OpenDialog Docs
opendialog.aiStart BuildingTalk to an expert
  • GETTING STARTED
    • Introduction
    • Getting ready
    • Billing and plans
    • Quick Start AI Agents
      • Quick Start AI Agent
      • The "Start from Scratch" AI Agent
        • Chat Management Conversation
        • Welcome Conversation
        • Topic Conversation
        • Global No Match Conversation
        • Supporting LLM Actions
        • Semantic Classifier: Query Classifier
      • A Process Handling AI Agent
  • STEP BY STEP GUIDES
    • AI Agent Creation Overview
    • Add a new topic of discussion
    • Use knowledge sources via RAG
    • Adding a structured conversation
    • Add a 3rd party integration
    • Test and tweak your AI Agent
    • Publish your AI Agent
  • CORE CONCEPTS
    • OpenDialog Approach
      • Designing Conversational AI Agents
    • OpenDialog Platform
      • Scenarios
        • Conversations
        • Scenes
        • Turns and intents
      • Language Services
      • OpenDialog Account Management
        • Creating and managing users
        • Deleting OpenDialog account
        • Account Security
    • OpenDialog Conversation Engine
    • Contexts and attributes
      • Contexts
      • Attributes
      • Attribute Management
      • Conditions and operators
      • Composite Attributes
  • CREATE AI APPLICATIONS
    • Designing your application
      • Conversation Design
        • Conversational Patterns
          • Introduction to conversational patterns
          • Building robust assistants
            • Contextual help
            • Restart
            • End chat
            • Contextual and Global No Match
            • Contextual FAQ
          • Openings
            • Anatomy of an opening
            • Transactional openings
            • Additional information
          • Authentication
            • Components
            • Example dialog
            • Using in OpenDialog
          • Information collection
            • Components
            • Example dialog
            • Using in OpenDialog
            • Additional information
          • Recommendations
            • Components
            • Example dialog
            • Additional information
          • Extended telling
            • Components
            • Example dialog
            • Additional information
          • Repair
            • Types of repair
            • User request not understood
            • Example dialog
            • Additional information
          • Transfer
            • Components
            • Example dialog
            • Additional information
          • Closing
            • Components
            • Example dialog
            • Using in OpenDialog
            • Additional information
        • Best practices
          • Use Case
          • Subject Matter Expertise
          • Business Goals
          • User needs
            • Primary research
            • Secondary research
            • Outcome: user profile
          • Assistant personality
          • Sample dialogs
          • Conversation structure
          • API Integration Capabilities
          • NLU modeling
          • Testing strategy
          • The team
            • What does a conversation designer do
          • Select resources
      • Message Design
        • Message editor
        • Constructing Messages
        • Message Conditions
        • Messages best practices
        • Subsequent Messages - Virtual Intents
        • Using Attributes in Messages
        • Using Markdown in messages
        • Message Types
          • Text Message
          • Image Message
          • Button Message
          • Date Picker Message
          • Audio Message
          • Form Message
          • Full Page Message
          • Conversation Handover message
          • Autocomplete Message
          • Address Autocomplete Message
          • List Message
          • Rich Message
          • Location Message
          • E-Sign Message
          • File Upload Message
          • Meta Messages
            • Progress Bar Message
          • Attribute Message
      • Webchat Interface design
        • Webchat Interface Settings
        • Webchat Controls
      • Accessibility
      • Inclusive design
    • Leveraging Generative AI
      • Language Services
        • Semantic Intent Classifier
          • OpenAI
          • Azure
          • Google Gemini
          • Output attributes
        • Retrieval Augmented Generation
        • Example-based intent classification [Deprecated]
      • Interpreters
        • Available interpreters
          • OpenDialog interpreter
          • Amazon Lex interpreter
          • Google Dialogflow
            • Google Dialogflow interpreter
            • Google Dialogflow Knowledge Base
          • OpenAI interpreter
        • Using a language service interpreter
        • Interpreter Orchestration
        • Troubleshooting interpreters
      • LLM Actions
        • OpenAI
        • Azure OpenAI
        • Output attributes
        • Using conversation history (memory) in LLM actions
        • LLM Action Analytics
    • 3rd party Integrations in your application
      • Webhook actions
      • Actions from library
        • Freshdesk Action
        • Send to Email Action
        • Set Attributes Action
      • Conversation Hand-off
        • Chatwoot
    • Previewing your application
    • Launching your application
    • Monitoring your application
    • Debugging your application
    • Translating your application
    • FAQ
    • Troubleshooting and Common Problems
  • Developing With OpenDialog
    • Integrating with OpenDialog
    • Actions
      • Webhook actions
      • LLM actions
    • WebChat
      • Chat API
      • WebChat authentication
      • User Tracking
      • Load Webchat within page Element
      • How to enable JavaScript in your browser
      • SDK
        • Methods
        • Events
        • Custom Components
    • External APIs
  • Release Notes
    • Version 3 Upgrade Guide
    • Release Notes
Powered by GitBook
On this page
  • Where to find
  • What you'll need
  • How to use
  • Setting up the OpenAI LLM action in OpenDialog
  • Using the OpenAI LLM action in your scenario
  • Testing the OpenAI LLM action in your scenario
  1. CREATE AI APPLICATIONS
  2. Leveraging Generative AI
  3. LLM Actions

