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

Topk

TopK is a retrieval engine and API for storing and querying dense and sparse vectors, multi-vector embeddings, and metadata in collections. It supports vector, BM25 keyword and hybrid search, metadata filters, custom ranking and managed inference.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Topk — 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

Use TopK when an AI application needs a retrieval layer that can combine vector and keyword search, filter on metadata, or apply custom ranking to collection results.

Who it is for

  • Developers building retrieval-augmented generation (RAG) backends.
  • Teams creating document-search services that need multiple retrieval methods.
  • Developers integrating retrieval through Python, JavaScript/TypeScript, Rust, SQL or a CLI.

Documented uses

  • Store and query vector embeddings and metadata in collections.
  • Retrieve documents with vector, BM25 keyword or hybrid search.
  • Filter search results by metadata and apply custom ranking expressions.
  • Connect a PostgreSQL client through the SQL interface.
  • Use a coding-agent skill covering TopK schema design, chunking and hybrid queries.
Before you choose

Requirements & limits

  • The repository identifies Rust as the primary language and the project as MIT-licensed and open source.
  • Available integration routes include Python, JavaScript/TypeScript and Rust SDKs, SQL connectivity for PostgreSQL clients, and a CLI.
  • A repository-provided coding-agent skill covers schema design, chunking, hybrid queries and multi-tenancy; it is a development aid, distinct from the retrieval service.

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

Install the TopK skill for a coding agent

Add the TopK skill to a coding-agent environment so it can reference guidance on schema design, chunking, hybrid queries, and multi-tenancy.

Before you start

  • Claude Code, Cursor, Codex, or another coding agent
  • The npx command

Steps

  1. Run the command below.

    Documented command
    npx skills add topk-io/topk --skill topk

  2. Use the installed skill as coding guidance for TopK schema design, chunking, hybrid queries, and multi-tenancy.

Expected outcome

The TopK skill is installed for the coding agent to consult when writing TopK code.

Guide limitations

  • The instructions describe installing a coding-agent skill, not configuring a TopK service or executing retrieval queries.
  • The skill is described as covering common mistakes, but specific procedures for using it are not given.
Documentation 1 ↗
Evidence and transparency

Sources & review

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