skills.rest
SethyPagna
SethyPagnaCOMMUNITY
Explore all skills by this author →
GitHub

chroma

Store embeddings and metadata in Chroma collections for semantic search.

Updated May 14, 2026
Search Tags:#semantic search#embeddings#rag#vector database#chroma#metadata filtering
One-click install
npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill chroma-sethypagna
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/SethyPagna/Secretary-Jarvis/tree/main/src/capabilities/optional-skills/mlops/chroma
Command: npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill chroma-sethypagna

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Chroma removes the complexity of storing embeddings, organizing metadata, and retrieving the most relevant content for AI applications. It gives you a simple local-first way to build semantic search and retrieval workflows without needing a heavy database stack.

Core Features & Use Cases

  • Vector storage and retrieval: Save embeddings with document metadata and query them efficiently.
  • Semantic search and RAG: Power retrieval-augmented generation, document lookup, and knowledge base search.
  • Filtering and persistence: Use metadata filters, persistent disk storage, and server mode for notebook, app, and production workflows.

Quick Start

Use the chroma skill to create a persistent collection, add your documents with metadata, and run a filtered similarity search for the query I provide.

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 semantic search?▼

To store embeddings for semantic search, you create a Chroma collection, add your documents alongside their metadata, and use persistent disk storage to manage retrieval workflows efficiently.

What is the best way to set up retrieval-augmented generation locally?▼

Retrieval-augmented generation can be set up locally by creating a persistent Chroma collection, adding your document base, and querying it to retrieve relevant content for your AI applications.

Can I use metadata filtering to narrow down vector database queries?▼

Yes, metadata filtering allows you to narrow down vector database queries by applying specific metadata conditions alongside similarity searches to retrieve highly targeted documents.

Does Chroma support both notebook prototyping and production vector database workflows?▼

Chroma supports both notebook prototyping and production workflows by offering persistent disk storage for local development and server mode for scaling AI content retrieval applications.

Why use a local-first vector database instead of a heavy database stack for document lookup?▼

A local-first vector database removes the complexity of organizing embeddings and retrieving content, providing a simple way to build semantic search and document lookup without heavy infrastructure.

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
seb1nseb1n
147

context-ranking

Rank retrieved context chunks by relevance, diversity, and utility for RAG systems.

Community
Advanced
zepdbzepdb
43

zeppelin

Index and search text with Zeppelin vector store and BM25 full-text indexing.

Official
Advanced
JKhyroJKhyro

chroma

Create Chroma vector collections for document retrieval and semantic search with embeddings and metadata filtering.

Community
Intermediate