AI-Powered GPT Connect

3 minutes to read

With the AI-Powered GPT Connect extension, you can create dynamic prompts using fields from your tables, which are sent to an OpenAI Large Language Model for tasks like data analysis, content generation, and more. You can store AI’s responses in designated fields, enabling a wide range of use cases.

Note: The AI model is trained on data available up until a certain date.

The credits cost of using AI-Powered GPT Connect depends on your particular requests and responses. You can check your credits usage in Plan and billing. Learn more.

Installing and Using AI-Powered GPT Connect

In the left panel on the main screen, click Integrations.
On the Extensions tab, in the AI-Powered GPT Connect section, click Add.
After the completed installation, click Open.
On the Agents screen, click Create agent.
In the right panel that opens, enter the name of your agent.
Select the profile for this agent.
In the profile settings, you can choose which OpenAI model will be used to process the requests from this agent.
Under Trigger, select the data source which will be monitored, and the type of event that will trigger the agent.
In the Outgoing data items section, enter your AI prompt. You can insert parameters that the extension should use when processing the prompt. You can select a file to be analyzed by AI.
In the Incoming data items section, select the target field of the table where you want the response to be stored.
Click Create.

Outgoing Data Item Types

AI prompt: Create a prompt with table fields for the AI model. Specify response length, value type, or if extra details should be excluded, and adjust for the destination field type (for example, max 255 characters).
File: Include a File/Attachment field in the prompt to be analyzed by AI. The supported formats are: c, cpp, css, csv, doc, docx, gif, go, html, java, jpeg, jpg, js, json, md, pdf, php, pkl, png, pptx, py, rb, tar, tex, ts, txt, webp, xlsx, xml, zip.
For png, jpeg, jpg, webp and non-animated gif files, the file size must not exceed 20 MB. For optimal image processing, the recommended resolution is 1024×1024 pixels or less.

For other file types, the maximum allowed size is 512 MB.

Incoming Data Item Types

Response: Store the AI model’s response in the table field. The output received from OpenAI depends on the data type of the target field selected.

AI language models

In the profile configuration for AI-Powered GPT Connect extension agents, you can choose one of the following language models to be applied:

GPT-4o – use this model to process complex requests that require high language precision.
GPT-4o mini – model optimized for fast performance and lower costs that you can use for simpler requests.