chroma

Store embeddings with metadata in a local vector database for semantic search.

Updated Apr 16, 2026

Search Tags:#rag #embedding #semantic-search #local-development #vector-database #self-hosted #document-retrieval

Ready to run

npx skills add https://github.com/jacardl/New-Radar --skill chroma-jacardl

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/jacardl/New-Radar/tree/main/backend/frameworks/hermes-agent/optional-skills/mlops/chroma
Command: npx skills add https://github.com/jacardl/New-Radar --skill chroma-jacardl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Open-source embedding database designed to store and query text embeddings with metadata, enabling fast semantic search and retrieval for AI applications.

Core Features & Use Cases

Vector storage with metadata filtering for semantic search, RAG workflows, and document retrieval.
Local development and self-hosted deployment with persistence and scalable architecture.
Simple 4-function API for easy integration into notebooks and production pipelines.

Quick Start

Set up a local chroma client, create a collection, add documents with embeddings, and run a similarity search.

Frequently Asked Questions about chroma

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I store embeddings with metadata for semantic search in AI applications?▼

To store embeddings with metadata for semantic search, you can use a local, open-source vector database. It enables fast document retrieval and RAG workflows by allowing you to store text embeddings alongside metadata and run similarity queries with a simple four-function API.

Can I use a local vector database for RAG development and self-hosted production?▼

Yes, you can use a local vector database for RAG development and self-hosted production. It supports local persistence and metadata filtering, allowing you to scale your document retrieval pipelines seamlessly from notebook environments to self-hosted deployments.

What is the best way to build a document retrieval pipeline using an open-source embedding database?▼

The best way to build a document retrieval pipeline is using an open-source embedding database with a simple four-function API. You set up a local client, create a collection, add documents with embeddings, and execute fast similarity searches to retrieve relevant text.

Does this local vector store support metadata filtering for semantic search?▼

Yes, this local vector store supports metadata filtering for semantic search. It allows you to store embeddings with associated metadata, enabling precise document retrieval and targeted similarity queries within your RAG workflows and AI applications.