# Custom GPT Models

### **Custom GPT Models**

<details>

<summary>How can I automate AI-driven responses in Autom Mate using custom GPT models</summary>

#### <mark style="background-color:green;">Answer</mark>

To automate AI-driven responses using custom GPT models in Autom Mate, implement the following actions:

* **Thread Scope:** Define the conversation thread by setting a Custom Thread ID or generating a new one.
* **Message:** Send a message to the GPT model by specifying the input prompt.
* **Run:** Execute the action to receive and process the GPT model's response.

Proper sequencing and configuration of these actions enable seamless integration of AI-driven responses into your workflows.

#### <mark style="background-color:yellow;">Real-World Example</mark>

In a workflow designed to handle customer inquiries, you can use the "Message" action to send the customer's question to the GPT model and the "Run" action to process and retrieve the AI-generated response, which can then be forwarded to the customer.

#### <mark style="background-color:blue;">Related Documentation</mark>

For comprehensive guidance, refer to the [How to Use My GPT Actions](https://docs.autommate.com/userguide/libraries/integration/my-chatgpt#how-to-use-my-gpt-actions) section.

</details>

<details>

<summary>What steps are necessary to set up credentials for integrating custom GPT models with Autom Mate?</summary>

#### <mark style="background-color:green;">Answer</mark>

To set up credentials for integrating custom GPT models with Autom Mate, follow these steps:

* Navigate to the "Vault" section under "Management" in Autom Mate.
* Click on "New App Credentials" and select "GPT" from the list of applications.
* Choose "API-KEY" as the Authentication Type.
* Enter your OpenAI API Key in the designated field.
* Click "Connect and Create" to complete the process.

#### <mark style="background-color:yellow;">Real-World Example</mark>

If you're integrating a custom-trained GPT model to automate content generation tasks, setting up the API key as described ensures secure and authenticated communication between Autom Mate and your GPT model.

#### <mark style="background-color:blue;">Related Documentation</mark>

Detailed instructions are available in the [Credentials Setup for My GPT](https://docs.autommate.com/userguide/libraries/integration/my-chatgpt#credentials-setup-for-my-gpt) section.

</details>

<details>

<summary>How can I manage conversation threads effectively when integrating custom GPT models into Autom Mate workflows?</summary>

#### <mark style="background-color:green;">Answer</mark>

To manage conversation threads effectively, utilize the "Thread Scope" action within Autom Mate. This action allows you to define whether a conversation thread is static or dynamic by setting a Custom Thread ID or generating a new Thread ID. Proper configuration ensures session continuity and maintains the context of interactions with your GPT model.

#### <mark style="background-color:yellow;">Real-World Example</mark>

If you're developing a customer support chatbot that needs to maintain context across multiple user interactions, setting a static Custom Thread ID ensures that the conversation history is preserved, providing more coherent and contextually relevant responses.

#### <mark style="background-color:blue;">Related Documentation</mark>

For detailed guidance on configuring the "Thread Scope" action, refer to the [My ChatGPT Integration with Custom GPT Models](https://docs.autommate.com/userguide/libraries/integration/my-chatgpt) section.

</details>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.autommate.com/userguide/faq/custom-gpt-models.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.