为什么在技能组管道中调用自定义 Web API 技能提取页码时没有触发 azure 函数？

问题描述 投票：0回答：1

我正在关注thisSO帖子，从纯文本的pdf中提取页码。我在索引中创建了一个 

page_number
字段。

我还使用 azure 函数创建了自定义 Web API 技能，并在索引器定义中使用 

OuputFieldMappings
数组映射技能丰富的输出。在下面的天蓝色函数定义中，我假设请求数据看起来像这样，正如上述 SO 帖子中提到的那样。这个假设正确吗？开发人员如何测试他们的技能强化步骤？

{
    "data": "BASE64 ENCODED STRING OF A JPEG IMAGE",
    "width": 500,
    "height": 300,
    "originalWidth": 5000,  
    "originalHeight": 3000,
    "rotationFromOriginal": 90,
    "contentOffset": 500,
    "pageNumber": 2
  }

运行索引器后，我通过为部署创建的 azure 函数应用程序资源中的日志流来监视日志，并且不会生成任何信息日志。我怀疑我的自定义 Web API 技能在技能组运行时没有被调用。因此，这就是为什么当我对搜索索引执行矢量搜索查询时，

page_number
字段始终为
null
。我列出了我的技能组、天蓝色函数和索引器的定义，任何人都可以指导我缺少的内容吗？ TIA

技能组定义

{
  "@odata.context": "https://ai-studio-search-test.search.windows.net/$metadata#skillsets/$entity",
  "@odata.etag": "\"0x8DC9745F955DC29\"",
  "name": "test-skillset",
  "description": "Skillset to chunk documents and generating embeddings",
  "skills": [
    {
      "@odata.type": "#Microsoft.Skills.Text.SplitSkill",
      "name": "#1",
      "description": "Split skill to chunk documents",
      "context": "/document",
      "defaultLanguageCode": "en",
      "textSplitMode": "pages",
      "maximumPageLength": 2000,
      "pageOverlapLength": 500,
      "maximumPagesToTake": 0,
      "inputs": [
        {
          "name": "text",
          "source": "/document/content"
        }
      ],
      "outputs": [
        {
          "name": "textItems",
          "targetName": "pages"
        }
      ]
    },
    {
      "@odata.type": "#Microsoft.Skills.Text.AzureOpenAIEmbeddingSkill",
      "name": "#2",
      "description": "Skill to generate embeddings via Azure OpenAI",
      "context": "/document/pages/*",
      "resourceUri": "https://crowemind-non-prd-us-east-2.openai.azure.com",
      "apiKey": "<redacted>",
      "deploymentId": "text-embedding-ada-002",
      "dimensions": 1536,
      "modelName": "text-embedding-ada-002",
      "inputs": [
        {
          "name": "text",
          "source": "/document/pages/*"
        }
      ],
      "outputs": [
        {
          "name": "embedding",
          "targetName": "vector"
        }
      ],
      "authIdentity": null
    },
    {
      "@odata.type": "#Microsoft.Skills.Custom.WebApiSkill",
      "name": "#3",
      "description": "",
      "context": "/document/normalized_images/*",
      "uri": "https://azure-searchskill-apis.azurewebsites.net/api/pageno_skillapi_anonymous",
      "httpMethod": "POST",
      "timeout": "PT30S",
      "batchSize": 1,
      "degreeOfParallelism": 1,
      "authResourceId": null,
      "inputs": [
        {
          "name": "normalized_images",
          "source": "/document/normalized_images/*"
        }
      ],
      "outputs": [
        {
          "name": "page_number",
          "targetName": "page_number"
        }
      ],
      "httpHeaders": {},
      "authIdentity": null
    }
  ],
  "cognitiveServices": null,
  "knowledgeStore": null,
  "indexProjections": {
    "selectors": [
      {
        "targetIndexName": "test-index-secondary",
        "parentKeyFieldName": "parent_id",
        "sourceContext": "/document",
        "mappings": [
          {
            "name": "chunk",
            "source": "/document/pages/*",
            "sourceContext": null,
            "inputs": []
          },
          {
            "name": "text_vector",
            "source": "/document/pages/*/vector",
            "sourceContext": null,
            "inputs": []
          },
          {
            "name": "title",
            "source": "/document/metadata_storage_name",
            "sourceContext": null,
            "inputs": []
          },
          {
            "name": "page_number",
            "source": "/document/normalized_images/*/page_number",
            "sourceContext": null,
            "inputs": []
          }
        ]
      }
    ],
    "parameters": {
      "projectionMode": "skipIndexingParentDocuments"
    }
  },
  "encryptionKey": null
}

