database.py

import chromadb
from chromadb.utils import embedding_functions

def get_client():
    client = chromadb.PersistentClient(path="./chromadb_linux/")
    MODEL_NAME: str = "mixedbread-ai/mxbai-embed-large-v1"  # ~ 0.5 gb
    COLLECTION_NAME: str = "scheme"
    EMBEDDING_FUNC = embedding_functions.SentenceTransformerEmbeddingFunction(
        model_name=MODEL_NAME
    )
    schemer = client.get_collection(
        name=COLLECTION_NAME,
        embedding_function=EMBEDDING_FUNC,
    )
    return schemer