Pinecone 嵌入

可以通过PineconeEmbeddings访问 Pinecone 的推理 API。通过 Pinecone 服务提供文本嵌入。我们首先安装必要的库

!pip install -qU "langchain-pinecone>=0.2.0" 

接下来，我们注册/登录 Pinecone以获取我们的 API 密钥

import os
from getpass import getpass

os.environ["PINECONE_API_KEY"] = os.getenv("PINECONE_API_KEY") or getpass(
    "Enter your Pinecone API key: "
)

查看文档以获取可用的模型。现在我们初始化我们的嵌入模型，如下所示

from langchain_pinecone import PineconeEmbeddings

embeddings = PineconeEmbeddings(model="multilingual-e5-large")

API 参考：PineconeEmbeddings

从这里我们可以创建同步或异步嵌入，让我们从同步开始！我们使用embed_query将单个文本作为查询嵌入（即我们在 RAG 中搜索的内容）进行嵌入

docs = [
    "Apple is a popular fruit known for its sweetness and crisp texture.",
    "The tech company Apple is known for its innovative products like the iPhone.",
    "Many people enjoy eating apples as a healthy snack.",
    "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces.",
    "An apple a day keeps the doctor away, as the saying goes.",
]

doc_embeds = embeddings.embed_documents(docs)
doc_embeds

query = "Tell me about the tech company known as Apple"
query_embed = embeddings.embed_query(query)
query_embed

相关

• 嵌入模型概念指南
• 嵌入模型操作指南