Skip to main content
Pinecone 是一个功能强大的向量数据库。
本 notebook 展示了如何使用与 Pinecone 向量数据库相关的功能。

安装配置

要使用 PineconeVectorStore,首先需要安装合作伙伴包以及本 notebook 中使用的其他包。
pip install -qU langchain langchain-pinecone langchain-openai
迁移说明:如果您正在从 langchain_community.vectorstores 的 Pinecone 实现迁移,在安装依赖于 pinecone-client v6 的 langchain-pinecone 之前,可能需要先移除 pinecone-client v2 依赖。

凭据

创建新的 Pinecone 账户,或登录现有账户,并创建本 notebook 中使用的 API 密钥。
import getpass
import os

from pinecone import Pinecone

if not os.getenv("PINECONE_API_KEY"):
    os.environ["PINECONE_API_KEY"] = getpass.getpass("Enter your Pinecone API key: ")

pinecone_api_key = os.environ.get("PINECONE_API_KEY")

pc = Pinecone(api_key=pinecone_api_key)
如果您希望自动追踪模型调用,也可以通过取消注释以下代码来设置您的 LangSmith API 密钥:
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

初始化

在初始化向量存储之前,先连接到 Pinecone 索引。如果名为 index_name 的索引不存在,将自动创建。
from pinecone import ServerlessSpec

index_name = "langchain-test-index"  # change if desired

if not pc.has_index(index_name):
    pc.create_index(
        name=index_name,
        dimension=1536,
        metric="cosine",
        spec=ServerlessSpec(cloud="aws", region="us-east-1"),
    )

index = pc.Index(index_name)
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
from langchain_pinecone import PineconeVectorStore

vector_store = PineconeVectorStore(index=index, embedding=embeddings)

管理向量存储

创建好向量存储后,可以通过添加和删除不同条目来与其交互。

向向量存储添加条目

可以使用 add_documents 函数向向量存储添加条目。
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"},
)

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

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

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

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

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

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

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

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

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

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)

从向量存储删除条目

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

查询向量存储

创建向量存储并添加相关文档后,您很可能希望在链或 agent 运行期间对其进行查询。

直接查询

执行简单的相似性搜索如下:
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}]")

带评分的相似性搜索

也可以带评分进行搜索:
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}]")

其他搜索方法

本 notebook 未列出更多搜索方法(例如 MMR),如需了解所有方法,请参阅 API 参考文档

转换为检索器进行查询

也可以将向量存储转换为检索器,以便在链中更方便地使用。
retriever = vector_store.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"k": 1, "score_threshold": 0.4},
)
retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})

用于检索增强生成

关于如何将此向量存储用于检索增强生成(RAG)的指南,请参阅以下章节:

API 参考

所有功能和配置的详细文档,请参阅 API 参考:python.langchain.com/api_reference/pinecone/vectorstores/langchain_pinecone.vectorstores.PineconeVectorStore.html