hwchase17 / chroma-langchain Goto Github PK

client.get_or_create_collection
collection.upsert()

db = Chroma.from_texts(texts, embeddings, metadatas=metadatas, ids=ids, collection_name=collection_name, persist_directory="db")

loader = PyPDFLoader("data/Diabetes.pdf")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
db = Chroma.from_documents(docs, OpenAIEmbeddings())

# create chroma db or load db from disk
from langchain.embeddings import OllamaEmbeddings
from langchain.vectorstores import Chroma
import chromadb
from chromadb.config import Settings

client_settings = Settings(
    chroma_api_impl="chromadb.api.fastapi.FastAPI",
    chroma_client_auth_provider="chromadb.auth.token.TokenAuthClientProvider",
    chroma_client_auth_credentials="xxxxxx",
    chroma_client_auth_token_transport_header="X_CHROMA_TOKEN",
    allow_reset=True,
    anonymized_telemetry=False
)

client = chromadb.HttpClient(
    host="localhost",
    port=8000,
    settings=client_settings,
)
collection = client.get_or_create_collection(name="documents")

emb_fn = OllamaEmbeddings(base_url=OLLAMA_URL, model=OLLAMA_MODEL)

def get_chroma(chroma_client):
    chroma_db = Chroma(
        collection_name="documents",
        embedding_function=emb_fn,
        client=chroma_client,
    )
    return chroma_db

chroma_db_client = get_chroma(client)

if init_db:
    chroma_db_client.from_documents(all_document_chunks, emb_fn)
    print(collection.count())
    print(collection.peek())
else:
    chroma_db_client = Chroma(embedding_function=emb_fn)

0
{'ids': [], 'embeddings': [], 'metadatas': [], 'documents': [], 'data': None, 'uris': None}