chroma
About
Chroma is an open-source embedding database for AI applications that provides vector search, metadata filtering, and a simple API. It's ideal for building RAG applications and semantic search, scaling from local development to production. Use it when you need a self-hosted vector database for document retrieval and embedding storage.
Quick Install
Claude Code
Recommendednpx skills add davila7/claude-code-templates -a claude-code/plugin add https://github.com/davila7/claude-code-templatesgit clone https://github.com/davila7/claude-code-templates.git ~/.claude/skills/chromaCopy and paste this command in Claude Code to install this skill
GitHub Repository
Related Skills
qdrant-vector-search
MetaThe qdrant-vector-search skill provides a high-performance vector similarity search engine for building production RAG systems. It enables fast nearest neighbor search, hybrid search with filtering, and scalable vector storage powered by Rust. Use it when you need low-latency semantic search with horizontal scaling capabilities and full data control.
llamaindex
MetaLlamaIndex is a data framework for building RAG applications, specializing in ingesting documents from numerous sources and indexing them for querying. It provides key components like vector indices and query engines to enable document Q&A, chatbots, and knowledge retrieval over private data. Use it when you need to connect LLMs to your own data for data-centric applications.
dspy
MetaDSPy is a framework for building complex AI systems like RAG pipelines and agents using declarative programming. It automatically optimizes prompts and LM calls based on your data, moving beyond manual prompt engineering. Use it to create modular, maintainable, and systematically improved AI applications.
pinecone
DevelopmentPinecone is a fully managed vector database for production AI applications, offering auto-scaling, low-latency hybrid search, and metadata filtering. It's ideal for developers building production RAG systems, recommendation engines, or semantic search at scale without managing infrastructure. Use it when you need a serverless, managed service with consistent sub-100ms performance.
