시작
Kore.ai 대화형 플랫폼
챗봇 개요
자연어 처리(NLP)
봇 개념 및 용어들
빠른 시작 가이드
봇 빌더 접근 방법
사용 고지 사항 (영어)
Kore.ai 봇 빌더로 작업하기
봇 구축 시작하기
릴리스 정보
현재 버전 (영어)
이전 버전 (영어)

개념
디자인
스토리보드
대화 작업
개요
Using the Dialog Builder Tool
노드 유형
사용자 의도 노드
대화 노드
엔티티 노드
양식 노드
확인 노드
서비스 노드
봇 조치 노드
Service Node
WebHook 노드
스크립트 노드
노드 그룹화하기
Agent Transfer Node
사용자 프롬프트
음성 통화 속성
대화 관리
노드 및 전환
구성 요소 전환
컨텍스트 개체
이벤트 기반 봇 조치
지식 그래프
소개
지식 추출
지식 그래프 생성
봇에 지식 그래프 추가
그래프 생성
지식 그래프 작성
FAQ 추가
작업 실행
기존 소스에서 FAQ 구축
특성, 동의어 및 불용어
변수 네임스페이스 관리
수정
용어 편집 및 삭제
용어 편집 및 삭제
질문과 응답 편집
Knowledge Graph Training
지식 그래프 분석
봇 온톨로지 가져오기 및 내보내기
지식 그래프 가져오기
지식 그래프 내보내기
지식 그래프 생성
CSV 파일에서
JSON 파일
지식 그래프 생성
경고 작업
스몰 토크
Digital Skills
디지털 양식
Views
Digital Views
Panels
Widgets
기차
봇 성능 향상 – NLP 최적화
기계 학습
소개
모델 검증
기초 의미
지식 그래프 학습
특성
순위 및 해결
고급 NLP 설정
NLP 설정 및 지침
봇 인텔리전스
소개
컨텍스트 관리
컨텍스트 관리
대화 관리
다중 – 의도 탐지
엔티티 수정
기본 대화
정서 관리
어조 분석
Test & Debug
봇과 대화
발화 테스트
배치 테스트하기
대화 테스트
배포
채널 활성화
봇 게시
분석
봇 분석하기
Conversations Dashboard
Performance Dashboard
사용자 정의 대시보드
소개
맞춤형 메타 태그
사용자 정의 대시보드 생성 방법
Conversation Flows
NLP 지표
Containment Metrics
사용량 지표
스마트 봇
소개
범용 봇
소개
범용 봇 정의
범용 봇 생성
범용 봇 학습
범용 봇 커스터마이징
범용 봇용 추가 언어 활성화
스토어
Manage Assistant
플랜 및 사용량
Overview
Usage Plans
Support Plans
플랜 관리
봇 인증
다국어 봇
개인 식별 정보 삭제하기
봇 변수 사용
IVR 통합
일반 설정
봇 관리

방법
간단한 봇 생성하기
Design Conversation Skills
뱅킹 봇 생성
뱅킹 봇 – 자금 이체
뱅킹 봇 – 잔액 업데이트
Knowledge Graph (KG) 구축
스마트 경고를 예약하는 방법
Design Digital Skills
디지털 양식 설정 방법
디지털 보기 설정 방법
데이터 테이블에 데이터를 추가하는 방법
데이터 테이블 내 데이터 업데이트 방법
UI 양식에서 데이터 테이블에 데이터를 추가하는 방법
Train the Assistant
특성 사용 방법
의도와 엔티티에 대한 패턴 사용 방법
컨텍스트 전환 관리 방법
Deploy the Assistant
상담사 전환을 설정하는 방법
봇 기능 사용 방법
콘텐츠 변수 사용 방법
전역 변수 사용 방법
Kore.ai 웹 SDK 튜토리얼
Kore.ai 위젯 SDK 튜토리얼
Analyze the Assistant
사용자 정의 대시보드 생성 방법
사용자 지정 태그를 사용하여 봇 메트릭을 필터링하는 방법

API 및 SDK
API 참조
Kore.ai API 사용
API 목록
API 컬렉션
koreUtil Libraries
SDK 참조
상담사 전환을 설정하는 방법
봇 기능 사용 방법
콘텐츠 변수 사용 방법
전역 변수 사용 방법
소개
Kore.ai 웹 SDK 튜토리얼
Kore.ai 위젯 SDK 튜토리얼

관리
소개
봇 관리자 콘솔
대시보드
사용자 관리
사용자 관리
그룹 관리
역할 관리
봇 관리 모듈
등록
사용자 초대
사용자 등록을 위한 대량 초대 보내기
사용자 및 사용자 데이터 가져오기
Active Directory에서 사용자 동기화
보안 및 준수
싱글 사인 온 사용
보안 설정
Kore.ai 커넥터
봇 관리자용 분석
Billing (지원하지 않음)
  1. Docs
  2. Virtual Assistants
  3. API Guide
  4. LLM and Generative AI Usage Logs API

LLM and Generative AI Usage Logs API

This API lets you get the LLM & Generative AI Usage Logs for both Co-Pilot and Dynamic Conversation features.

