Tutorial: Memulai Menggunakan Amazon A2I API

Untuk mempelajari lebih lanjut tentang template ini, lihatContoh Template Kustom untuk Amazon Texttract.

template = r"""
<script src="https://assets.crowd.aws/crowd-html-elements.js"></script>
{% capture s3_uri %}http://s3.amazonaws.com/{{ task.input.aiServiceRequest.document.s3Object.bucket }}/{{ task.input.aiServiceRequest.document.s3Object.name }}{% endcapture %}
<crowd-form>
  <crowd-textract-analyze-document 
      src="{{ s3_uri | grant_read_access }}" 
      initial-value="{{ task.input.selectedAiServiceResponse.blocks }}" 
      header="Review the key-value pairs listed on the right and correct them if they don"t match the following document." 
      no-key-edit="" 
      no-geometry-edit="" 
      keys="{{ task.input.humanLoopContext.importantFormKeys }}" 
      block-types='["KEY_VALUE_SET"]'>
    <short-instructions header="Instructions">
        <p>Click on a key-value block to highlight the corresponding key-value pair in the document.
        </p><p><br></p>
        <p>If it is a valid key-value pair, review the content for the value. If the content is incorrect, correct it.
        </p><p><br></p>
        <p>The text of the value is incorrect, correct it.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/correct-value-text.png">
        </p><p><br></p>
        <p>A wrong value is identified, correct it.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/correct-value.png">
        </p><p><br></p>
        <p>If it is not a valid key-value relationship, choose No.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/not-a-key-value-pair.png">
        </p><p><br></p>
        <p>If you can’t find the key in the document, choose Key not found.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/key-is-not-found.png">
        </p><p><br></p>
        <p>If the content of a field is empty, choose Value is blank.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/value-is-blank.png">
        </p><p><br></p>
        <p><strong>Examples</strong></p>
        <p>Key and value are often displayed next or below to each other.
        </p><p><br></p>
        <p>Key and value displayed in one line.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/sample-key-value-pair-1.png">
        </p><p><br></p>
        <p>Key and value displayed in two lines.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/sample-key-value-pair-2.png">
        </p><p><br></p>
        <p>If the content of the value has multiple lines, enter all the text without line break. 
        Include all value text even if it extends beyond the highlight box.</p>
        <p><img src="https://assets.crowd.aws/images/a2i-console/multiple-lines.png"></p>
    </short-instructions>
    <full-instructions header="Instructions"></full-instructions>
  </crowd-textract-analyze-document>
</crowd-form>
"""

Untuk mempelajari lebih lanjut tentang template ini, lihatContoh Template Kustom untuk Amazon Rekognition.

template = r"""
<script src="https://assets.crowd.aws/crowd-html-elements.js"></script>
{% capture s3_uri %}http://s3.amazonaws.com/{{ task.input.aiServiceRequest.image.s3Object.bucket }}/{{ task.input.aiServiceRequest.image.s3Object.name }}{% endcapture %}

<crowd-form>
  <crowd-rekognition-detect-moderation-labels
    categories='[
      {% for label in task.input.selectedAiServiceResponse.moderationLabels %}
        {
          name: "{{ label.name }}",
          parentName: "{{ label.parentName }}",
        },
      {% endfor %}
    ]'
    src="{{ s3_uri | grant_read_access }}"
    header="Review the image and choose all applicable categories."
  >
    <short-instructions header="Instructions">
      <style>
        .instructions {
          white-space: pre-wrap;
        }
      </style>
      <p class="instructions">Review the image and choose all applicable categories.
If no categories apply, choose None.

<b>Nudity</b>
Visuals depicting nude male or female person or persons

<b>Partial Nudity</b>
Visuals depicting covered up nudity, for example using hands or pose

<b>Revealing Clothes</b>
Visuals depicting revealing clothes and poses

<b>Physical Violence</b>
Visuals depicting violent physical assault, such as kicking or punching

<b>Weapon Violence</b>
Visuals depicting violence using weapons like firearms or blades, such as shooting

<b>Weapons</b>
Visuals depicting weapons like firearms and blades
    </short-instructions>

    <full-instructions header="Instructions"></full-instructions>
  </crowd-rekognition-detect-moderation-labels>
</crowd-form>"""

Berikut ini adalah contoh template yang dapat digunakan dalam integrasi kustom. Template ini digunakan dalam notebook ini, menunjukkan integrasi kustom dengan Amazon Comprehend.

