LogoLogo
DialoX Manual
DialoX Manual
  • Start
    • News
    • Getting Started
    • Ordering
    • Signup
    • Switcher
  • STORE
    • Marketplace Apps
      • Level 1 - Basic
        • Callback Note Basic
        • On-call Router Basic
        • Smart Group Voicemail
        • Smart IVR Basic
        • SMS Call Deflector
        • Survey Basic
      • Level 2 - Advanced
        • Call Deflector
        • Callback Note
        • Order Assistant
        • Smart IVR
        • Survey
        • Website Chat
      • Level 3 - Professional
        • Callback Planner
        • Appointment Planner
    • Legacy Apps
      • Survey Extension
      • Smart IVR Basic
      • Smart IVR 2.0
      • Whatsapp Calldeflector 1.0
      • Whatsapp Calldeflector 2.0
      • Social Inbox 1.0
      • Social Inbox 2.0
      • Basic Group Voicemail
      • Group Voicemail
      • Oncall Assistant
      • Web App
      • Basic Callback Note
      • Callback Note
      • Callback Planner
      • Caller Based Router
    • Skills
      • Base flows
      • Platform defaults
      • Phone flows
      • Chat flows
      • Web flows
      • LLM Flows
      • LLM Knowledge base
      • Address Flows
      • Email flows
      • Timeplans
        • How to add a flow for lunch breaks
      • On-call schedule
      • Planner
      • OAuth Flows
      • Integrations
        • Zendesk
        • Jira
        • Hubspot
  • SETTINGS
    • User Settings
      • Availability settings
      • Profile settings
      • Security
    • App Settings
      • App identity
      • Opening hours
      • Tags
      • Studio
      • Extra options
      • Backups
  • Inbox
    • Inbox
      • Assigning
      • Joining and leaving
      • Sending messages
      • Canned responses
      • Team chat
      • Watching
      • Close
      • Filter conversations
      • Multiple inboxes
    • Contacts
    • Notes
    • Today
    • Notifications
      • Notification panel
      • Notification preferences
      • Rules for notification
      • Chrome and Windows settings
      • Microsoft Teams notifications
  • Studio
    • Home
      • Customer settings
        • Settings
        • Advanced settings
        • Store settings
      • Audit Log
      • Access Request
    • Dashboard
    • Flows
      • Playbook
      • Triggers
      • Variables
      • Conditions
      • Tags
      • Languages
      • Links
      • Nodes
        • Say
        • Ask: Open
        • Ask: Choice
        • Ask: Single
        • Ask: Date
        • Ask: Name
        • Ask: Phone
        • Ask: Email
        • Ask: Form
        • Ask: Language
        • Ask: Selection
        • Ask: Time
        • Ask: Audio
        • Ask: Number
        • Ask: Custom entity
        • Ask: Address
        • Ask: Zipcode
        • Iterate
        • Iterate: LLM
        • Say: LLM
        • Say: LLM Knowledgebase
        • Iterate: LLM Knowledgebase
        • Iterate: continue
        • Show: audio
        • Show: whatsapp link
        • Show: image
        • Show: video
        • Show: file
        • Show: location
        • Control flow: branch
        • Control flow: go to flow
        • Control flow: switch language
        • Control flow: close
        • Control flow: restart
        • Control flow: pause
        • Control flow: invoke dialog
        • Dial: number
        • Dial: smart
        • Send: note
        • Send: email
        • Send: SMS
        • Send: whatsapp
        • Escalate: default
        • Escalate: smart
        • Perform: create jira ticket
        • Perform: get jira ticket
        • Plan
    • AI
      • Intents
        • LLM Intents
        • Q&A Intents
      • Knowledge bases
      • Prompts
    • Channels
      • Chatwidget
      • Whatsapp
        • How to integrate Whatsapp
        • How to change my Whatsapp profile
        • How to manage Whatsapp templates
        • How to send Whatsapp template with documents
        • How to automate outbound Whatsapp
        • How to send Whatsapp template
        • How to use Commerce Catalog
        • Whatsapp for Business
      • MS Teams
        • How to migrate new Version
        • How to change channel connection
      • Facebook Messenger
      • Phone
      • Progressive Web App (PWA)
    • Content
      • Nudges
      • Whatsapp optout
      • Voice lexicon
      • FAQs
      • Calendars
    • Visitors
    • Calendars
    • Campaigns
    • Conversations
    • Notes
    • Contacts
  • ADMINISTRATION
    • Organisation
    • Bots
    • Licenses
    • Channels
    • Orders
    • Usage
    • Users
    • Access Requests
    • Analytics
  • DESKTOP
    • Enreach Contact Desktop
  • FAQ
    • Studio
      • How to Publish
      • How to make 2FA Required
      • How to add additional columns to contactlist
      • Conversation retention time
      • How to help the bot pronounce phone numbers correctly
      • How to help the bot pronounce loose numbers correctly
    • Flow Topics
      • Skipping step based on language tag
      • Switching language using intent trigger
    • Meta
      • How to get Meta Business Suite Verification
      • How to connect Facebook page to Facebook Business Account
    • 360Dialog
      • How to give permission API access
      • How do I change my profile in 360Dialog
      • How to make 360dialog templates
      • How do I terminate my number in 360Dialog
    • Bubblescript
      • How to add a custom button
      • How to change the email template
    • Operator
      • Where are my CDRs?
      • Onboarding required
    • Google Tag Manager
    • Platform
      • Network Security Policies
    • Make
Powered by GitBook
On this page
  • What is a large language model?
  • What is a knowledge base?
  • How to use?
  • Node properties
  • Limitations