Azure 功能已部署

@app.route(route="pageno_skillapi_anonymous", auth_level=func.AuthLevel.ANONYMOUS)
def pageno_skillapi_anonymous(req: func.HttpRequest) -> func.HttpResponse:
    payload = req.get_json()
    if payload:
        logging.info("request body received from /document/normalized_images/* context")
        logging.info(f"payload: ${payload}")

        if "pageNumber" in payload:
            page_number = payload
            return func.HttpResponse(str(payload["pageNumber"]), status_code=200)
        else:
            return func.HttpResponse("No pageNumber parameter in /document/normalized_images/* context", status_code=200)

    else:
        logging.info("request body is empty")
        return func.HttpResponse("request body is empty", status_code=200)

索引器定义

{
  "@odata.context": "https://ai-studio-search-test.search.windows.net/$metadata#indexers/$entity",
  "@odata.etag": "\"0x8DC976AFC2C0D01\"",
  "name": "test-indexer",
  "description": "Indexer to index documents and generate embeddings",
  "dataSourceName": "test-blob",
  "skillsetName": "test-skillset",
  "targetIndexName": "test-index",
  "disabled": false,
  "schedule": null,
  "parameters": {
    "batchSize": null,
    "maxFailedItems": null,
    "maxFailedItemsPerBatch": null,
    "base64EncodeKeys": null,
    "configuration": {
      "dataToExtract": "contentAndMetadata",
      "parsingMode": "default",
      "imageAction": "generateNormalizedImagePerPage"
    }
  },
  "fieldMappings": [
    {
      "sourceFieldName": "metadata_storage_name",
      "targetFieldName": "title",
      "mappingFunction": null
    }
  ],
  "outputFieldMappings": [
    {
      "sourceFieldName": "/document/normalized_images/*/page_number",
      "targetFieldName": "page_number"
    }
  ],
  "cache": null,
  "encryptionKey": null
}

我尝试更改自定义字段的上下文，但没有执行任何操作。

azure-cognitive-search
1个回答
0
投票

根据此文档，当您设置

imageAction
时，您将在
/document/normalized_images/*
上下文中获得图像数组

因此，您不能在主索引中进行输出字段映射，如果进行映射，则需要将其映射到结果数据类型的类型集合的字段，如下所示。

enter image description here

要单独获取数据，需要创建二级索引并对其进行投影。

您无需将 

page_number
传递给您的自定义 Web api 技能，当您将 
imageAction
作为 
generateNormalizedImages
时，它已经配置好了。

因此，您可以使用

ocr
技能组从页面中提取文本并使用页码进行投影。

以下是技能组定义。

{
  "@odata.context": "https://jgsai.search.windows.net/$metadata#skillsets/$entity",
  "@odata.etag": "\"0x8DC9A7C02836ACA\"",
  "name": "skillset1719835991688",
  "description": "",
  "skills": [
    {
      "@odata.type": "#Microsoft.Skills.Vision.OcrSkill",
      "name": "#1",
      "description": null,
      "context": "/document/normalized_images/*",
      "textExtractionAlgorithm": null,
      "lineEnding": "Space",
      "defaultLanguageCode": "en",
      "detectOrientation": true,
      "inputs": [
        {
          "name": "image",
          "source": "/document/normalized_images/*"
        }
      ],
      "outputs": [
        {
          "name": "text",
          "targetName": "text"
        }
      ]
    }
  ],
  "cognitiveServices": {
    "@odata.type": "#Microsoft.Azure.Search.DefaultCognitiveServices",
    "description": null
  },
  "knowledgeStore": null,
  "indexProjections": {
    "selectors": [
      {
        "targetIndexName": "test-index",
        "parentKeyFieldName": "parent_id",
        "sourceContext": "/document/normalized_images/*",
        "mappings": [
          {
            "name": "page_number",
            "source": "/document/normalized_images/*/pageNumber",
            "sourceContext": null,
            "inputs": []
          },
          {
            "name": "page_content",
            "source": "/document/normalized_images/*/text",
            "sourceContext": null,
            "inputs": []
          }
        ]
      }
    ],
    "parameters": {
      "projectionMode": "skipIndexingParentDocuments"
    }
  },
  "encryptionKey": null
}

