はじめに
対話型AIプラットフォーム
チャットボットの概要
自然言語処理(NLP)
ボットの概念と用語
クイックスタートガイド
プラットフォームへのアクセス
ボットビルダーの操作
リリースノート
最新バージョン(英語)
以前のバージョン(英語)
廃止機能(英語)
コンセプト
設計
ストーリーボード
ダイアログタスク
ダイアログタスクとは
ダイアログビルダー
ノードタイプ
インテントノード
ダイアログノード
エンティティノード
フォームノード
確認ノード
ロジックノード
ボットアクションノード
サービスノード
Webhookノード
スクリプトノード
グループノード
エージェント転送ノード
ユーザープロンプト
音声通話プロパティ
イベント ハンドラー
ナレッジグラフ
ナレッジグラフの抽出
ナレッジグラフの構築
ボットにナレッジグラフを追加
グラフの作成
ナレッジグラフの構築
既存のソースからFAQを構築
通知タスク
スモールトーク
デジタルスキル
デジタルフォーム
デジタルビュー
デジタルビューとは
パネル
ウィジェット
トレーニング
トレーニングとは
機械学習
機械学習とは
モデル検証
ファンダメンタルミーニング
ナレッジグラフ
示唆
ランキングおよび解決
NLPの詳細設定
NLPのガイドライン
インテリジェンス
インテリジェンスとは
コンテキスト
コンテキストインテント
割り込み
複数インテントの検出
エンティティの変更
デフォルトの会話
センチメント管理
トーン分析
テストとデバッグ
ボットと会話
発話テスト
バッチテスト
会話テスト
デプロイ
チャネル
公開
分析
ボットの分析
NLPメトリクス
会話フロー
Usage Metrics
封じ込め測定
カスタムダッシュボード
カスタムダッシュボードとは
メタタグ
カスタムダッシュボードとウィジェット
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
ユニバーサルボット
ユニバーサルボットとは
ユニバーサルボットの定義
ユニバーサルボットの作成
ユニバーサルボットのトレーニング
ユニバーサルボットのカスタマイズ
他言語の有効化
ストア
プラントと使用
Overview
Usage Plans
Support Plans
Invoices
管理
ボット認証
複数言語対応ボット
個人を特定できる情報の編集
ボット変数の使用
IVRのシステム連携
一般設定
ボット管理
ハウツー
会話スキルの設計
バンキングボットを作成
バンキングボット – 資金の振り替え
バンキングボット – 残高を更新
ナレッジグラフを構築
スマートアラートの予約方法
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
デジタルスキルの設計
デジタルフォームの設定方法
デジタルビューの設定方法
データテーブルのデータの追加方法
データテーブルのデータの更新方法
Add Data from Digital Forms
ボットのトレーニング
示唆の使用方法
インテントとエンティティのパターンの使用方法
コンテキスト切り替えの管理方法
ボットのデプロイ
エージェント転送の設定方法
ボット関数の使用方法
コンテンツ変数の使用方法
グローバル変数の使用方法
ボットの分析
カスタムダッシュボードの作成方法
カスタムタグを使ってフィルタリング
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
  1. ホーム
  2. Integrations
  3. Using the Azure OpenAI Action Templates

Using the Azure OpenAI Action Templates

You can use the Prebuilt Action Templates from your Azure OpenAI integration to auto-create dialog tasks and test them using the Talk to Bot option.

Steps to create a dialog task using the Azure OpenAI action templates:

  1. Go to Build > Conversation Skills > Dialog Tasks.
  2. Click Create a Dialog Task.
  3. On the Dialog Task pop-up, under the Integration, select the Azure OpenAI option to view the action templates.
  4. If you have not configured any integration for your virtual assistant, you will see the Explore Integrations option. Once you click this option, you will be redirected to the Actions page to configure an integration for your VA. For more information, see Actions Overview.

Azure OpenAI Actions

The following Azure OpenAI action is supported:

Supported Tasks Description Method
General Query Resolve any query using the intelligence of Azure and OpenAI. POST

General Query

Steps to resolve the query in the Azure OpenAI integration:

  1. Refer to the Installing the Azure OpenAI Action Templates section to install this template.
  2. The General Query dialog task is added with the following components:
    • generalQuery: A user intent for a general query.
    • userQuestion and deploymentID – Entity nodes pass a user’s question.
    • generalQueryService – A bot action service to send a query in an external integration. Click the Plus icon to expand to view the generalQueryService bot action component properties.
    • In the Component Properties window, click the Edit Request link to edit the request parameters, as shown below:

      Sample Request

      {
      "prompt": "I am the owner of a SAAS product company. How can i increase my customer base?",
      "temperature": 0.25,
      "max_tokens": 1024,
      "top_p": 1,
      "frequency_penalty": 0,
      "presence_penalty": 0
      }

      To add one or more response, scroll down and click the +Add Response button:
      Sample Response

