skills.rest
azaanaliraza
azaanalirazaCOMMUNITY
Explore all skills by this author →
GitHub

chroma

Store embeddings and metadata in Chroma for vector search and RAG applications.

Updated Apr 18, 2026
Search Tags:#semantic search#embeddings#langchain#rag#vector database#chroma#metadata filtering
One-click install
npx skills add https://github.com/azaanaliraza/operarius --skill chroma-azaanaliraza
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/azaanaliraza/operarius/tree/main/src-tauri/bin/hermes/optional-skills/mlops/chroma
Command: npx skills add https://github.com/azaanaliraza/operarius --skill chroma-azaanaliraza

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Building AI applications with memory requires storing and searching document embeddings, but setting up a vector database from scratch is complex. This Skill provides ready-to-use patterns for Chroma, the open-source embedding database, covering collection management, similarity search, and metadata filtering. ## Core Features & Use Cases - Vector Storage & Search: Create collections, add documents with embeddings and metadata, and run similarity queries with a simple 4-function API. - Metadata Filtering: Combine semantic search with structured filters using comparison and logical operators to narrow results. - Framework Integration: Connect Chroma to LangChain and LlamaIndex for retrieval-augmented generation pipelines, with persistent local storage or client-server mode. - Use Case: Build a RAG chatbot over your documentation by embedding markdown files into a persistent Chroma collection, then querying it with metadata filters to retrieve the most relevant sections for each user question. ## Quick Start Use the chroma skill to create a persistent collection, add my documents with metadata, and run a filtered similarity search.

Frequently Asked Questions about chroma

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

FAQPage Schema
How do I store and search embeddings with Chroma in Python?▼

Install chromadb, create a client and collection, then use collection.add() with documents, metadatas, and ids. Run collection.query() with query_texts and n_results to retrieve the most similar documents by embedding distance.

Chroma vs Pinecone vs FAISS for vector search?▼

Chroma is open-source and self-hosted with metadata filtering, ideal for local development and RAG prototypes. Pinecone is a managed cloud service with auto-scaling, while FAISS offers pure similarity search without metadata storage.

Does Chroma support persistent storage across restarts?▼

Yes, use chromadb.PersistentClient with a path argument to save data to disk. Data persists automatically and can be reloaded later by connecting to the same directory path.

Can I use Chroma with LangChain or LlamaIndex?▼

Yes, Chroma integrates with both frameworks. Use langchain_chroma.Chroma for LangChain vector stores and retrievers, or ChromaVectorStore from llama_index for building query engines over your collections.

How do I filter Chroma query results by metadata?▼

Pass a where clause to collection.query() with operators like $gt, $lte, $in, or combine conditions using $and and $or. This narrows the search space before similarity ranking is applied.

When should I not use Chroma for a vector database?▼

Avoid Chroma when you need managed auto-scaling cloud infrastructure (use Pinecone), pure high-speed similarity search without metadata (use FAISS), or Rust-based high-performance production clusters (use Qdrant).

Related Skills

Explore More Software Engineering Skills→
HosungYouHosungYou
5

i3

Download PDFs, extract text, chunk documents, and create a local ChromaDB vector database.

Community
Advanced
JhabbigJhabbig

rag-implementation

Build retrieval-augmented generation systems that ground LLM answers in external knowledge.

Community
Advanced
githubgithub
38.5k

qdrant-search-strategies

Guides selection of Qdrant search strategies to improve retrieval relevance and diversity.

Official
Intermediate
math-incmath-inc
1.2k

pinecone

Create serverless Pinecone indexes for similarity search with metadata filtering.

Official
Intermediate