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

Chromem Go

Chromem Go is an embeddable vector database library for Go applications, providing collections for documents and embeddings and nearest-neighbor queries through a Chroma-like interface. It supports in-memory storage with optional persistence and can add retrieval to applications without a separate database service.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Chromem Go — 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 it when a Go application needs embedded vector storage and similarity retrieval, particularly for common-scale RAG or semantic-search workflows that do not call for a separate database service.

Who it is for

  • Go developers building RAG or question-answering features into an application.
  • Teams adding semantic text or code search, recommendations, classification or clustering to Go software.

Documented uses

  • Store documents and their embeddings in an application-embedded database.
  • Retrieve content related to a user question for use as context in an LLM workflow.
  • Prototype a local in-memory vector index, with persistence available as an option.
Before you choose

Requirements & limits

  • It is a standalone embedded database, not a library for connecting to Chroma.
  • The README presents in-memory operation and optional persistence.
  • The documented default embedding setup uses OpenAI and needs OPENAI_API_KEY; Ollama is also identified as an option.
  • The project states that its focus is common use cases rather than scale to millions of documents or a broad feature set.
  • The README labels the project beta and warns of possible breaking changes before 1.0.0.

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 minimal in-memory collection and query

Follow the README's minimal example to add documents to an in-memory database and retrieve a similar result.

Before you start

  • A Go application using the chromem-go package.
  • An embedding function. The example's default uses OpenAI and requires the OPENAI_API_KEY environment variable; the README also names Ollama as an alternative.

Steps

  1. Create a context and initialize the database with chromem.NewDB().

  2. Create a collection, passing the documented embedding configuration.

  3. Add documents with IDs and content to the collection.

  4. Query the collection with a question and a requested result count.

Expected outcome

The example returns a matching document with its ID, similarity score and content.

Guide limitations

  • This describes the README example, not a separately performed execution test.
  • The project is labeled beta and warns of possible breaking changes before version 1.0.0.
Documentation 1 ↗
Evidence and transparency

Sources & review

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