OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Korvus

Korvus is an open-source search SDK that builds RAG pipelines on PostgreSQL, combining retrieval and generation stages through a database-centered interface. Its documented stages include embedding generation, vector search, reranking, summarization and text generation. SDK bindings are listed for Python, JavaScript, Rust and C.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Korvus — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Consider Korvus when you want to build a PostgreSQL-centered RAG workflow and can provide a database with the required pgml and pgvector extensions.

Who it is for

  • Developers building RAG features for applications backed by PostgreSQL.
  • Teams seeking a language-specific SDK interface for search and generation workflows.

Documented uses

  • Configure a collection and search pipeline.
  • Insert documents for retrieval.
  • Run vector search and use retrieved context in a RAG request.
Before you choose

Requirements & limits

The repository identifies Korvus as open source under the MIT license.

  • A PostgreSQL database with pgml and pgvector is a prerequisite.
  • The Python quick start uses a database URL environment variable and a configured collection pipeline.
  • The repository lists bindings for four languages, with C builds directed to the project documentation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a Python RAG collection and query

Use the documented Python quick-start stages to configure a Korvus pipeline, add sample documents and request a RAG result.

Before you start

  • A PostgreSQL database with pgml and pgvector installed.
  • Python and the Korvus package.
  • A database connection string set as KORVUS_DATABASE_URL.

Steps

  1. Install Korvus with the command below.

    Documented command
    pip install korvus

  2. Set KORVUS_DATABASE_URL to the database connection string.

  3. Create a Collection and Pipeline, then add the pipeline to the collection.

  4. Upsert documents into the collection.

  5. Call the collection's RAG method with a vector-search context and chat configuration.

Expected outcome

A Python workflow that submits a RAG query against documents in a Korvus collection.

Guide limitations

  • The documented example requires pgml and pgvector in the database.
  • The example uses a specific semantic-search model and chat model; it does not establish suitability for other model or deployment configurations.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
KorvusConfigure a collection and search pipeline.ServerThe repository identifies Korvus as open source under the MIT license.
LangsearchCrawl website or local data for a knowledge base.CLI, Self-hosted, Server
Hybrid Search RagCombine document retrieval and language-model generation in a configurable workflow.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
postgresml/korvus · Official homepage title · retained in its source language
How we review sourcesSuggest a correction