Pinecone
Pinecone 是一個具有廣泛功能的向量資料庫。
此筆記本展示了如何使用與 Pinecone 向量資料庫相關的功能。
設定 (Setup)
要使用 PineconeVectorStore，您首先需要安裝合作夥伴套件，以及本筆記本中使用的其他套件。
%pip install -qU langchain-pinecone pinecone-notebooks
遷移注意事項：如果您從 langchain_community.vectorstores 的 Pinecone 實作遷移，您可能需要在安裝依賴 pinecone-client v3 的 langchain-pinecone 之前，移除您的 pinecone-client v2 依賴。
憑證 (Credentials)
建立一個新的 Pinecone 帳戶，或登入您現有的帳戶，並建立一個 API 金鑰，以便在本筆記本中使用。
import getpass
import os
import time
from pinecone import Pinecone, ServerlessSpec
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)
如果您想要取得模型呼叫的自動追蹤，您也可以取消註解以下內容來設定您的 LangSmith API 金鑰
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"
初始化 (Initialization)
在初始化我們的向量儲存之前，讓我們先連接到 Pinecone 索引。如果名為 index_name 的索引不存在，將會建立一個。
import time
index_name = "langchain-test-index" # change if desired
existing_indexes = [index_info["name"] for index_info in pc.list_indexes()]
if index_name not in existing_indexes:
pc.create_index(
name=index_name,
dimension=3072,
metric="cosine",
spec=ServerlessSpec(cloud="aws", region="us-east-1"),
)
while not pc.describe_index(index_name).status["ready"]:
time.sleep(1)
index = pc.Index(index_name)
現在我們的 Pinecone 索引已設定完成，我們可以初始化我們的向量儲存。
選擇 嵌入模型
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_pinecone import PineconeVectorStore
vector_store = PineconeVectorStore(index=index, embedding=embeddings)
API 參考：PineconeVectorStore
管理向量儲存 (Manage vector store)
一旦您建立了向量儲存，我們就可以透過新增和刪除不同的項目與之互動。
新增項目到向量儲存 (Add items to vector store)
我們可以透過使用 add_documents 函數來新增項目到我們的向量儲存。
from uuid import uuid4
from langchain_core.documents import Document
document_1 = Document(
page_content="I had chocalate 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)
API 參考：Document
['167b8681-5974-467f-adcb-6e987a18df01',
'd16010fd-41f8-4d49-9c22-c66d5555a3fe',
'ffcacfb3-2bc2-44c3-a039-c2256a905c0e',
'cf3bfc9f-5dc7-4f5e-bb41-edb957394126',
'e99b07eb-fdff-4cb9-baa8-619fd8efeed3',
'68c93033-a24f-40bd-8492-92fa26b631a4',
'b27a4ecb-b505-4c5d-89ff-526e3d103558',
'4868a9e6-e6fb-4079-b400-4a1dfbf0d4c4',
'921c0e9c-0550-4eb5-9a6c-ed44410788b2',
'c446fc23-64e8-47e7-8c19-ecf985e9411e']
從向量儲存刪除項目 (Delete items from vector store)
vector_store.delete(ids=[uuids[-1]])
查詢向量儲存 (Query vector store)
一旦您的向量儲存被建立並且相關文件被新增，您很可能會希望在您的鏈或代理程式運行期間查詢它。
直接查詢 (Query directly)
可以如下執行簡單的相似性搜尋
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 (Similarity search with score)
您也可以用分數進行搜尋
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=0.553187] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]
其他搜尋方法 (Other search methods)
還有更多搜尋方法（例如 MMR）未在本筆記本中列出，要找到所有方法，請務必閱讀 API 參考。
通過轉換成檢索器來查詢 (Query by turning into retriever)
您也可以將向量儲存轉換為檢索器，以便在您的鏈中更輕鬆地使用。
retriever = vector_store.as_retriever(
search_type="similarity_score_threshold",
search_kwargs={"k": 1, "score_threshold": 0.5},
)
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.')]
用於檢索增強生成 (retrieval-augmented generation) 的用法
有關如何將此向量儲存用於檢索增強生成 (RAG) 的指南，請參閱以下章節
- 教程 (Tutorials)
- 操作方法：使用 RAG 進行問答 (How-to: Question and answer with RAG)
- 檢索概念文件 (Retrieval conceptual docs)
API 參考 (API reference)
有關所有 __ModuleName__VectorStore 功能和配置的詳細文檔，請前往 API 參考：https://langchain-python.dev.org.tw/api_reference/pinecone/vectorstores/langchain_pinecone.vectorstores.PineconeVectorStore.html