索引器定义

{
  "@odata.context": "https://jgsai.search.windows.net/$metadata#indexers/$entity",
  "@odata.etag": "\"0x8DC9A7C1434746D\"",
  "name": "azureblob-indexer",
  "description": "",
  "dataSourceName": "ds",
  "skillsetName": "skillset1719835991688",
  "targetIndexName": "azureblob-index",
  "disabled": null,
  "schedule": null,
  "parameters": {
    "batchSize": null,
    "maxFailedItems": 0,
    "maxFailedItemsPerBatch": 0,
    "base64EncodeKeys": null,
    "configuration": {
      "dataToExtract": "contentAndMetadata",
      "parsingMode": "default",
      "imageAction": "generateNormalizedImages"
    }
  },
  "fieldMappings": [
    {
      "sourceFieldName": "metadata_storage_path",
      "targetFieldName": "metadata_storage_path",
      "mappingFunction": {
        "name": "base64Encode",
        "parameters": null
      }
    }
  ],
  "outputFieldMappings": [],
  "cache": null,
  "encryptionKey": null
}

以及目标指标定义。

{
  "@odata.context": "https://jgsai.search.windows.net/$metadata#indexes/$entity",
  "@odata.etag": "\"0x8DC9A73656E2423\"",
  "name": "test-index",
  "defaultScoringProfile": null,
  "fields": [
    {
      "name": "id",
      "type": "Edm.String",
      "searchable": true,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": true,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "keyword",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "vectorEncoding": null,
      "synonymMaps": []
    },
    {
      "name": "parent_id",
      "type": "Edm.String",
      "searchable": true,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "vectorEncoding": null,
      "synonymMaps": []
    },
    {
      "name": "page_number",
      "type": "Edm.Int64",
      "searchable": false,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "vectorEncoding": null,
      "synonymMaps": []
    },
    {
      "name": "page_content",
      "type": "Edm.String",
      "searchable": true,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "vectorEncoding": null,
      "synonymMaps": []
    }
  ],
  "scoringProfiles": [],
  "corsOptions": null,
  "suggesters": [],
  "analyzers": [],
  "normalizers": [],
  "tokenizers": [],
  "tokenFilters": [],
  "charFilters": [],
  "encryptionKey": null,
  "similarity": {
    "@odata.type": "#Microsoft.Azure.Search.BM25Similarity",
    "k1": null,
    "b": null
  },
  "semantic": null,
  "vectorSearch": null
}

输出：

enter image description here

如果您想使用自定义 Web api 自定义数据，那么 您使用下面的功能代码。

import azure.functions as func
import logging
import json
import base64

app = func.FunctionApp(http_auth_level=func.AuthLevel.ANONYMOUS)

@app.route(route="http_trigger1")
def http_trigger1(req: func.HttpRequest) -> func.HttpResponse:
    logging.info('Python HTTP trigger function processed a request.')

    values = req.get_json()['values']
    res=[]
    content = base64.b64decode(i['data']['normalized_images']['data']) #do whatever you want with this image.
    for i in values:
        tmp = i
        tmp['data'] = {
            "page_number": i['data']['normalized_images']['pageNumber']
        }
        res.append(tmp)

    return func.HttpResponse(json.dumps({"values":res}),mimetype="application/json")

有关结合标准化图像和自定义 Web api 的更多信息，请参阅 this。

最新问题
© www.soinside.com 2019 - 2024. All rights reserved.