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. Docs
  3. Virtual Assistants
  4. Natural Language
  5. LLM and Generative AI
  6. Prompts and Requests Library

Prompts and Requests Library

Effective prompts play a crucial role in enhancing response accuracy when interacting with LLMs. The new Prompts Library module empowers bot designers by allowing them to create and test suitable prompts for their specific use cases. It also displays all the newly added/custom and default request/prompt templates for the integrated models with their status as active or inactive. The default prompts are related to the pre-built models. However, you can import any default prompt, customize it, and use it for a pre-built and custom LLM model.

The post-processor for prompts allows designers to align LLM responses perfectly with Platform expectations. Designers can modify the LLM response to guarantee the correct behavior and high-quality interactions during runtime.

Note: Currently, the custom LLM integration and prompt creation are available only in English.

Pre-requisites

Before proceeding, ensure that you have successfully Integrated a Pre-built or Custom LLM. For more information, see LLM Integration.

How to add Prompts and Requests

To add a new prompt, follow the steps:

  1. Go to Build > Natural Language > Generative AI & LLM.

  2. On the top right corner of the Prompts and Requests Library section, click +Add New.
  3. Enter the prompt name. Select the feature and the respective model.

  4. The Configuration section consists of End-point URLs, Authentication, and Header values required to connect to a large language model. These are auto-populated based on the input provided while model integration and are not editable.

  5. In the Request section, you can either create a request from scratch or import the existing prompt from the Library to modify as needed.

    1. To import an existing prompt, do the following:
      1. Click Import from Prompts and Requests Library. All the newly added/custom prompts and prompts related to the pre-built LLM are displayed without integrating them.

      2. Select the Feature from the dropdown menu, select the Model, and select the Prompt from the dropdown menu. Hover over and click Preview Prompt to view the prompt before importing.
        Note: You have the flexibility to interchange a prompt designated for one feature with that of another, and vice versa.
      3. Click Confirm to get it imported into the JSON body.
    2. To create a prompt from scratch, click Start from scratch and enter the JSON request the LLM.

  6. Once you type the JSON, the Sample Context Values fields are displayed. Fill in the values and click Test.
  7. If the request values are correct, the response from the LLM is displayed. If not, an error message is displayed.

  8. In the Actual Response section, double-click the Key that should be used to generate the response path. For example, double-click the text key and click Save.

  9. The Response Path is displayed. Click Lookup Path.
  10. The Actual Response and Expected Response are displayed. 
    1. If the response structure matches, the responses will be in green. Click Save. Skip to Step 11.
      Note: Both Actual Response and Expected Response are not editable.

    2. If the response structure does not match, the responses will be in red. Click Configure to modify the Actual Response. The Post Processor Script is displayed.

      1. Enter the Post Processor Script. Click Save & Test.

      2. The response is displayed.

      3. Click Save. The actual response and expected response turn green.
  11. (Only for GenAI Node) Enter the Exit Scenario Key-Value fields and Virtual Assistance Response Key. The Exit Scenario Key-Value fields help identify when to end the interaction with the GenAI model and return to the dialog flow. A Virtual Assistance Response Key is available in the response payload to display the VA’s response to the user.
  12. Click Save. The request is added and displayed in the Prompts and Requests Library section.

  13. Now proceed to enable Co-Pilot Features and Dynamic Conversations features.

Prompts and Requests Library

Effective prompts play a crucial role in enhancing response accuracy when interacting with LLMs. The new Prompts Library module empowers bot designers by allowing them to create and test suitable prompts for their specific use cases. It also displays all the newly added/custom and default request/prompt templates for the integrated models with their status as active or inactive. The default prompts are related to the pre-built models. However, you can import any default prompt, customize it, and use it for a pre-built and custom LLM model.

The post-processor for prompts allows designers to align LLM responses perfectly with Platform expectations. Designers can modify the LLM response to guarantee the correct behavior and high-quality interactions during runtime.

Note: Currently, the custom LLM integration and prompt creation are available only in English.

Pre-requisites

Before proceeding, ensure that you have successfully Integrated a Pre-built or Custom LLM. For more information, see LLM Integration.

How to add Prompts and Requests

To add a new prompt, follow the steps:

  1. Go to Build > Natural Language > Generative AI & LLM.

  2. On the top right corner of the Prompts and Requests Library section, click +Add New.
  3. Enter the prompt name. Select the feature and the respective model.

  4. The Configuration section consists of End-point URLs, Authentication, and Header values required to connect to a large language model. These are auto-populated based on the input provided while model integration and are not editable.

  5. In the Request section, you can either create a request from scratch or import the existing prompt from the Library to modify as needed.

    1. To import an existing prompt, do the following:
      1. Click Import from Prompts and Requests Library. All the newly added/custom prompts and prompts related to the pre-built LLM are displayed without integrating them.

      2. Select the Feature from the dropdown menu, select the Model, and select the Prompt from the dropdown menu. Hover over and click Preview Prompt to view the prompt before importing.
        Note: You have the flexibility to interchange a prompt designated for one feature with that of another, and vice versa.
      3. Click Confirm to get it imported into the JSON body.
    2. To create a prompt from scratch, click Start from scratch and enter the JSON request the LLM.

  6. Once you type the JSON, the Sample Context Values fields are displayed. Fill in the values and click Test.
  7. If the request values are correct, the response from the LLM is displayed. If not, an error message is displayed.

  8. In the Actual Response section, double-click the Key that should be used to generate the response path. For example, double-click the text key and click Save.

  9. The Response Path is displayed. Click Lookup Path.
  10. The Actual Response and Expected Response are displayed. 
    1. If the response structure matches, the responses will be in green. Click Save. Skip to Step 11.
      Note: Both Actual Response and Expected Response are not editable.

    2. If the response structure does not match, the responses will be in red. Click Configure to modify the Actual Response. The Post Processor Script is displayed.

      1. Enter the Post Processor Script. Click Save & Test.

      2. The response is displayed.

      3. Click Save. The actual response and expected response turn green.
  11. (Only for GenAI Node) Enter the Exit Scenario Key-Value fields and Virtual Assistance Response Key. The Exit Scenario Key-Value fields help identify when to end the interaction with the GenAI model and return to the dialog flow. A Virtual Assistance Response Key is available in the response payload to display the VA’s response to the user.
  12. Click Save. The request is added and displayed in the Prompts and Requests Library section.

  13. Now proceed to enable Co-Pilot Features and Dynamic Conversations features.
メニュー