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

Svdb

SVDB is an open-source Swift library for storing text and supplied embedding vectors in local collections and searching those collections with query embeddings.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Svdb — 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 SVDB when a Swift app needs collection-based search over text whose embeddings are generated separately, with the vector database kept local to the app.

Who it is for

  • Swift developers adding local semantic or nearest-match search to app content.
  • App builders who want an on-device retrieval component and can supply their own embeddings.

Documented uses

  • Add document text and its embedding to a named collection.
  • Search stored content using an embedding generated for a query.
  • Add a local vector retrieval component to a Swift app.
Before you choose

Requirements & limits

The repository is public and lists an MIT license. Installation instructions use Swift Package Manager.

  • The app must provide document and query embeddings; SVDB's examples use NaturalLanguage or a separate OpenAI Swift package.
  • The documented interface uses named collections and adds text with its embedding before searching.
  • The repository includes a demo directory for a Swift example.

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

Add a Swift Package Manager dependency

Include SVDB in a Swift project using Swift Package Manager.

Before you start

  • A Swift project using Xcode or a Package.swift manifest.
  • Xcode 11 is named in the repository instructions for the Xcode installation route.

Steps

  1. Add https://github.com/Dripfarm/SVDB.git as a package dependency in Xcode, or

  2. Add .package(url: "https://github.com/Dripfarm/SVDB.git", from: "1.0.0") to the dependencies in Package.swift.

Expected outcome

The project manifest or Xcode project includes SVDB as a package dependency.

Guide limitations

  • The documented steps cover dependency setup, not building or running an app.
Documentation 1 ↗
Source-based practical guide

Store text and search a collection

Use SVDB's documented collection workflow to store text with an embedding and query for similar results.

Before you start

  • SVDB included in a Swift project.
  • An embedding vector for each document and a query vector, generated separately; the README shows NaturalLanguage and an OpenAI package as examples.

Steps

  1. Obtain an embedding for the document text.

  2. Create or retrieve a collection with SVDB.shared.collection("animals").

  3. Add the document text and embedding with SVDB.shared.addDocument(text:embedding:).

  4. Obtain an embedding for the search query and pass it to animalCollection.search(query:).

Expected outcome

The collection search returns results for the supplied query embedding.

Guide limitations

  • The example leaves embedding generation to separate frameworks or packages.
Documentation 1 ↗
Evidence and transparency

Sources & review

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