template = r"""
<script src="https://assets.crowd.aws/crowd-html-elements.js"></script>

<crowd-form>
    <crowd-classifier
      name="sentiment"
      categories='["Positive", "Negative", "Neutral", "Mixed"]'
      initial-value="{{ task.input.initialValue }}"
      header="What sentiment does this text convey?"
    >
      <classification-target>
        {{ task.input.taskObject }}
      </classification-target>
      
      <full-instructions header="Sentiment Analysis Instructions">
        <p><strong>Positive</strong> sentiment include: joy, excitement, delight</p>
        <p><strong>Negative</strong> sentiment include: anger, sarcasm, anxiety</p>
        <p><strong>Neutral</strong>: neither positive or negative, such as stating a fact</p>
        <p><strong>Mixed</strong>: when the sentiment is mixed</p>
      </full-instructions>

      <short-instructions>
       Choose the primary sentiment that is expressed by the text. 
      </short-instructions>
    </crowd-classifier>
</crowd-form>
"""

Contoh ini menentukan kondisi untuk kunci tertentu (sepertiMail address) dalam dokumen. Jika kepercayaan Amazon Textract berada di luar ambang batas yang ditetapkan di sini, dokumen dikirim ke manusia untuk ditinjau, dengan kunci spesifik yang memulai loop manusia diminta ke pekerja.

      import json  

      humanLoopActivationConditions = json.dumps(
        {
            "Conditions": [
                {
                  "Or": [
                    
                    {
                        "ConditionType": "ImportantFormKeyConfidenceCheck",
                        "ConditionParameters": {
                            "ImportantFormKey": "Mail address",
                            "ImportantFormKeyAliases": ["Mail Address:","Mail address:", "Mailing Add:","Mailing Addresses"],
                            "KeyValueBlockConfidenceLessThan": 100,
                            "WordBlockConfidenceLessThan": 100
                        }
                    },
                    {
                        "ConditionType": "MissingImportantFormKey",
                        "ConditionParameters": {
                            "ImportantFormKey": "Mail address",
                            "ImportantFormKeyAliases": ["Mail Address:","Mail address:","Mailing Add:","Mailing Addresses"]
                        }
                    },
                    {
                        "ConditionType": "ImportantFormKeyConfidenceCheck",
                        "ConditionParameters": {
                            "ImportantFormKey": "Phone Number",
                            "ImportantFormKeyAliases": ["Phone number:", "Phone No.:", "Number:"],
                            "KeyValueBlockConfidenceLessThan": 100,
                            "WordBlockConfidenceLessThan": 100
                        }
                    },
                    {
                      "ConditionType": "ImportantFormKeyConfidenceCheck",
                      "ConditionParameters": {
                        "ImportantFormKey": "*",
                        "KeyValueBlockConfidenceLessThan": 100,
                        "WordBlockConfidenceLessThan": 100
                      }
                    },
                    {
                      "ConditionType": "ImportantFormKeyConfidenceCheck",
                      "ConditionParameters": {
                        "ImportantFormKey": "*",
                        "KeyValueBlockConfidenceGreaterThan": 0,
                        "WordBlockConfidenceGreaterThan": 0
                      }
                    }
            ]
        }
            ]
        }
    )

Kondisi aktivasi loop manusia yang digunakan di sini disesuaikan dengan moderasi konten Rekognition Amazon; mereka didasarkan pada ambang Suggestive kepercayaan untuk label dan moderasi. Female Swimwear Or Underwear

        import json  

        humanLoopActivationConditions = json.dumps(
        {
            "Conditions": [
                {
                  "Or": [
                    {
                        "ConditionType": "ModerationLabelConfidenceCheck",
                        "ConditionParameters": {
                            "ModerationLabelName": "Suggestive",
                            "ConfidenceLessThan": 98
                        }
                    },
                    {
                        "ConditionType": "ModerationLabelConfidenceCheck",
                        "ConditionParameters": {
                            "ModerationLabelName": "Female Swimwear Or Underwear",
                            "ConfidenceGreaterThan": 98
                        }
                    }
                  ]
               }
            ]
        }
    )

