chroma

Store and query embeddings with metadata in a local vector database.

Updated Aug 23, 2026

Search Tags:#embeddings #rag #metadata #open-source #semantic-search #vector-database #chromadb

Ready to run

npx skills add https://github.com/travelinman1013/leroys-agent --skill chroma-travelinman1013

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/travelinman1013/leroys-agent/tree/main/optional-skills/mlops/chroma
Command: npx skills add https://github.com/travelinman1013/leroys-agent --skill chroma-travelinman1013

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chromadb, sentence-transformers, and includes references (resource) components.

What problem does it solve?

Organizations building AI apps need a local, scalable way to store and query embeddings and associated metadata for memory and retrieval tasks.

Core Features & Use Cases

Local vector store for embeddings with metadata, enabling offline development and production-scale deployments.
Unified API for storing embeddings, running similarity search, and filtering by metadata.
Suitable for RAG pipelines, semantic search, and document retrieval from notebooks to production.

Quick Start

Install chromadb, create a collection, add documents, and run a query to verify the setup.

Frequently Asked Questions about chroma

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

FAQPage Schema

How do I store and query embeddings with metadata for a RAG pipeline?▼

Store and query embeddings with metadata for retrieval-augmented generation using a local, self-hosted vector database. A unified API handles semantic similarity search and metadata filtering for production-scale AI memory.

What is the best way to run a local vector database for semantic search?▼

Run a local vector database to enable offline development and production-scale semantic search. It provides a simple API to store embeddings and execute similarity queries without relying on external managed services.

Can I use sentence-transformers to generate embeddings for chromadb?▼

Yes, sentence-transformers is a required dependency for generating embeddings. The database stores these vector representations alongside associated metadata to support retrieval queries and similarity matching.

Does this self-hosted embedding store support metadata filtering for AI applications?▼

The self-hosted embedding store supports metadata filtering for AI applications. You can store document embeddings with contextual metadata and filter similarity search results based on those specific metadata attributes.

When do I need a local vector database for document retrieval?▼

You need a local vector database for document retrieval when building AI apps that require memory and self-hosted data control. It scales from notebook prototyping to production deployments for semantic search tasks.