KorvusSearch SDK to unify RAG pipeline in a single database query

Korvus: Unified RAG Pipeline in a Single Database Query

Korvus is an open-source search SDK that streamlines the entire Retrieval-Augmented Generation (RAG) pipeline into a single database query. Built on PostgreSQL with language bindings for Python, JavaScript, Rust, and C, Korvus offers high-performance, customizable search capabilities with minimal infrastructure overhead.

Key Features

• Unified Pipeline: Combine embedding generation, vector search, reranking, and text generation in one query
• Postgres-Native RAG: Leverage Postgres for complex RAG operations without external services
• Single Query Efficiency: Execute the entire RAG pipeline in a single SQL query
• Scalability: Inherit Postgres' excellent scalability and performance characteristics
• Multi-Language Support: Use Korvus with Python, JavaScript, Rust, and C
• Open Source: Improve developer experience with locally-runnable open-source software and models

Use Cases

• Semantic search applications
• Question-answering systems
• Content recommendation engines
• Knowledge management systems
• AI-powered chatbots and virtual assistants

Pricing

Korvus is open-source and free to use. For enterprise support and consulting services, contact PostgresML directly.

Teams

Korvus is maintained by the PostgresML team, with contributions from the open-source community. Join their Discord or follow them on Twitter to connect with other users and contributors.

View documentation Get started with Korvus