Method POST
End Point https://{{host}}/api/1.1/public/bot/{{botId}}/getLLMUsageLogs
Content Type application/json
Authorization auth: {{JWT}}

See How to generate the JWT Token.

API Scope
  • Bot Builder: Fetch Gen AI and LLM Usage Logs
  • Admin Console: API Scopes > Gen AI and LLM Usage Logs

 

Note: You can access records spanning up to a 90-day timeframe with one request.

Query Parameters

Parameter Required/Optional Description
host Required The environment URL. For example, https://bots.kore.ai
botId Required Bot ID or Stream ID. You can access it from the General Settings page of the bot.

Sample Request

--header 'auth: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwiYXBwSWQiOiJjcy03ZWMxNmFjZS03ZGNmLTU3MjQtYjM5NS1hYTA4YmRmYTAwMzMifQ.n_Es9ZBsiCYzpzsfN4p4I1SlHK05gewJFyqAIngr4Qg' \
--header 'Content-Type: application/json' \
--data '{
    "dateFrom": "2024-03-07",
    "dateTo":"2024-03-09",
    "limit":"1",
    "skip" : "5",
    "isDeveloper": true,
    "channel" : "msteams",
    "featureName" : ["dynamicEntity"],
    "taskId" : "dg-d4924db4-b325-5b4d-ae51-aa5c7be41d4f",
    "channelUserIds":["29:1gmw8z03rvk6njl6k7ohtdh2v9zubxiip7kvu1yiek_qri4grpmd0k_d1yjlpzbj40wk1am9dphqkoiwatzwttw"],
    "userIds" : ["u-40b3eafc-a5aa-55f2-83e8-cf4d0fb1de07"],
    "sort" : {
        "field" : "Time Taken",
        "order" : "desc"
    }
}'

Body Parameters

Parameter Required/Optional Description
dateFrom Required The timestamp from which the records are displayed.
dateTo Required The timestamp till which the records are displayed.
limit Required The number of records to be displayed on each page.
channel Optional The channels to be considered for the metrics.
channelUIds Optional The user ids (channel specified) to be included in the metrics.
isDeveloper Optional To include developer metrics. Set to true or false.
taskId Optional To filter records based on the task ids.
userId Optional To filter records based on user id.
sort Optional To sort the results.