Jika Anda menggunakan integrasi bawaan dengan Amazon Textract, Anda harus menentukan "AWS/Textract/AnalyzeDocument/Forms/V1" untuk "AwsManagedHumanLoopRequestSource" in. HumanLoopRequestSource

    response = client.create_flow_definition(
        FlowDefinitionName="human-review-workflow-name",
        HumanLoopRequestSource={
            "AwsManagedHumanLoopRequestSource": "AWS/Textract/AnalyzeDocument/Forms/V1"
        }, 
        HumanLoopActivationConfig={
            "HumanLoopActivationConditionsConfig": {
                "HumanLoopActivationConditions": humanLoopActivationConditions
            }
        },
        HumanLoopConfig={
            "WorkteamArn": workteamArn,
            "HumanTaskUiArn": humanTaskUiArn,
            "TaskTitle": "Document entry review",
            "TaskDescription": "Review the document and instructions. Complete the task",
            "TaskCount": 1,
            "TaskAvailabilityLifetimeInSeconds": 43200,
            "TaskTimeLimitInSeconds": 3600,
            "TaskKeywords": [
                "document review",
            ],
        },
        OutputConfig={
            "S3OutputPath": "s3://DOC-EXAMPLE-BUCKET/prefix/",
        },
        RoleArn="arn:aws:iam::<account-number>:role/<role-name>",
        Tags=[
            {
                "Key": "string",
                "Value": "string"
            },
        ]
    )

Jika Anda menggunakan integrasi bawaan dengan Amazon Rekognition, Anda harus "AWS/Rekognition/DetectModerationLabels/Image/V3" menentukan untuk di. "AwsManagedHumanLoopRequestSource" HumanLoopRequestSource

    response = client.create_flow_definition(
        FlowDefinitionName="human-review-workflow-name",
        HumanLoopRequestSource={
            "AwsManagedHumanLoopRequestSource": "AWS/Rekognition/DetectModerationLabels/Image/V3"
        }, 
        HumanLoopActivationConfig={
            "HumanLoopActivationConditionsConfig": {
                "HumanLoopActivationConditions": humanLoopActivationConditions
            }
        },
        HumanLoopConfig={
            "WorkteamArn": workteamArn,
            "HumanTaskUiArn": humanTaskUiArn,
            "TaskTitle": "Image content moderation",
            "TaskDescription": "Review the image and instructions. Complete the task",
            "TaskCount": 1,
            "TaskAvailabilityLifetimeInSeconds": 43200,
            "TaskTimeLimitInSeconds": 3600,
            "TaskKeywords": [
                "content moderation",
            ],
        },
        OutputConfig={
            "S3OutputPath": "s3://DOC-EXAMPLE-BUCKET/prefix/",
        },
        RoleArn="arn:aws:iam::<account-number>:role/<role-name>",
        Tags=[
            {
                "Key": "string",
                "Value": "string"
            },
        ]
    )

Jika Anda menggunakan integrasi kustom, kecualikan parameter berikut:HumanLoopRequestSource,HumanLoopActivationConfig.

    response = client.create_flow_definition(
        FlowDefinitionName="human-review-workflow-name",
        HumanLoopConfig={
            "WorkteamArn": workteamArn,
            "HumanTaskUiArn": humanTaskUiArn,
            "TaskTitle": "Image content moderation",
            "TaskDescription": "Review the image and instructions. Complete the task",
            "TaskCount": 1,
            "TaskAvailabilityLifetimeInSeconds": 43200,
            "TaskTimeLimitInSeconds": 3600,
            "TaskKeywords": [
                "content moderation",
            ],
        },
        OutputConfig={
            "S3OutputPath": "s3://DOC-EXAMPLE-BUCKET/prefix/",
        },
        RoleArn="arn:aws:iam::<account-number>:role/<role-name>",
        Tags=[
            {
                "Key": "string",
                "Value": "string"
            },
        ]
    )

Contoh berikut menggunakan AWS SDK for Python (Boto3) to call analyze_document in us-west-2. Ganti teks merah yang dicetak miring dengan sumber daya Anda. Sertakan DataAttributesparameter jika Anda menggunakan tenaga kerja Amazon Mechanical Turk. Untuk informasi selengkapnya, lihat dokumen analyze_document di Referensi API.AWS SDK for Python (Boto)

   response = client.analyze_document(
         Document={"S3Object": {"Bucket": "AWSDOC-EXAMPLE-BUCKET", "Name": "document-name.pdf"},
         HumanLoopConfig={
            "FlowDefinitionArn":"arn:aws:sagemaker:us-west-2:111122223333:flow-definition/flow-definition-name",
            "HumanLoopName":"human-loop-name",
            "DataAttributes" : {ContentClassifiers:["FreeOfPersonallyIdentifiableInformation"|"FreeOfAdultContent"]}
         }
         FeatureTypes=["FORMS"]
    )

