chroma

Store embeddings and metadata, then run vector and full-text searches.

4|Updated Apr 19, 2026

Search Tags:#semantic search #vector database #document retrieval #metadata filtering #embedding database

Ready to run

npx skills add https://github.com/ragnarokhaa/hermes --skill chroma-ragnarokhaa

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/ragnarokhaa/hermes/tree/main/hermes-cerul-tech-news-package/hermes-cerul-tech-news-package/hermes-agent/optional-skills/mlops/chroma
Command: npx skills add https://github.com/ragnarokhaa/hermes --skill chroma-ragnarokhaa

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manages and searches for embeddings and metadata in documents, streamlining document retrieval and semantic analysis.

Core Features & Use Cases

Embedding Database: Store and manage embeddings and metadata for document retrieval.
Vector and Full-Text Search: Perform both vector and full-text searches on embeddings.
Metadata Filtering: Filter search results by metadata attributes.
Use Cases: Ideal for semantic search, RAG applications, and document retrieval in local development and open-source projects.

Quick Start

Start by creating a Chroma collection and adding documents, then run a query to search for documents based on your criteria.

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 on my documents?▼

Semantic search is performed by employing an open-source embedding database to store document embeddings and metadata, facilitating vector and full-text searches. You create a collection, add documents, and query based on your criteria.

Can I filter vector search results by metadata attributes?▼

Yes, metadata filtering allows you to filter vector and full-text search results by specific metadata attributes. This streamlines document retrieval and semantic analysis within your stored collections.

Does Chroma work with sentence-transformers for RAG applications?▼

Yes, the system relies on sentence-transformers and chromadb dependencies to manage embeddings. It is designed for use in Retrieval-Augmented Generation (RAG) applications and local development.

What is the best way to store embeddings and metadata for local development?▼

The best way to store embeddings and metadata for local development is using an open-source embedding database. This approach manages and searches embeddings efficiently, streamlining document retrieval.

Why use an embedding database for document retrieval?▼

An embedding database is used for document retrieval to manage and search embeddings and metadata effectively. It enables both vector and full-text searches, streamlining semantic analysis tasks.