OpenAI

This section outlines how you can set up an LLM action using OpenAI.

PreviousLLM ActionsNextAzure OpenAI

Last updated 10 months ago

Where to find

LLM Actions allow you to integrate with a large language model provider, for example, OpenAI. It can be found under the Integrate section of a specific scenario. Once you select 'Create an LLM action' you will then have the opportunity to create the LLM action of your choice. Select OpenAI to start setting up your OpenAI integration.

What you'll need

To set up an integration between your LLM action, and an OpenAI model, you can either use OpenDialog's managed credentials, or your own credentials if you prefer. Selecting 'OpenDialog managed' means you will use a service directly managed by OpenDialog, and will not need to provide any credentials. If you would like to use your own credentials, you will need an OpenAI account.

If you are using your own credentials, unselect 'OpenDialog managed' and provide the following three elements:

How to use

Setting up the OpenAI LLM action in OpenDialog

To set up your OpenAI LLM action, navigate to "Integrate", and select "LLM Actions" from the menu. Use the "Create an LLM action" button to set up a new LLM action.

After providing a name and a description for your LLM action, select "Open AI" and provide the necessary account details to set up your integration. Hit 'Save' to set up this integration and use it within your scenario.

Using the OpenAI LLM action in your scenario

To use your OpenAI LLM action in your scenario, you can add it to an intent in the Designer.

When your scenario matches this intent, your LLM prompts will be sent to the language model and any output attributes will be populated.

Testing the OpenAI LLM action in your scenario

The OpenAI API Key is an API key associated with your OpenAI account. This can be found under the page in your OpenAI platform.

The OpenAI Organisation is a unique identifier for your organisation within OpenAI. This can be found on the page under "Organization ID".

The Model is an identifier for the large language model that you would like to use. OpenAI provides a list of identifiers, or you can use a custom fine-tuned model identifier associated with your organisation.

To display the LLM's response text in your scenario, you will need to use the llm_response attribute (or any other desired output attributes) within a . Within a message, create a new text block, set the text to {llm_response} and click "Save Message".

You can check if your action is successful by testing your conversation in the Preview (Test - Preview) and checking the user context on the right side of your screen. When you match the intent with the action then the user context will update to include action_success: true as well as any other , such as llm_response.

How to create an OpenAI account
"API keys"
general settings
pre-built model
message
output attributes
Setting up an OpenAI integration via OpenDialog
Use the "Create an LLM action" button to set up a new OpenAI integration
Select the desired intent in the designer and click "Add conditions, actions & attributes" to reveal the Action section
Create a text message using the LLM's response by using the llm_response attribute