Azure AI Search向量存储导入报错：无法转换为Edm.String

问题场景 #

已成功创建Azure AI Search索引，代码如下：

# Define the index fields
client = SearchIndexClient(endpoint, credential)
fields = [
  SimpleField(name="id", type=SearchFieldDataType.String, key=True, sortable=True, 
                   filterable=True, facetable=True),
  SimpleField(name="originalbalancedue", type=SearchFieldDataType.Double, 
                   sortable=True, filterable=True, facetable=True),
  SimpleField(name="adjustedbalancedue", type=SearchFieldDataType.Double, 
                   sortable=True, filterable=True, facetable=True),
  SimpleField(name="feeamount", type=SearchFieldDataType.Double, sortable=True, 
                   filterable=True, facetable=True),
  SearchableField(name="result", type=SearchFieldDataType.Double, sortable=True, 
                   filterable=True)
]

index = SearchIndex(name=index_name, fields=fields, vector_search=vector_search)
result = client.create_or_update_index(index)
print(f'{result.name} created')

执行文档导入代码时：

with open('worthiness_with_result_small.json', 'r') as f:
    content = f.read().strip()
    if content:
        documents = json.loads(content)
        print(f"loaded {len(documents)} documents")
    else:
        print("The file is empty.")
search_client = SearchClient(endpoint=endpoint, index_name=index_name, 
credential=credential)
result = search_client.upload_documents(documents)
print(f"Uploaded {len(documents)} documents") 

出现如下错误：

HttpResponseError: () The request is invalid. Details: Cannot convert the literal '5759.12' to the expected type 'Edm.String'.
Code: 
Message: The request is invalid. Details: Cannot convert the literal '5759.12' to the expected type 'Edm.String'.

导入的JSON数据：

[{"id":"425001","originalbalancedue":1684269.59,"adjustedbalancedue":1683369.59,"feeamount":6659.1199999999998900,"result":5759.1199999999998900}]

错误原因 #

SearchableField类型不支持直接定义SearchFieldDataType.Double类型。当用SearchableField声明字段时，Azure AI Search默认期望该字段为字符串类型（Edm.String），但导入的result字段是数值类型，因此触发类型转换错误。

解决方案 #

将result字段的定义从SearchableField改为SimpleField，并添加searchable=True参数，这样既保留数值类型，又能让字段支持搜索：

修改后的索引字段定义代码：

# Define the index fields
client = SearchIndexClient(endpoint, credential)
fields = [
  SimpleField(name="id", type=SearchFieldDataType.String, key=True, sortable=True, 
                   filterable=True, facetable=True),
  SimpleField(name="originalbalancedue", type=SearchFieldDataType.Double, 
                   sortable=True, filterable=True, facetable=True),
  SimpleField(name="adjustedbalancedue", type=SearchFieldDataType.Double, 
                   sortable=True, filterable=True, facetable=True),
  SimpleField(name="feeamount", type=SearchFieldDataType.Double, sortable=True, 
                   filterable=True, facetable=True),
  # 修改此处：用SimpleField并开启searchable
  SimpleField(name="result", type=SearchFieldDataType.Double, sortable=True, 
                   filterable=True, searchable=True)
]

index = SearchIndex(name=index_name, fields=fields, vector_search=vector_search)
result = client.create_or_update_index(index)
print(f'{result.name} created')

修改后重新创建索引，再执行文档导入操作即可解决问题。

内容的提问来源于stack exchange，提问作者VictorGram