Reference · Glossary
Chroma
Last updated
A **lightweight, in-process vector database** — it runs inside your Python app (no separate server required), which makes it the fastest way to go from "I have embeddings" to "I can search them."
#When to use
Local prototypes, learning labs, and small single-machine RAG apps where you don't want to stand up external infrastructure.
#When not to
Multi-server production apps that need the index shared across many machines — reach for a managed store like Pinecone or a self-hosted cluster like Weaviate/Qdrant instead.
#Example
import chromadb
client = chromadb.Client()
collection = client.create_collection("docs")
collection.add(documents=["Refunds take 5-7 business days"], ids=["faq-1"])
results = collection.query(query_texts=["how long do refunds take"], n_results=3)