ChromaDB Quickstart

First insert two documents and retrieve a relevant result. A local client is enough to understand that loop before adding server infrastructure or external providers.

#Install and run a minimal example

bashCopy
pip install chromadb

pythonCopy
import chromadb

client = chromadb.PersistentClient(path="./my_db")
collection = client.get_or_create_collection(name="my_documents")
collection.add(
    documents=["Apple makes the iPhone.", "Microsoft develops Windows."],
    metadatas=[{"source": "wiki"}, {"source": "wiki"}],
    ids=["id1", "id2"],
)
results = collection.query(query_texts=["Who develops Windows?"], n_results=1)
print(results)

The configured/default embedding function may download a local model. Confirm the environment and version requirements before running the example.

#Establish a baseline

Start with documents and metadata, confirm correct retrieval, then evaluate around twenty representative queries before selecting a custom embedding model.

#Storage modes

The source shows a basic Docker server:

bashCopy
docker pull chromadb/chroma
docker run -p 8000:8000 chromadb/chroma

This is an illustrative start command, not a complete secure production deployment. Plan persistence, access and versioning for an actual service.

#Next step

• Collections