skills.rest
Clay-HHK
Clay-HHKCOMMUNITY
Explore all skills by this author →
GitHub

chroma

Store embeddings and metadata for semantic and full-text retrieval.

2|Updated Apr 12, 2026
Search Tags:#embeddings#rag#retrieval#chroma#semantic-search#vector-database#metadata-filtering
One-click install
npx skills add https://github.com/Clay-HHK/claude-config --skill chroma-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/Clay-HHK/claude-config/tree/main/skills/AI-research-SKILLs/15-rag/chroma
Command: npx skills add https://github.com/Clay-HHK/claude-config --skill chroma-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Chroma provides an open-source, self-hosted vector database to store embeddings and metadata and enable fast, scalable semantic and full-text retrieval for RAG and document search workflows, removing reliance on managed vector services.

Core Features & Use Cases

  • Embedding storage and retrieval: Persist embeddings and associated metadata for similarity search and document retrieval.
  • Vector and full-text search: Combine nearest-neighbor search with filters and full-text capabilities for precise results.
  • Metadata filtering & logical queries: Narrow searches using exact matches, comparison and logical operators, and tag inclusion.
  • Persistence and server modes: Run in-process for notebooks or as a persistent server for multi-user deployments, with integrations for LangChain and LlamaIndex.
  • Use Case: Index product manuals or support articles locally, then power a RAG pipeline that returns context-aware answers filtered by source, category, or date.

Quick Start

Create a persistent Chroma client at ./chroma_db, index your documents with embeddings, and run a semantic query to fetch the top relevant passages.

Frequently Asked Questions about chroma

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

FAQPage Schema
How do I store embeddings and metadata for a self-hosted RAG pipeline?▼

You can store embeddings and metadata for a self-hosted RAG pipeline using a local vector database that persists data on disk. This enables efficient semantic retrieval over your documents without relying on managed cloud services.

Can I filter semantic search results using metadata tags and comparison operators?▼

Yes, semantic search results can be filtered using metadata tags. The system supports exact matches, comparison operators, and logical queries to narrow down nearest-neighbor searches for precise document retrieval.

Does this vector database work with LangChain and LlamaIndex integrations?▼

Yes, the vector database works with LangChain and LlamaIndex integrations. It supports both in-process notebook prototyping and persistent server modes for multi-user production deployments within these LLM toolkits.

What is the best way to run semantic search locally during notebook prototyping?▼

The best way to run semantic search locally during notebook prototyping is using an in-process client mode. This allows you to index documents, store embeddings, and test similarity queries directly within your development environment.

How do I combine full-text search with vector similarity for document retrieval?▼

You can combine full-text search with vector similarity for document retrieval by using a database that supports both capabilities. This allows you to run nearest-neighbor searches alongside full-text matching and metadata filtering.

When should I use a self-hosted vector database instead of a managed cloud service?▼

You should use a self-hosted vector database when you need to remove reliance on managed services for storing embeddings. It satisfies requirements for persistent local storage, batch ingestion, and self-hosted production deployments.

Related Skills

Explore More Software Engineering Skills→
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
OmidZamaniOmidZamani
120

dspy-rag-pipeline

Build and optimize RAG pipelines with ColBERTv2 in DSPy.

Community
Advanced
hochoa13hochoa13

qdrant-vector-search

Provides scalable vector similarity search and hybrid search with metadata filtering for RAG systems.

Community
Advanced
thisismynewfmail-uithisismynewfmail-ui

chroma

Store and query vector embeddings with metadata filtering for semantic retrieval.

Community
Intermediate