"
azure_openai_api_version: str = "2023-05-15"
azure_deployment: str = "text-embedding-ada-002"
```
我们将使用来自 Azure OpenAI 的嵌入模型将我们的文档转换为存储在 Azure AI 搜索向量存储中的嵌入。我们还将索引名称设置为 `langchain-vector-demo`。这将创建一个与该索引名称关联的新向量存储。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
embeddings = AzureOpenAIEmbeddings(
model=azure_deployment,
azure_endpoint=azure_endpoint,
openai_api_key=azure_openai_api_key,
)
vector_store: AzureSearch = AzureSearch(
embedding_function=embeddings.embed_query,
azure_search_endpoint=os.getenv("AZURE_AI_SEARCH_SERVICE_NAME"),
azure_search_key=os.getenv("AZURE_AI_SEARCH_API_KEY"),
index_name="langchain-vector-demo",
)
```
接下来，我们将数据加载到新创建的向量存储中。对于此示例，我们加载 `state_of_the_union.txt` 文件。我们将文本拆分为 400 个 token 的块，无重叠。最后，文档作为嵌入添加到我们的向量存储中。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import CharacterTextSplitter
loader = TextLoader("../../how_to/state_of_the_union.txt", encoding="utf-8")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=400, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
vector_store.add_documents(documents=docs)
```
接下来，我们将创建一个检索器。当前的 `index_name` 变量是上一步中的 `langchain-vector-demo`。如果您跳过了向量存储创建，请在参数中提供您的索引名称。在此查询中，将返回顶部结果。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
retriever = AzureAISearchRetriever(
content_key="content", top_k=1, index_name="langchain-vector-demo"
)
```
现在我们可以从上传的文档中检索与我们的查询相关的数据。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
retriever.invoke("does the president have a plan for covid-19?")
```
## 在链中使用
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI
prompt = ChatPromptTemplate.from_template(
"""Answer the question based only on the context provided.
Context: {context}
Question: {question}"""
)
llm = ChatOpenAI(model="gpt-4.1-mini")
def format_docs(docs):
return "\n\n".join(doc.page_content for doc in docs)
chain = (
{"context": retriever | format_docs, "question": RunnablePassthrough()}
| prompt
| llm
| StrOutputParser()
)
```
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.invoke("does the president have a plan for covid-19?")
```
***
## API 参考
有关所有 `AzureAISearchRetriever` 功能和配置的详细文档，请前往 [API 参考](https://reference.langchain.com/python/langchain-community/retrievers/azure_ai_search/AzureAISearchRetriever)。
***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\integrations\retrievers\azure_ai_search.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.