chroma

Store and search embedding data with metadata-filtered semantic retrieval.

3|Updated Apr 4, 2026

Search Tags:#semantic search #embeddings #rag #vector search #chroma #document retrieval #metadata filtering

Ready to run

npx skills add https://github.com/twjarviszyra-web/hermes-unbound --skill chroma-twjarviszyra-web

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/twjarviszyra-web/hermes-unbound/tree/main/optional-skills/mlops/chroma
Command: npx skills add https://github.com/twjarviszyra-web/hermes-unbound --skill chroma-twjarviszyra-web

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Chroma removes the friction of building AI retrieval systems by giving you a simple way to store embeddings, attach metadata, and find the most relevant content fast.

Core Features & Use Cases

Semantic Search: Retrieve documents by meaning instead of exact keyword matches.
RAG Backends: Support retrieval-augmented generation workflows with metadata filtering and persistent storage.
Framework Integration: Work with LangChain and LlamaIndex for document indexing, querying, and retrieval.
Use Case: If you need to search a growing knowledge base, Chroma lets you persist vectors locally, filter by source or category, and query the most relevant passages in one workflow.

Quick Start

Use the chroma skill to store embeddings for your documents and retrieve the most relevant matches with metadata filters.

Frequently Asked Questions about chroma

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

FAQPage Schema

How do I perform semantic search over my document embeddings?▼

Semantic search over document embeddings works by storing your vector data and querying for the most relevant content by meaning rather than exact keywords. Chroma handles this retrieval process along with metadata filtering.

How do I set up a persistent local database for RAG pipelines?▼

To set up a persistent local database for RAG pipelines, you store embeddings and attach metadata to your documents. Chroma allows you to persist vectors locally so your knowledge base remains available across sessions.

Can I use Chroma with LangChain and LlamaIndex for document retrieval?▼

Yes, Chroma works with LangChain and LlamaIndex for document indexing, querying, and retrieval. These framework integrations allow you to plug semantic search directly into your retrieval-augmented generation workflows.

How do I filter vector search results by metadata?▼

Filtering vector search results by metadata involves attaching descriptive tags to your stored embeddings and applying filter conditions during your similarity query. Chroma supports metadata-filtered lookup to find specific passages.

What is the best way to scale semantic search for AI applications?▼

To scale semantic search for AI applications, you can transition from local persistent storage to an optional server mode. Chroma supports this scalable configuration to handle growing knowledge bases and increased retrieval demands.