      {
      "id": "cmpl-6s8YPFcRGYrDtPys2OdVfxxxxxx",
      "object": "text_completion",
      "created": 1678360613,
      "model": "text-davinci-003",
      "choices": [
      {
      "text": "\n\n1. Focus on creating a great user experience: Make sure your product is easy to use, intuitive, and provides value to your customers.\n\n2. Offer free trials: Give potential customers the opportunity to try out your product before committing to a purchase.\n\n3. Leverage word-of-mouth marketing: Ask existing customers to share their experiences with their friends and family.\n\n4. Invest in content marketing: Create helpful content related to your product and share it on social media and other platforms.\n\n5. Utilize search engine optimization (SEO): Optimize your website and content for search engines to increase visibility and attract more customers.\n\n6. Run targeted ads: Use paid advertising to reach potential customers who are likely to be interested in your product.\n\n7. Participate in industry events: Attend conferences, trade shows, and other events to network and build relationships with potential customers.\n\n8. Offer discounts and promotions: Provide discounts and other promotions to encourage customers to purchase your product.",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop"
      }
      ],
      "usage": {
      "prompt_tokens": 19,
      "completion_tokens": 212,
      "total_tokens": 231
      }
      }
    • generalQueryMessage – A message node with the script to display the query in Azure OpenAI system.
  3. Click the Train tab to complete the Dialog task training.
  4. Click the Talk to Bot icon to test and debug the dialog task.
  5. Follow the prompts in the VA console to resolve a general query.
  6. Enter a question based on a query when prompted by the VA, as shown below:
  7. You will notice an answer is generated for your query.

このページの内容

Using the Azure OpenAI Action Templates

You can use the Prebuilt Action Templates from your Azure OpenAI integration to auto-create dialog tasks and test them using the Talk to Bot option.

Steps to create a dialog task using the Azure OpenAI action templates:

  1. Go to Build > Conversation Skills > Dialog Tasks.
  2. Click Create a Dialog Task.
  3. On the Dialog Task pop-up, under the Integration, select the Azure OpenAI option to view the action templates.
  4. If you have not configured any integration for your virtual assistant, you will see the Explore Integrations option. Once you click this option, you will be redirected to the Actions page to configure an integration for your VA. For more information, see Actions Overview.

Azure OpenAI Actions

The following Azure OpenAI action is supported:

Supported Tasks Description Method
General Query Resolve any query using the intelligence of Azure and OpenAI. POST

General Query

Steps to resolve the query in the Azure OpenAI integration:

  1. Refer to the Installing the Azure OpenAI Action Templates section to install this template.
  2. The General Query dialog task is added with the following components:
    • generalQuery: A user intent for a general query.
    • userQuestion and deploymentID – Entity nodes pass a user’s question.
    • generalQueryService – A bot action service to send a query in an external integration. Click the Plus icon to expand to view the generalQueryService bot action component properties.
    • In the Component Properties window, click the Edit Request link to edit the request parameters, as shown below:

      Sample Request

      {
      "prompt": "I am the owner of a SAAS product company. How can i increase my customer base?",
      "temperature": 0.25,
      "max_tokens": 1024,
      "top_p": 1,
      "frequency_penalty": 0,
      "presence_penalty": 0
      }

      To add one or more response, scroll down and click the +Add Response button:
      Sample Response

      {
      "id": "cmpl-6s8YPFcRGYrDtPys2OdVfxxxxxx",
      "object": "text_completion",
      "created": 1678360613,
      "model": "text-davinci-003",
      "choices": [
      {
      "text": "\n\n1. Focus on creating a great user experience: Make sure your product is easy to use, intuitive, and provides value to your customers.\n\n2. Offer free trials: Give potential customers the opportunity to try out your product before committing to a purchase.\n\n3. Leverage word-of-mouth marketing: Ask existing customers to share their experiences with their friends and family.\n\n4. Invest in content marketing: Create helpful content related to your product and share it on social media and other platforms.\n\n5. Utilize search engine optimization (SEO): Optimize your website and content for search engines to increase visibility and attract more customers.\n\n6. Run targeted ads: Use paid advertising to reach potential customers who are likely to be interested in your product.\n\n7. Participate in industry events: Attend conferences, trade shows, and other events to network and build relationships with potential customers.\n\n8. Offer discounts and promotions: Provide discounts and other promotions to encourage customers to purchase your product.",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop"
      }
      ],
      "usage": {
      "prompt_tokens": 19,
      "completion_tokens": 212,
      "total_tokens": 231
      }
      }
    • generalQueryMessage – A message node with the script to display the query in Azure OpenAI system.
  3. Click the Train tab to complete the Dialog task training.
  4. Click the Talk to Bot icon to test and debug the dialog task.
  5. Follow the prompts in the VA console to resolve a general query.
  6. Enter a question based on a query when prompted by the VA, as shown below:
  7. You will notice an answer is generated for your query.
メニュー