OpenAIEmbeddings 集成

import getpass
import os

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

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

pip install -qU langchain-openai

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-large",
    # 对于 `text-embedding-3` 类模型，
    # 您可以指定返回嵌入的维度。
    # dimensions=1024
)

# 使用示例文本创建向量存储
from langchain_core.vectorstores import InMemoryVectorStore

text = "LangChain is the framework for building context-aware reasoning applications"

vectorstore = InMemoryVectorStore.from_texts(
    [text],
    embedding=embeddings,
)

# 使用向量存储作为检索器
retriever = vectorstore.as_retriever()

# 检索最相似的文本
retrieved_documents = retriever.invoke("What is LangChain?")

# 显示检索到的文档内容
retrieved_documents[0].page_content

'LangChain is the framework for building context-aware reasoning applications'

single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100])  # 显示向量的前 100 个字符

[-0.019276829436421394, 0.0037708976306021214, -0.03294256329536438, 0.0037671267054975033, 0.008175

text2 = (
    "LangGraph is a library for building stateful, multi-actor applications with LLMs"
)
two_vectors = embeddings.embed_documents([text, text2])
for vector in two_vectors:
    print(str(vector)[:100])  # 显示向量的前 100 个字符

[-0.019260549917817116, 0.0037612367887049913, -0.03291035071015358, 0.003757466096431017, 0.0082049
[-0.010181212797760963, 0.023419594392180443, -0.04215526953339577, -0.001532090245746076, -0.023573

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-large",  # 您的 Azure 部署名称
    base_url="https://{your-resource-name}.openai.azure.com/openai/v1/",
    api_key="your-azure-api-key"
)

# 正常使用
vector = embeddings.embed_query("Hello world")

from azure.identity import DefaultAzureCredential, get_bearer_token_provider
from langchain_openai import OpenAIEmbeddings

# 创建一个处理自动刷新的令牌提供程序
token_provider = get_bearer_token_provider(
    DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default"
)

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-large",  # 您的 Azure 部署名称
    base_url="https://{your-resource-name}.openai.azure.com/openai/v1/",
    api_key=token_provider  # 处理令牌刷新的可调用对象
)

# 正常使用
vectors = embeddings.embed_documents(["Hello", "World"])

from azure.identity.aio import DefaultAzureCredential
from langchain_openai import OpenAIEmbeddings

credential = DefaultAzureCredential()

embeddings_async = OpenAIEmbeddings(
    model="text-embedding-3-large",
    api_key=credential
)

# 使用异步可调用对象时使用异步方法
vectors = await embeddings_async.aembed_documents(["Hello", "World"])