skills.rest
JKhyro
JKhyroCOMMUNITY
Explore all skills by this author →
GitHub

chroma

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

Updated Apr 2, 2026
Search Tags:#semantic search#embeddings#rag#vector database#chroma#document retrieval#metadata filtering
One-click install
npx skills add https://github.com/JKhyro/HERMES-AGENT --skill chroma-jkhyro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/JKhyro/HERMES-AGENT/tree/main/optional-skills/mlops/chroma
Command: npx skills add https://github.com/JKhyro/HERMES-AGENT --skill chroma-jkhyro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It helps you store embeddings and metadata in Chroma so you can retrieve the right documents quickly instead of searching manually across unstructured content.

Core Features & Use Cases

  • Vector storage: Add documents, embeddings, and metadata to local or server-backed Chroma collections.
  • Semantic retrieval: Run similarity search and metadata filters for RAG pipelines, document lookup, and knowledge bases.
  • Integrations: Connect Chroma with LangChain or LlamaIndex to power retrieval workflows in apps and notebooks.

Quick Start

Ask the skill to create a Chroma collection for your documents and show how to add, query, and persist embeddings.

Frequently Asked Questions about chroma

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

FAQPage Schema
How do I build a vector database for semantic search and document retrieval?▼

To build a vector database for semantic search, you create Chroma collections to store document embeddings and metadata. This allows you to retrieve relevant documents quickly through similarity search instead of manual scanning across unstructured content.

Can I use metadata filtering with Chroma collections for RAG workflows?▼

Yes, metadata filtering is supported with Chroma collections for RAG workflows. You can attach metadata to your stored embeddings and run similarity searches combined with specific metadata filters to narrow down document retrieval results accurately.

Does Chroma work with LangChain and LlamaIndex for retrieval workflows?▼

Chroma works with LangChain and LlamaIndex to power retrieval workflows in apps and notebooks. These integrations allow you to connect your vector collections directly into larger retrieval augmented generation pipelines for document lookup and knowledge bases.

What is the best way to persist local embeddings in a Chroma database?▼

The best way to persist local embeddings in a Chroma database is by configuring persistent local storage during collection creation. This ensures your vector collections and associated metadata are saved to disk, maintaining your document retrieval data between sessions.

How do I add and query documents in a Chroma vector collection?▼

To add and query documents in a Chroma vector collection, you configure your embedding settings, add your documents and metadata to the collection, and then execute a similarity search. This process supports notebook prototyping, local databases, and server-based deployments.

Related Skills

Explore More Software Engineering Skills→
markus41markus41
1

vectordb

Manage vector embeddings for semantic search across Pinecone, Weaviate, Chroma, and pgvector.

Community
Intermediate
llama-farmllama-farm
835

rag-skills

Audit and optimize RAG pipelines with LlamaIndex, ChromaDB, and Celery best practices.

Official
Basic
jason660519jason660519

chroma

Manage vector-embedding storage with Chroma for RAG workflows and semantic search.

Community
Advanced
DrLuggelsDrLuggels
3

similarity-search-patterns

Provide patterns for similarity search with vector databases like Pinecone and Qdrant.

Community
Advanced