How to use Python to perform vector search or hybrid search on Azure AI Search?
题意 ：如何使用 Python 在 Azure AI 搜索上执行向量搜索或混合搜索？
问题背景：
As title 如题
My configuration involves navigating to "Import and Vectorize Data" within the Azure AI Search Portal, which results in the creation of an indexed dataset containing vectorized values. I am familiar with Python as a tool for integrating into Azure AI Search platforms.
我的设置如下：我在 Azure AI 搜索门户中配置了向量化数据导入流程，并进而生成了一个包含向量值的索引。我习惯使用 Python 来进行 Azure AI 搜索。
Python code is as follow;
Python 代码如下：
credential = AzureKeyCredential(key)
search_client = SearchClient(
endpoint=endpoint,
index_name=index_name,
credential=credential
)
text=input("Qes:")
results=search_client.search(search_text=text,select="title")
for ans in results:
print(ans)What can I carry out a vector or hybrid search in Python within this scenario?
在这种情况下，我该如何在 Python 中执行向量搜索或混合搜索？
问题解决：
Posting my comments as an answer is a benefit for the community.
将我的评论作为答案发布对社区是有益的。
Click on the following steps to perform vector search.
你可以查看这个 GitHub 链接，按照下面的步骤执行向量搜索：
Create or Generate Embeddings : Begin with analyzing and processing the data to create meaningful embeddings using OpenAI's powerful AI model. Once created, export these embeddings in a structured format that seamlessly integrates with the Azure AI Search index for efficient retrieval of information.
Configure Search Index Setup: Define the schema structure for your search index and establish vector search parameters according to specific requirements.
Insert Document Content and Embeddings into the Index: Your vector store will be populated with the text data, along with its associated metadata, extracted directly from your JSON dataset.
执行向量相似度搜索：通过提供的代码实现向量相似度搜索。只需提供文本查询，并由预设程序自动完成查询的预处理工作
from azure.search.documents.models import VectorizedQuery
query = "tools for software development"
embedding = client.embeddings.create(input=query, model=embedding_model_name).data[0].embedding
vector_query = VectorizedQuery(vector=embedding, k_nearest_neighbors=3, fields="contentVector")
results = search_client.search(
search_text=None,
vector_queries= [vector_query],
select=["title", "content", "category"],
)
for result in results:
print(f"Title: {result['title']}")
print(f"Score: {result['@search.score']}")
print(f"Content: {result['content']}")
print(f"Category: {result['category']}\n") Below is the code for Hybrid Search :
下面是混合搜索的代码：
query = "scalable storage solution"
embedding = client.embeddings.create(input=query, model=embedding_model_name).data[0].embedding
vector_query = VectorizedQuery(vector=embedding, k_nearest_neighbors=3, fields="contentVector")
results = search_client.search(
search_text=query,
vector_queries=[vector_query],
select=["title", "content", "category"],
top=3
)
for result in results:
print(f"Title: {result['title']}")
print(f"Score: {result['@search.score']}")
print(f"Content: {result['content']}")
print(f"Category: {result['category']}\n") 