- domain: large-language-models, databases, machine-learning, developer-tools
- platform: python, rust, self-hosted, cloud
- tags: postgres, pgvector, embeddings, single-query-rag, multi-language-sdk, sql, retrieval-augmented-generation, search, nodejs

## Member repositories
- postgresml/korvus (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:49.386380+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:42.897696+00:00, confidence not recorded.
  - readme: https://github.com/postgresml/korvus (fetched 2026-08-28T04:04:49.386380+00:00, sha 0769bf193de6)
  - homepage: https://postgresml.org (fetched 2026-08-29T11:42:33.442024+00:00, sha 9ee6d24b48e2)
  - site_page: https://postgresml.org/docs/cloud/overview (fetched 2026-08-29T11:42:33.451592+00:00, sha 3967bf4e27ba)
  - site_page: https://postgresml.org/docs/cloud/enterprise/vpc (fetched 2026-08-29T11:42:33.453714+00:00, sha 8ed00db20956)
  - site_page: https://postgresml.org/docs/open-source/pgml/guides/llms (fetched 2026-08-29T11:42:33.455470+00:00, sha 0dd72baeee4b)
  - site_page: https://postgresml.org/docs/open-source/pgml/guides/embeddings (fetched 2026-08-29T11:42:33.457083+00:00, sha a812cb201bd6)
  - site_page: https://postgresml.org/docs/open-source/pgml/guides/vector-database (fetched 2026-08-29T11:42:33.458993+00:00, sha d13d6fff9649)
  - site_page: https://postgresml.org/docs/open-source/pgml/guides/supervised-learning (fetched 2026-08-29T11:42:33.460769+00:00, sha fe335e49b8e8)
  - site_page: https://postgresml.org/docs/open-source/pgml/guides/improve-search-results-with-machine-learning (fetched 2026-08-29T11:42:33.462523+00:00, sha d5bb22bbea47)
  - registry_crates: https://crates.io/api/v1/crates/korvus (fetched 2026-08-29T11:42:33.466760+00:00, sha adf2c773db37)
- Data as of 2026-08-30T08:39:29.467469+00:00.