Chroma is an AI-native open-source vector database that simplifies building LLM apps by providing tools for storing, embedding, and searching embeddings with a focus on simplicity and speed. It supports both local deployment and cloud hosting through ChromaDB Cloud.

​
Usage

​
Local Installation

import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "sk-xx"

config = {
    "vector_store": {
        "provider": "chroma",
        "config": {
            "collection_name": "test",
            "path": "db",
            # Optional: ChromaDB Cloud configuration
            # "api_key": "your-chroma-cloud-api-key",
            # "tenant": "your-chroma-cloud-tenant-id",
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="alice", metadata={"category": "movies"})

​
Config

Here are the parameters available for configuring Chroma:
ParameterDescriptionDefault Value
collection_nameThe name of the collectionmem0
clientCustom client for ChromaNone
pathPath for the Chroma databasedb
hostThe host where the Chroma server is runningNone
portThe port where the Chroma server is runningNone
api_keyChromaDB Cloud API key (for cloud usage)None
tenantChromaDB Cloud tenant ID (for cloud usage)None