skills.rest
eddielueng
eddieluengCOMMUNITY
Explore all skills by this author →
GitHub

chroma

Indexes document vectors with metadata for semantic similarity search and retrieval.

1|Updated Apr 14, 2026
Search Tags:#semantic search#embeddings#rag#vector database#self-hosted#document retrieval#metadata filtering
One-click install
npx skills add https://github.com/eddielueng/hermes-agent-zh --skill chroma-eddielueng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/optional-skills/mlops/chroma
Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill chroma-eddielueng

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Chroma helps you turn your documents into searchable embeddings so you can quickly find relevant context using semantic meaning instead of exact keywords.

Core Features & Use Cases

  • Vector storage & similarity search: Store embeddings and retrieve the most similar documents for a query.
  • Metadata filtering: Filter retrieval results by document attributes (e.g., source, category, tags, numeric ranges).
  • Persistence & scalability: Save data to disk for reloads and progress from local notebooks to production usage.

Use case example: You maintain a self-hosted knowledge base of past tickets and notes; use Chroma to retrieve the most relevant entries for a new question, then pass those results to your LLM for grounded answers (RAG).

Quick Start

Use Chroma to store embeddings and retrieve top matches by asking for semantic search over your documents in a local or self-hosted setup.

Frequently Asked Questions about chroma

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

FAQPage Schema
How do I build a self-hosted vector database for semantic search?▼

You build a self-hosted vector database by indexing documents as embeddings with attached metadata, enabling similarity search for semantic retrieval. This Skill provides local Chroma-compatible storage for RAG and knowledge-base scenarios.

Can I filter semantic search results by document metadata?▼

Yes, metadata filtering is fully supported for semantic search results. You can filter retrieved documents using where-based filters on attributes like source, category, tags, or numeric ranges during collection queries.

Does this vector database support persistence across restarts for production workflows?▼

Yes, the vector database supports persistence across restarts for production workflows. You can save indexed embeddings and metadata to disk, allowing you to reload collections and progress from local notebooks to production usage.

Do I need sentence-transformers to store embeddings with Chroma?▼

You need sentence-transformers or OpenAI-compatible embedding functions to generate vectors for Chroma. The Skill requires these dependencies to convert documents into searchable embeddings for the local store.

What is the best way to retrieve past tickets for a RAG application?▼

The best way to retrieve past tickets for a RAG application is using a self-hosted embedding store. Index tickets as vectors with metadata, query for similar entries, and pass filtered results to your LLM for grounded answers.

Related Skills

Explore More Data & Analytics Skills→
an8079an8079
4

vector-search

Implement vector search with FAISS, Milvus, Qdrant, and Weaviate databases.

Community
Advanced
sgcarstrendssgcarstrends
21

schema-design

Design and modify Drizzle ORM schemas with relationships, constraints, and indexes.

Official
Advanced
Nuwanda04Nuwanda04

senior-prompt-engineer

Analyze prompts, evaluate RAG systems, and design agentic workflows.

Community
Advanced
discountedcookiediscountedcookie

postgres-vectors

Store 384-dimensional embeddings in Postgres and query cosine similarity with pgvector.

Community
Advanced