Loop manusia hanya dibuat jika kepercayaan Amazon Texact untuk tugas analisis dokumen memenuhi kondisi aktivasi yang Anda tentukan dalam alur kerja tinjauan manusia Anda. Anda dapat memeriksa response elemen untuk menentukan apakah loop manusia telah dibuat. Untuk melihat semua yang termasuk dalam tanggapan ini, lihat HumanLoopActivationOutput.

    if "HumanLoopArn" in analyzeDocumentResponse["HumanLoopActivationOutput"]:
        # A human loop has been started!
        print(f"A human loop has been started with ARN: {analyzeDocumentResponse["HumanLoopActivationOutput"]["HumanLoopArn"]}"

Contoh berikut menggunakan AWS SDK for Python (Boto3) to call detect_moderation_labels in us-west-2. Ganti teks merah yang dicetak miring dengan sumber daya Anda. Sertakan DataAttributesparameter jika Anda menggunakan tenaga kerja Amazon Mechanical Turk. Untuk informasi selengkapnya, lihat dokumen detect_moderation_labels di Referensi API.AWS SDK for Python (Boto)

   response = client.detect_moderation_labels(
            Image={"S3Object":{"Bucket": "AWSDOC-EXAMPLE-BUCKET", "Name": "image-name.png"}},
            HumanLoopConfig={
               "FlowDefinitionArn":"arn:aws:sagemaker:us-west-2:111122223333:flow-definition/flow-definition-name",
               "HumanLoopName":"human-loop-name",
               "DataAttributes":{ContentClassifiers:["FreeOfPersonallyIdentifiableInformation"|"FreeOfAdultContent"]}
             }
    )

Loop manusia hanya dibuat jika kepercayaan Amazon Rekognition untuk tugas moderasi gambar memenuhi kondisi aktivasi yang Anda tentukan dalam alur kerja tinjauan manusia Anda. Anda dapat memeriksa response elemen untuk menentukan apakah loop manusia telah dibuat. Untuk melihat semua yang termasuk dalam tanggapan ini, lihat HumanLoopActivationOutput.

    if "HumanLoopArn" in response["HumanLoopActivationOutput"]:
        # A human loop has been started!
        print(f"A human loop has been started with ARN: {response["HumanLoopActivationOutput"]["HumanLoopArn"]}")

Contoh berikut menggunakan AWS SDK for Python (Boto3) to call start_human_loop in us-west-2. Ganti teks merah yang dicetak miring dengan sumber daya Anda. Sertakan DataAttributesparameter jika Anda menggunakan tenaga kerja Amazon Mechanical Turk. Untuk informasi selengkapnya, lihat dokumen start_human_loop di Referensi API.AWS SDK for Python (Boto)

   response = client.start_human_loop(
        HumanLoopName= "human-loop-name",
        FlowDefinitionArn= "arn:aws:sagemaker:us-west-2:111122223333:flow-definition/flow-definition-name",
        HumanLoopInput={"InputContent": inputContentJson},
        DataAttributes={"ContentClassifiers":["FreeOfPersonallyIdentifiableInformation"|"FreeOfAdultContent"]}
   )

Contoh ini menyimpan konten input dalam variabel inputContentJson. Asumsikan bahwa konten input berisi dua elemen: uraian teks dan sentimen (sepertiPositive,, atauNeutral)Negative, dan diformat sebagai berikut:

    inputContent = {
        "initialValue": sentiment,
         "taskObject": blurb
     }

Kunci initialValue dan taskObject harus sesuai dengan kunci yang digunakan dalam elemen cair dari template tugas pekerja. Lihat template kustom Buat UI Tugas Manusia untuk melihat contoh.

Untuk membuatinputContentJson, lakukan hal berikut:

    import json
    
    inputContentJson = json.dumps(inputContent)

Lingkaran manusia dimulai setiap kali Anda meneleponstart_human_loop. Untuk memeriksa status loop manusia Anda, gunakan describe_human_loop:

    human_loop_info = a2i.describe_human_loop(HumanLoopName="human_loop_name")
    print(f"HumanLoop Status: {resp["HumanLoopStatus"]}")
    print(f"HumanLoop Output Destination: {resp["HumanLoopOutput"]}")