跳至主要內容

Chroma

本筆記本涵蓋如何開始使用 Chroma 向量儲存庫。

Chroma 是一個 AI 原生的開源向量資料庫，專注於開發人員的生產力和幸福感。 Chroma 採用 Apache 2.0 許可證。 在此頁面檢視 Chroma 的完整文件，並在此頁面找到 LangChain 整合的 API 參考資料。

設定​

要存取 Chroma 向量儲存庫，您需要安裝 langchain-chroma 整合套件。

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

憑證​

您可以使用 Chroma 向量儲存庫而無需任何憑證，只需安裝上面的套件就足夠了！

如果您想要獲得一流的模型呼叫自動追蹤功能，您也可以透過取消註釋下面內容來設定您的 LangSmith API 金鑰

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

初始化​

基本初始化​

以下是一個基本初始化，包括使用目錄在本地儲存資料。

pip install -qU langchain-openai
import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

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,
    persist_directory="./chroma_langchain_db",  # Where to save data locally, remove if not necessary
)

從客戶端初始化​

您也可以從 Chroma 客戶端初始化，如果您想要更輕鬆地存取底層資料庫，這特別有用。

import chromadb

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

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

管理向量儲存庫​

一旦您創建了向量儲存庫，我們可以透過新增和刪除不同的項目與其互動。

將項目新增到向量儲存庫​

我們可以使用 add_documents 函數將項目新增到向量儲存庫。

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)
API 參考資料：Document
['f22ed484-6db3-4b76-adb1-18a777426cd6',
 'e0d5bab4-6453-4511-9a37-023d9d288faa',
 '877d76b8-3580-4d9e-a13f-eed0fa3d134a',
 '26eaccab-81ce-4c0a-8e76-bf542647df18',
 'bcaa8239-7986-4050-bf40-e14fb7dab997',
 'cdc44b38-a83f-4e49-b249-7765b334e09d',
 'a7a35354-2687-4bc2-8242-3849a4d18d34',
 '8780caf1-d946-4f27-a707-67d037e9e1d8',
 'dec6af2a-7326-408f-893d-7d7d717dfda9',
 '3b18e210-bb59-47a0-8e17-c8e51176ea5e']

更新向量儲存庫中的項目​

現在我們已經將文件新增到向量儲存庫，我們可以透過使用 update_documents 函數來更新現有文件。

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)
# You can also update multiple documents at once
vector_store.update_documents(
    ids=uuids[:2], documents=[updated_document_1, updated_document_2]
)

從向量儲存庫中刪除項目​

我們也可以如下方式從向量儲存庫中刪除項目

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

查詢向量儲存庫​

一旦您的向量儲存庫已建立並且已新增相關文件，您很可能希望在您的鏈或代理程式執行期間查詢它。

直接查詢​

執行簡單的相似性搜尋可以如下方式完成

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}]")
* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

帶分數的相似性搜尋​

如果您想要執行相似性搜尋並接收相應的分數，您可以執行

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}]")
* [SIM=1.726390] The stock market is down 500 points today due to fears of a recession. [{'source': 'news'}]

依向量搜尋​

您也可以依向量搜尋

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}]")
* I had chocalate chip pancakes and fried eggs for breakfast this morning. [{'source': 'tweet'}]

其他搜尋方法​

本筆記本未涵蓋各種其他搜尋方法，例如 MMR 搜尋或依向量搜尋。 如需 AstraDBVectorStore 可用的完整搜尋能力清單，請查看 API 參考資料。

透過轉換為檢索器來查詢​

您也可以將向量儲存庫轉換為檢索器，以便在您的鏈中更輕鬆地使用。 如需您可以傳遞的不同搜尋類型和 kwargs 的更多資訊，請造訪 API 參考資料此處。

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

用於檢索增強產生的用法​

如需有關如何使用此向量儲存庫進行檢索增強產生 (RAG) 的指南，請參閱以下各節

API 參考資料​

如需所有 Chroma 向量儲存庫功能和配置的詳細文件，請前往 API 參考資料：https://langchain-python.dev.org.tw/api_reference/chroma/vectorstores/langchain_chroma.vectorstores.Chroma.html

此頁面是否對您有幫助？