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

Swarndb

SwarnDB is a Rust database engine for storing and retrieving vector embeddings and graph data in one system. A vector and its graph node share an identity; collections can use vector search alone or add an opt-in typed graph for relationship-aware retrieval. It exposes documented REST and gRPC interfaces and has a Python SDK.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Swarndb — 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 SwarnDB when building a retrieval backend that needs vector search and may also need graph relationships in the same store. A vector-only collection supports nearest-neighbor use; hybrid mode adds explicit typed edges and graph-aware query operations.

Who it is for

  • Developers building retrieval-augmented generation or knowledge-graph systems.
  • Teams that need embedding similarity and explicit graph relationships in a shared data layer.
  • Engineers integrating vector and graph retrieval through REST, gRPC or the Python SDK.

Documented uses

  • Store embeddings and search for nearest neighbors.
  • Represent explicit, typed relationships with confidence and provenance.
  • Combine vector similarity, graph traversal and vector ranking in a retrieval query.
  • Filter candidate items by attributes before ranking them by vector similarity.
  • Optionally propose graph entities and edges from text using an OpenAI-compatible model.
Before you choose

Requirements & limits

The repository documents Docker-based startup, a Python package, and REST and gRPC interfaces. Its configuration reference lists API keys as configurable; an empty key setting disables authentication.

  • Graph functionality is opt-in per collection; collections are vector-only by default.
  • Graph edges are explicit or extracted and are not inferred from embedding similarity.
  • Optional LLM extraction requires a user-provided OpenAI-compatible API key.
  • The README describes both REST and gRPC interfaces, plus a Python SDK and async client.

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

Start SwarnDB and connect with the Python SDK

Start the documented Docker service and install the Python client for a local connection.

Before you start

  • Docker
  • Python with pip

Steps

  1. Start the container with the command below.

    Documented command
    docker run -d -p 8080:8080 -p 50051:50051 sarthiai/swarndb

  2. Install the SDK with the command below.

    Documented command
    pip install swarndb

  3. Create a SwarnDBClient pointed at localhost on port 50051.

Expected outcome

The documented service is started with REST and gRPC ports mapped, and the Python client can be configured to connect over gRPC.

Guide limitations

  • This covers service startup and client connection setup, not creation of a collection or a search workflow.
  • The README points to the Docker guide for persistence and configuration.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

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
SwarndbStore embeddings and search for nearest neighbors.Self-hosted, ServerThe repository documents Docker-based startup, a Python package, and REST and gRPC interfaces. Its configuration reference lists API keys as configurable; an empty key setting disables authentication.
MettisIndex text documents through an HTTP endpoint.Linux, Self-hosted, Server
Evidence and transparency

Sources & review

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