Sample Response

[
{
"Prompt Name": "Default",
"Integration": "OpenAI",
"start Date": "2024-03-08T06:38:54.008Z",
"End Date": "2024-03-08T06:38:58.386Z",
"Time Taken": 4378,
"statusCode": 200,
"Bot ID": "st-73bfdb2f-9101-55e6-b4c8-3f568a6ea8e0",
"User ID": "u-40b3eafc-a5aa-55f2-83e8-cf4d0fb1de07",
"Feature Name ": "GenAI Node",
"Model Name": "GPT-4",
"Channel Name": "msteams",
"Description": "Order pizza-GenAINode0002",
"task Id": "dg-200ad1ff-8db8-5219-810e-4ee3800d212c",
"Status": "Success",
"Payload Details": {
"Prompt Name": "Default",
"Request Payload": {
"model": "gpt-4",
"temperature": 0.5,
"max_tokens": 1500,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0,
"messages": [
{
"role": "system",
"content": "You are a virtual assistant representing an enterprise business, and so you have to act professionally at all times. You do not participate or respond to any abusive language or indulge in any conversation that does not represent enterprise business.\nAct like pizza ordering site. For the instructions that the user provides, you have to process the instructions. Here are the rules that you are supposed to follow: \nRule 0:\n Each pizza can only have maximum of 3 toppings \nRule 1:\n List of entities you need to capture from user are number of pizzas, toppings and size.. You need to capture all these entitites. \nRule 2:\n Capture entities from the user and the conversation history. \nRule 3:\n Collect the unfulfilled entities or check if the user wants to update a collected entity. \nRule 4:\n If user has provided the required value for any of the required entities, then do not prompt for it again. \nRule 5:\n Generate appropriate prompt to the end user to collect the information for the unfulfilled entities. \nRule 6:\n In the output return JSON must containing {\"bot\"://next prompt , \"analysis\"://Summarization of the entire conversation with all details.,\"entities\"://array of objects,\"conv_status\"://The status of the conversation. \"ongoing\" or \"ended\".} \nRule 7:\n When returning the result return a json, stringified and formatting removed. \nRule 8:\n Once all the entities details are captured generate conv_status as 'ended'. When the flow is to be continued, generate conv_status as 'ongoing'  \nRule 9:\n Keep the prompts and messages voice friendly. \nRule 10:\n If there are mutiple entities, return entitites in format of array of objects. Where each object is entity key values pairs. \nRule 11:\n Ignore any out of topic user/assistant conversations and always collect ALL the mentioned entities. \n\n "
},
{
"role": "user",
"content": "Order pizza"
},
{
"role": "assistant",
"content": "{\"bot\":\"Sure, I can help with that. How many pizzas would you like to order?\",\"analysis\":\"The user initiated the pizza ordering process but didn't provide any details.\",\"entities\":[],\"conv_status\":\"ongoing\"}"
},
{
"role": "user",
"content": "5"
},
{
"role": "assistant",
"content": "{\"bot\":\"Great, 5 pizzas it is. What size would you like these pizzas to be?\",\"analysis\":\"The user has ordered 5 pizzas but has not specified the size or toppings.\",\"entities\":[{\"number_of_pizzas\":\"5\"}],\"conv_status\":\"ongoing\"}"
},
{
"role": "user",
"content": "Medium Size"
},
{
"role": "assistant",
"content": "{\"bot\":\"Perfect, 5 medium-sized pizzas. Now, could you please specify the toppings for your pizzas? Remember, each pizza can have a maximum of 3 toppings.\",\"analysis\":\"The user has ordered 5 medium-sized pizzas but has not specified the toppings.\",\"entities\":[{\"number_of_pizzas\":\"5\"},{\"size\":\"Medium\"}],\"conv_status\":\"ongoing\"}"
},
{
"role": "user",
"content": "okay\n\n{"
}
]
},
"Response Payload": {
"id": "chatcmpl-90OAYDFFkbjgMxhMxKukwqklT6SWO",
"object": "chat.completion",
"created": 1709879934,
"model": "gpt-4-0613",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "{\"bot\":\"I'm sorry, but your message seems incomplete. Could you please specify the toppings for your pizzas? Remember, each pizza can have a maximum of 3 toppings.\",\"analysis\":\"The user's response was incomplete. The toppings for the pizzas are still needed.\",\"entities\":[{\"number_of_pizzas\":\"5\"},{\"size\":\"Medium\"}],\"conv_status\":\"ongoing\"}"
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 614,
"completion_tokens": 74,
"total_tokens": 688
},
"system_fingerprint": null
},
"Request Tokens": 614,
"Response Tokens": 74
}
}
]

LLM and Generative AI Usage Logs API

This API lets you get the LLM & Generative AI Usage Logs for both Co-Pilot and Dynamic Conversation features.

Method POST
End Point https://{{host}}/api/1.1/public/bot/{{botId}}/getLLMUsageLogs
Content Type application/json
Authorization auth: {{JWT}}

See How to generate the JWT Token.

API Scope
  • Bot Builder: Fetch Gen AI and LLM Usage Logs
  • Admin Console: API Scopes > Gen AI and LLM Usage Logs

 

Note: You can access records spanning up to a 90-day timeframe with one request.

Query Parameters

Parameter Required/Optional Description
host Required The environment URL. For example, https://bots.kore.ai
botId Required Bot ID or Stream ID. You can access it from the General Settings page of the bot.

Sample Request

--header 'auth: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwiYXBwSWQiOiJjcy03ZWMxNmFjZS03ZGNmLTU3MjQtYjM5NS1hYTA4YmRmYTAwMzMifQ.n_Es9ZBsiCYzpzsfN4p4I1SlHK05gewJFyqAIngr4Qg' \
--header 'Content-Type: application/json' \
--data '{
    "dateFrom": "2024-03-07",
    "dateTo":"2024-03-09",
    "limit":"1",
    "skip" : "5",
    "isDeveloper": true,
    "channel" : "msteams",
    "featureName" : ["dynamicEntity"],
    "taskId" : "dg-d4924db4-b325-5b4d-ae51-aa5c7be41d4f",
    "channelUserIds":["29:1gmw8z03rvk6njl6k7ohtdh2v9zubxiip7kvu1yiek_qri4grpmd0k_d1yjlpzbj40wk1am9dphqkoiwatzwttw"],
    "userIds" : ["u-40b3eafc-a5aa-55f2-83e8-cf4d0fb1de07"],
    "sort" : {
        "field" : "Time Taken",
        "order" : "desc"
    }
}'

Body Parameters

Parameter Required/Optional Description
dateFrom Required The timestamp from which the records are displayed.
dateTo Required The timestamp till which the records are displayed.
limit Required The number of records to be displayed on each page.
channel Optional The channels to be considered for the metrics.
channelUIds Optional The user ids (channel specified) to be included in the metrics.
isDeveloper Optional To include developer metrics. Set to true or false.
taskId Optional To filter records based on the task ids.
userId Optional To filter records based on user id.
sort Optional To sort the results.

