skills.rest
kaminocorp
kaminocorpOFFICIAL
Explore all skills by this author →
Website𝕏@kaminocorpoGitHub

chroma

Store embeddings and query documents with vector similarity and metadata filtering in Chroma.

1|Updated Mar 12, 2026
Search Tags:#semantic search#embeddings#langchain#rag#vector database#chroma#metadata filtering
One-click install
npx skills add https://github.com/kaminocorp/hermes-alpha-hunter --skill chroma-kaminocorp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chroma
Source: https://github.com/kaminocorp/hermes-alpha-hunter/tree/main/skills/mlops/vector-databases/chroma
Command: npx skills add https://github.com/kaminocorp/hermes-alpha-hunter --skill chroma-kaminocorp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Building RAG and semantic search applications requires a database that can store embeddings alongside metadata and retrieve relevant documents quickly, without the overhead of managed cloud services. ## 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 filters using operators like $and, $or, $gt, and $in to narrow results. - Framework Integration: Works with LangChain and LlamaIndex for retrieval pipelines, and supports OpenAI, HuggingFace, and custom embedding functions. - Use Case: Prototype a RAG chatbot locally by persisting document chunks to a Chroma collection, then querying it as a retriever inside a LangChain chain. ## Quick Start Install chromadb with pip and ask the agent to create a persistent Chroma collection, add your documents with metadata, and run a filtered similarity query.

Frequently Asked Questions about chroma

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

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

Install chromadb, create a client and collection, then call collection.add with documents, metadatas, and ids. Query with collection.query passing query_texts and n_results to get the most similar documents with distances.

Chroma vs Pinecone vs FAISS for vector search?▼

Chroma is open-source and runs locally with metadata filtering, suiting development and self-hosted projects. Pinecone is a managed auto-scaling cloud service, while FAISS provides pure similarity search without metadata storage.

Does Chroma support metadata filtering in queries?▼

Yes, Chroma supports metadata filtering via the where parameter with operators like $gt, $gte, $lt, $lte, $ne, $in, and logical $and/$or combinations. Filters can be combined with vector similarity queries in a single call.

Can I use Chroma with LangChain or LlamaIndex?▼

Yes, Chroma integrates with LangChain via langchain_chroma.Chroma as a vector store and retriever, and with LlamaIndex via ChromaVectorStore. Both support persistent directories so indexes survive restarts.

How do I persist Chroma data between sessions?▼

Use chromadb.PersistentClient with a path argument instead of the default in-memory client. Data is written to disk automatically and can be reloaded by connecting to the same path later.

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

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

Related Skills

Explore More Software Engineering Skills→
daniel-dihardjadaniel-dihardja

langchain-rag

Orchestrate document loading, splitting, embedding, vector storage, and answer generation for RAG pipelines.

Community
Advanced
JhabbigJhabbig

rag-implementation

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

Community
Advanced
lebsrallebsral
11

ai-monitoring

Monitor AI model performance, drift, and cost in production.

Community
Advanced
ldzhhxxldzhhxx
1

faiss

Provides efficient nearest-neighbor search and vector indexing for ML workflows.

Community
Advanced