Was this helpful?

Export as PDF
  1. Studio
  2. Flows
  3. Nodes

Iterate: LLM Knowledgebase

To provide the user a way to ask questions that can be answered by a LLM using a predefined knowledgebase

PreviousSay: LLM KnowledgebaseNextIterate: continue

Last updated 4 months ago

Was this helpful?

The LLM Knowledgebase node is used in the same way theor node is used. This means, it is most often used as a form of main menu of your Smart App: "What can I do for you today?".

Large language models are great at understanding user questions and provide sensible answers based on the information stored in the common knowledge of the language model. The node solely relies on a predefined but limited prompt instruction to answer the user. This node however will also use a Knowledgebase on top of this prompt instruction. This can be configured in the .

What is a large language model?

A Large Language Model (LLM) is a type of artificial intelligence (AI) model designed to understand and generate human-like text based on the input it receives. These models are trained on massive datasets of text from books, articles, websites, and other written content, enabling them to process and generate coherent language.

This node uses the ChatGPT models from Open AI together with the Assistants API, hosted on the Microsoft Azure platform to answer the users of your Smart app.

What is a knowledge base?

A knowledge base is a centralized repository for information, designed to store, organize, and manage knowledge in a way that makes it easily accessible and usable for a specific purpose. Knowledge bases are commonly used by organizations, apps, and systems to provide self-service support, streamline workflows, and enhance decision-making.

How to use?

As explained in the introduction, the Iterate: LLM Knowledgebase node is working the same way as the Iterate: LLM node, adding the ability to use a predefined knowledgebase as its knowledge. Also, the Iterate: LLM Knowledgebase works as a menu. It either responds due to one of the or are triggered or otherwise respond from the LLM.

In the above example, the Iterate: LLM knowledgebase will match the intents associated with the two labelled links "Talk to a human" and "Done". When the user doesn't appear to be asking for one of these intents, it will use the LLM to generate an answer.

Node properties

Property
Description
Explanation

Question

The initial question

Repeat (1)

The text to use when re-prompting the user after a turn

optional

Repeat (2)

The next text to use when re-prompting the user after a turn. The system will keep on iterating this step the third and all other turns

Prompt

AI Knowledge base

Limitations

The LLM can use a specific instruction from you (as the Smart App designer) to guide the generation of the answer. This instruction is given in the form of a "Prompt". The prompt can be configured in the AI section of the platform. Besides instructions, the prompt will also contain content that the LLM can use on top of its own dataset to generate answers, like information regarding your address, opening hours, parking instructions, etc. See the page for more information on this topic.

The which contains the instructions and content the LLM can use when generating a response

The to use by the LLM to generate answers to the user

The knowledge base limitations are described in the .

Prompts
knowledge base page in the AI section
prompt
knowledge base
default Iterate
Iterate: LLM
Iterate: LLM
knowledgebase
AI section
labelled links
dialog triggers
Example of how to use the node in your flow