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.
import os
from zentry import Memory
os.environ["OPENAI_API_KEY"] = "sk-xx"
config = {
"vector_store": {
"provider": "chroma",
"config": {
"collection_name": "test",
"path": "db",
}
}
}
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": "Iām 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"})
Here are the parameters available for configuring Chroma:
| Parameter | Description | Default Value |
|---|
collection_name | The name of the collection | zentry |
client | Custom client for Chroma | None |
path | Path for the Chroma database | db |
host | The host where the Chroma server is running | None |
port | The port where the Chroma server is running | None |