My ChatGPT

Integration with Custom GPT Models

Introduction

The My GPT integration allows Autom Mate users to connect their custom-trained GPT models into their automation workflows seamlessly. This integration enables users to leverage specialized AI bots tailored to their specific needs without requiring any additional coding. My GPT can also integrate with external platforms such as Microsoft Teams or other supported messaging tools, enhancing user experiences with AI-driven interactions.

What is My GPT?

My GPT integrates with OpenAI’s GPT models, allowing users to customize and deploy AI bots directly within Autom Mate. By connecting to the OpenAI platform, users can create and manage conversations using their GPT models and automate various interactions.

Key Features:

Custom GPT Integration: Use custom GPT models trained on the OpenAI platform.
Flexible Thread Management: Support for both static and dynamic conversation threads using Thread IDs.
Multi-platform Integration: Autom Mate integrates custom GPTs with external platforms like MS Teams.
Dynamic Message Handling: Automate AI-driven responses based on user inputs.

Autom Mate Integration with My GPT

Autom Mate seamlessly integrates with custom GPT models, allowing users to leverage their own AI creations in automation workflows. With My GPT, users can train and use their GPT models to interact with Autom Mate actions, facilitating intelligent conversations and responses within their processes.

Key Integration Features:

Thread Management: Use Custom Thread ID for static conversations or Generate Thread ID for dynamic conversations.
Message Handling: Automate message sending and response handling with GPT.
Session Continuity: Maintain consistent conversations across sessions using Thread IDs.
AI Integration: Utilize AI bots in processes without writing any code.

Benefits of Autom Mate's My GPT Integration

No Additional Coding: Easily create and integrate AI bots into workflows without programming skills.
Customizable AI Conversations: Tailor AI interactions based on specific business needs.
Time Savings: Automate repetitive tasks or queries with AI-driven responses.
Seamless Workflow Integration: Integrate AI into any Autom Mate process for dynamic and intelligent automation.

It is essential to properly configure the Thread Scope when working with GPT models in Autom Mate. The Thread Scope ensures session management remains intact, whether you are using a static Custom Thread ID for ongoing sessions or a dynamic Generate Thread ID for temporary interactions. Mismanaging the Thread ID can cause a loss of conversation context, leading to irrelevant or incomplete responses from the GPT model. Additionally, proper configuration of the Assistant ID and credentials in the Vault is crucial. Without correct API key setup, Autom Mate will not be able to communicate with the GPT model. Moreover, users must handle the conversation thread carefully—deleting or resetting conversations may cause the Thread ID to change, breaking the flow continuity.

Incorrect usage of these elements may result in the automation failing or producing inaccurate responses. Ensure that you follow the correct action sequence—Thread Scope, Message, and Run—to avoid issues in workflow execution. Misplacing these actions, especially running a flow without a valid Assistant ID or Thread ID, will disrupt the GPT interaction and cause errors.

Credentials Setup for My GPT

Autom Mate provides secure management of credentials to connect GPT models through API keys. Follow these steps to set up credentials for My GPT:

Step-by-Step Guide:

Go to the Vault section under Management.
Navigate to the Application Credentials section.
Click on the "New App Credentials" button located at the top-right.
From the list of applications, select GPT.
Define a Connector Name for the GPT integration.
Under Authentication Type, select API-KEY.
Enter your OpenAI API Key in the designated field.
Click Connect and Create to complete the process.

How to Use My GPT Actions

Autom Mate provides three main actions for integrating custom GPT models into automation workflows: Thread Scope, Message, and Run. Each action plays a crucial role in managing and interacting with GPT-based conversations.

Thread Scope

Description and Purpose

The Thread Scope action manages conversation threads in Autom Mate, ensuring that GPT conversations are either static or dynamic across multiple interactions. It helps Autom Mate identify and maintain the same conversation session, whether the thread is predefined or generated dynamically.

Usage

Drag and drop the Thread Scope action into the Autom Mate flow designer.
Select the Thread ID option:
- Custom Thread ID: Use a predefined, static thread ID from the GPT logs for persistent sessions.
- Generate Thread ID: Automatically generate a new thread ID for dynamic sessions, where the conversation resets after each session.
Define whether the session should remain static or dynamic, depending on the business needs.

Inputs

Thread ID: Either select Custom Thread ID from the OpenAI GPT platform or let Autom Mate generate one dynamically.

Action Output

A maintained thread for either static or dynamic GPT conversations. This thread ensures that messages in the same scope are part of the same conversation.

Message

Description and Purpose

The Message action sends a user-defined input message to the custom GPT model. This action is crucial for generating GPT responses based on the conversation thread.

Usage

Drag and drop the Message action into the Autom Mate flow after the Thread Scope action.
Define the message content: Enter the text or question that you want to send to the custom GPT model for processing.
Ensure that the Thread Scope action is set up correctly to ensure the conversation remains within the intended context.

Inputs

Message Content: The text input or question that will be sent to the GPT model for generating a response.

Action Output

The message is sent to the GPT model based on the thread defined in the Thread Scope. The output will depend on the next action, which handles the response from the GPT model.

Run

Description and Purpose

The Run action executes the conversation with the custom GPT model by sending the defined message and receiving the AI-generated response. This is where the input from the Message action is processed by GPT, and the response is returned for use in further actions.

Usage

Drag and drop the Run action into the Autom Mate flow.
Enter the Assistant ID: Copy the Assistant ID from the OpenAI platform and paste it into the Run action.
Define the response handling: The response from the GPT can be saved as a string variable for use in subsequent actions.
Execute the flow to send the message, process it through GPT, and retrieve the response.

Inputs

Assistant ID: The ID for your custom GPT model obtained from the OpenAI playground.
Thread ID: Use the Thread ID defined in the Thread Scope action to maintain session continuity.
Message: The input message that the GPT model will process, provided by the Message action.

Action Output

The Run action returns the GPT model's response as a string variable. This response can be further utilized in Autom Mate workflows, such as storing the result, triggering additional actions, or integrating with external platforms.