GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Help & Learning Resources
Release Notes
Current Version
Recent Updates
Previous Versions
Deprecations
Request a Feature
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Node Types
Overview
Intent Node
Dialog Node
Dynamic Intent Node
GenAI Node
GenAI Node (v2, BETA)
GenAI Prompt
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections
Node Connections Setup
Sub-Intent Scoping
Entity Types
Entity Rules
User Prompts or Messages
Voice Call Properties
Knowledge AI
Introduction
Knowledge Graph
Introduction
Terminology
Build a Knowledge Graph
Manage FAQs
Knowledge Extraction
Import or Export Knowledge Graph
Prepare Data for Import
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Knowledge Graph Analysis
Answer from Documents
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Intent Discovery
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Guardrails
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentiment Management
Tone Analysis
Default Standard Responses
Ignore Words & Field Memory
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Conversation Testing Overview
Create a Test Suite
Test Editor
Test Case Assertion
Test Case Execution Summary
Glossary
Health and Monitoring
NLP Health
Flow Health
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
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Dashboard Filters
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
Create Custom Dashboard Filters
LLM and Generative AI Logs
NLP Insights
Task Execution Logs
Conversations History
Conversation Flows
Conversation Insights
Feedback Analytics
Usage Metrics
Containment Metrics
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Team Collaboration
Plan & Usage
Overview
Usage Plans
Templates
Support Plans
Invoices
Authorization
Conversation Sessions
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Feedback Survey
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data
Overview
Guidelines
Data Table
Table Views
App Definitions
Data as Service
HOW TOs
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
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Composite Entities
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Intent Scoping using Group Node
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters
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
Installing Botkit in AWS
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer

ADMINISTRATION
Intro to Bots Admin Console
Administration Dashboard
User Management
Managing Your Users
Managing Your Groups
Role Management
Manage Data Tables and Views
Bot Management
Enrollment
Inviting Users
Sending Bulk Invites to Enroll Users
Importing Users and User Data
Synchronizing Users from Active Directory
Security & Compliance
Using Single Sign-On
Two-Factor Authentication for Platform Access
Security Settings
Cloud Connector
Analytics for Bots Admin
Billing
  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