Chroma: The Easiest Vector Database for LLM Apps

pip install chromadb

import chromadb

client = chromadb.Client()  # ephemeral, in-memory
collection = client.create_collection("docs")

collection.add(
    documents=["PagedAttention manages KV cache as pages.", "HNSW is a graph ANN index."],
    ids=["doc1", "doc2"],
)

results = collection.query(
    query_texts=["how does LLM memory work?"],
    n_results=2,
)
print(results["documents"])

client = chromadb.PersistentClient(path="./chroma_db")

collection.add(
    documents=["LangGraph is a state machine framework.", "Instructor adds Pydantic to LLMs."],
    metadatas=[{"category": "agents"}, {"category": "tooling"}],
    ids=["doc3", "doc4"],
)

results = collection.query(
    query_texts=["build an agent"],
    where={"category": "agents"},
    n_results=1,
)

from chromadb import EmbeddingFunction
from sentence_transformers import SentenceTransformer

class LocalEmbedder(EmbeddingFunction):
    def __init__(self):
        self.model = SentenceTransformer("all-mpnet-base-v2")

    def __call__(self, input: list[str]) -> list[list[float]]:
        return self.model.encode(input).tolist()

collection = client.create_collection("docs", embedding_function=LocalEmbedder())

pip install langchain-chroma

from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings

vectorstore = Chroma(
    collection_name="docs",
    embedding_function=OpenAIEmbeddings(),
    persist_directory="./chroma_db",
)
retriever = vectorstore.as_retriever(search_kwargs={"k": 4})

chroma run --host 0.0.0.0 --port 8000

client = chromadb.HttpClient(host="localhost", port=8000)