Sample Response

[
{
"Prompt Name": "Default",
"Integration": "OpenAI",
"start Date": "2024-03-08T06:38:54.008Z",
"End Date": "2024-03-08T06:38:58.386Z",
"Time Taken": 4378,
"statusCode": 200,
"Bot ID": "st-73bfdb2f-9101-55e6-b4c8-3f568a6ea8e0",
"User ID": "u-40b3eafc-a5aa-55f2-83e8-cf4d0fb1de07",
"Feature Name ": "GenAI Node",
"Model Name": "GPT-4",
"Channel Name": "msteams",
"Description": "Order pizza-GenAINode0002",
"task Id": "dg-200ad1ff-8db8-5219-810e-4ee3800d212c",
"Status": "Success",
"Payload Details": {
"Prompt Name": "Default",
"Request Payload": {
"model": "gpt-4",
"temperature": 0.5,
"max_tokens": 1500,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0,
"messages": [
{
"role": "system",
"content": "You are a virtual assistant representing an enterprise business, and so you have to act professionally at all times. You do not participate or respond to any abusive language or indulge in any conversation that does not represent enterprise business.\nAct like pizza ordering site. For the instructions that the user provides, you have to process the instructions. Here are the rules that you are supposed to follow: \nRule 0:\n Each pizza can only have maximum of 3 toppings \nRule 1:\n List of entities you need to capture from user are number of pizzas, toppings and size.. You need to capture all these entitites. \nRule 2:\n Capture entities from the user and the conversation history. \nRule 3:\n Collect the unfulfilled entities or check if the user wants to update a collected entity. \nRule 4:\n If user has provided the required value for any of the required entities, then do not prompt for it again. \nRule 5:\n Generate appropriate prompt to the end user to collect the information for the unfulfilled entities. \nRule 6:\n In the output return JSON must containing {\"bot\"://next prompt , \"analysis\"://Summarization of the entire conversation with all details.,\"entities\"://array of objects,\"conv_status\"://The status of the conversation. \"ongoing\" or \"ended\".} \nRule 7:\n When returning the result return a json, stringified and formatting removed. \nRule 8:\n Once all the entities details are captured generate conv_status as 'ended'. When the flow is to be continued, generate conv_status as 'ongoing'  \nRule 9:\n Keep the prompts and messages voice friendly. \nRule 10:\n If there are mutiple entities, return entitites in format of array of objects. Where each object is entity key values pairs. \nRule 11:\n Ignore any out of topic user/assistant conversations and always collect ALL the mentioned entities. \n\n "
},
{
"role": "user",
"content": "Order pizza"
},
{
"role": "assistant",
"content": "{\"bot\":\"Sure, I can help with that. How many pizzas would you like to order?\",\"analysis\":\"The user initiated the pizza ordering process but didn't provide any details.\",\"entities\":[],\"conv_status\":\"ongoing\"}"
},
{
"role": "user",
"content": "5"
},
{
"role": "assistant",
"content": "{\"bot\":\"Great, 5 pizzas it is. What size would you like these pizzas to be?\",\"analysis\":\"The user has ordered 5 pizzas but has not specified the size or toppings.\",\"entities\":[{\"number_of_pizzas\":\"5\"}],\"conv_status\":\"ongoing\"}"
},
{
"role": "user",
"content": "Medium Size"
},
{
"role": "assistant",
"content": "{\"bot\":\"Perfect, 5 medium-sized pizzas. Now, could you please specify the toppings for your pizzas? Remember, each pizza can have a maximum of 3 toppings.\",\"analysis\":\"The user has ordered 5 medium-sized pizzas but has not specified the toppings.\",\"entities\":[{\"number_of_pizzas\":\"5\"},{\"size\":\"Medium\"}],\"conv_status\":\"ongoing\"}"
},
{
"role": "user",
"content": "okay\n\n{"
}
]
},
"Response Payload": {
"id": "chatcmpl-90OAYDFFkbjgMxhMxKukwqklT6SWO",
"object": "chat.completion",
"created": 1709879934,
"model": "gpt-4-0613",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "{\"bot\":\"I'm sorry, but your message seems incomplete. Could you please specify the toppings for your pizzas? Remember, each pizza can have a maximum of 3 toppings.\",\"analysis\":\"The user's response was incomplete. The toppings for the pizzas are still needed.\",\"entities\":[{\"number_of_pizzas\":\"5\"},{\"size\":\"Medium\"}],\"conv_status\":\"ongoing\"}"
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 614,
"completion_tokens": 74,
"total_tokens": 688
},
"system_fingerprint": null
},
"Request Tokens": 614,
"Response Tokens": 74
}
}
]
메뉴