python-3.x - 为什么 Azure 认知搜索 Python SDK 不返回 @search.answers arraya，而 API 却返回？

Question

我在使用 Azure 认知搜索 Python SDK“azure-search-documents 11.3.0b6”的 Beta 版时遇到问题，该 SDK 可用于查询 Azure 认知搜索索引并提供结果，包括相关内容和可以回答的简短文本段落查询(如果其格式为问题)。

当使用 POSTMAN 直接查询 API 时，它会在名为“@search.answers”的数组中提供答案，但是当使用相同的参数和查询时，我在结果中看不到答案。 SDK 是否存在已知问题，因为它是测试版，或者有人有一个工作版本可以告诉我我做错了什么？谢谢!

索引定义

{
"@odata.context": "https://<servicename>.search.windows.net/$metadata#indexes/$entity",
"@odata.etag": "\"0x8DBC386F9BFC9DA\"",
"name": "<indexname>",
"defaultScoringProfile": null,
"fields": [
    {
        "name": "id",
        "type": "Edm.String",
        "searchable": false,
        "filterable": true,
        "retrievable": true,
        "sortable": true,
        "facetable": true,
        "key": true,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    },
    {
        "name": "metadata_spo_item_name",
        "type": "Edm.String",
        "searchable": true,
        "filterable": true,
        "retrievable": true,
        "sortable": true,
        "facetable": false,
        "key": false,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    },
    {
        "name": "metadata_spo_item_path",
        "type": "Edm.String",
        "searchable": false,
        "filterable": false,
        "retrievable": true,
        "sortable": false,
        "facetable": false,
        "key": false,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    },
    {
        "name": "metadata_spo_item_content_type",
        "type": "Edm.String",
        "searchable": false,
        "filterable": true,
        "retrievable": true,
        "sortable": false,
        "facetable": true,
        "key": false,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    },
    {
        "name": "metadata_spo_item_last_modified",
        "type": "Edm.DateTimeOffset",
        "searchable": false,
        "filterable": false,
        "retrievable": true,
        "sortable": true,
        "facetable": false,
        "key": false,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    },
    {
        "name": "metadata_spo_item_size",
        "type": "Edm.Int64",
        "searchable": false,
        "filterable": false,
        "retrievable": true,
        "sortable": false,
        "facetable": false,
        "key": false,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    },
    {
        "name": "metadata_spo_item_weburi",
        "type": "Edm.String",
        "searchable": true,
        "filterable": false,
        "retrievable": true,
        "sortable": false,
        "facetable": false,
        "key": false,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    },
    {
        "name": "content",
        "type": "Edm.String",
        "searchable": true,
        "filterable": false,
        "retrievable": true,
        "sortable": false,
        "facetable": false,
        "key": false,
        "indexAnalyzer": null,
        "searchAnalyzer": null,
        "analyzer": null,
        "synonymMaps": []
    }
],
"scoringProfiles": [],
"corsOptions": null,
"suggesters": [
    {
        "name": "sg",
        "searchMode": "analyzingInfixMatching",
        "sourceFields": [
            "metadata_spo_item_name"
        ]
    }
],
"analyzers": [],
"tokenizers": [],
"tokenFilters": [],
"charFilters": [],
"encryptionKey": null,
"similarity": {
    "@odata.type": "#Microsoft.Azure.Search.BM25Similarity",
    "k1": null,
    "b": null
}

}

POSTMAN API 配置和结果

Python 代码和结果

import os

# load classes from libraries
from dotenv import load_dotenv
from typing import cast
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
load_dotenv()

# Load the environment variables
index_name = cast(str, os.getenv("SEARCH_INDEX_NAME"))
endpoint_name = cast(str, os.getenv("SEARCH_ENDPOINT"))
key = cast(str, os.getenv("SEARCH_API_KEY"))

# search function configured with semanatic search configuration
def search(event=None):
    search_query = "what is a service that provides site recovery"
    search_client = SearchClient(endpoint_name, index_name, AzureKeyCredential(key))
    results = search_client.search(
          search_text=search_query,
          query_speller="lexicon",
          query_type="semantic",
          semantic_configuration_name="Pilot Semantic",
          query_answer="extractive",
          query_answer_count=1,
          query_caption="extractive",
          query_caption_highlight=True,
          query_language="en-us",
          search_mode="any",
          include_total_count=True,
          top=1,
          select="metadata_spo_item_name"
    )
    for result in results:
        #content = result["content"]
        #truncated_content = (content[:300] + '..') if len(content) > 100 else content
        #print(truncated_content)
        print(result)
  

if __name__ == "__main__":
    search()

Answer 1

要使用 python SDK 获取 @search.answers，您可以在结果输出中使用 results.get_answers()。

下面是从答案中获取文本并突出显示的示例代码片段:

semantic_answers = results.get_answers()
for answer in semantic_answers:
    if answer.highlights:
        print(f"Semantic Answer: {answer.highlights}")
    else:
        print(f"Semantic Answer: {answer.text}")
    print(f"Semantic Answer Score: {answer.score}\n")

我已经使用了最新的测试版:azure-search-documents 11.4.0b8

使用上述SDK版本和代码，我能够得到所需的结果。

有关更多详细信息，您可以查看此 sample notebook.