Chroma 集成

pip install -qU "langchain-chroma>=0.1.2"

chroma db connect [db_name] --env-file

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

# | output: false
# | echo: false
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

from langchain_chroma import Chroma

vector_store = Chroma(
    collection_name="example_collection",
    embedding_function=embeddings,
)

from langchain_chroma import Chroma

vector_store = Chroma(
    collection_name="example_collection",
    embedding_function=embeddings,
    persist_directory="./chroma_langchain_db",
)

from langchain_chroma import Chroma

vector_store = Chroma(
    collection_name="example_collection",
    embedding_function=embeddings,
    host="localhost",
)

from langchain_chroma import Chroma

vector_store = Chroma(
    collection_name="example_collection",
    embedding_function=embeddings,
    chroma_cloud_api_key=os.getenv("CHROMA_API_KEY"),
    tenant=os.getenv("CHROMA_TENANT"),
    database=os.getenv("CHROMA_DATABASE"),
)

import chromadb

client = chromadb.Client()

import chromadb

client = chromadb.PersistentClient(path="./chroma_langchain_db")

import chromadb

client = chromadb.HttpClient(host="localhost", port=8000, ssl=False)

import chromadb

client = chromadb.CloudClient()

collection = client.get_or_create_collection("collection_name")
collection.add(ids=["1", "2", "3"], documents=["a", "b", "c"])

vector_store_from_client = Chroma(
    client=client,
    collection_name="collection_name",
    embedding_function=embeddings,
)

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
    id=1,
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
    id=2,
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
    id=3,
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
    id=4,
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
    id=5,
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
    id=6,
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
    id=7,
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
    id=8,
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
    id=9,
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
    id=10,
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)

updated_document_1 = Document(
    page_content="I had chocolate chip pancakes and fried eggs for breakfast this morning.",
    metadata={"source": "tweet"},
    id=1,
)

updated_document_2 = Document(
    page_content="The weather forecast for tomorrow is sunny and warm, with a high of 82 degrees.",
    metadata={"source": "news"},
    id=2,
)

vector_store.update_document(document_id=uuids[0], document=updated_document_1)
# 您也可以一次更新多个文档
vector_store.update_documents(
    ids=uuids[:2], documents=[updated_document_1, updated_document_2]
)

vector_store.delete(ids=uuids[-1])

results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy",
    k=2,
    filter={"source": "tweet"},
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

results = vector_store.similarity_search_with_score(
    "Will it be hot tomorrow?", k=1, filter={"source": "news"}
)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

results = vector_store.similarity_search_by_vector(
    embedding=embeddings.embed_query("I love green eggs and ham!"), k=1
)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

retriever = vector_store.as_retriever(
    search_type="mmr", search_kwargs={"k": 1, "fetch_k": 5}
)
retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})