FirstBatch integrates Chroma through the Chroma Class.
Example run:
import chromadb
from firstbatch import Chroma
path = os.environ["CHROMA_CLIENT_PATH"]
collection = "default"
client = chromadb.PersistentClient(path=path)
embedding_size = int(os.environ["EMBEDDING_SIZE"])
config = Config(batch_size=20, verbose=True)
personalized = FirstBatch(api_key=os.environ["FIRSTBATCH_API_KEY"], config=config)
personalized.add_vdb("chroma_db", Chroma(client=client, collection_name=collection, embedding_size=embedding_size))
Distance metric can explicitly be provided. If not, default value is COSINE_SIM
class DistanceMetric(Enum):
COSINE_SIM = "cosine_sim"
EUCLIDEAN_DIST = "euclidean_dist"
DOT_PRODUCT = "dot_product"
from firstbatch import DistanceMetric
Chroma(client=client, collection_name=collection,
distance_metric=DistanceMetric.EUCLIDEAN_DIST)
