Notifications
Clear all
Topic starter
Subject:
i want to use a model gpt4 or gpt-4-1106-preview. callin.io masters, please tell us
Description:
What I’m doing: I’m working on automating content in Airtable by calling the GPT API via callin.io.
Problem situation: But when I call the GPT API, I use the select method to create a prompt completion and use text-davinci-003 from GPT-3 as the model. However, the accuracy of the output value is not good.
Desired changes: I’m trying to change the model to GPT-4.
Obstacle: When the existing selection method is changed to create a chat completion and the model is changed to gpt-4-1106-preview, the operation fails.
How can I use the GPT-4 model in this situation? I am a non-developer.
Please provide the rewritten markdown content *it should be in the markdown format.
Posted : 15/11/2023 6:26 am
Welcome to the callin.io community!
1. Screenshots of module fields and filters
Please share screenshots of the relevant module fields and any errors you are encountering. This will greatly assist other community members in understanding your situation.
You can upload images here using the Upload icon in the text editor:
2. Scenario blueprint
Kindly export the scenario blueprint file to enable others to review the mappings and settings. You can find the Export Blueprint option by clicking the three dots at the bottom of the scenario editor.
(Note: Exporting your scenario will not include private information or connection keys)
Uploading it here will appear as follows:
blueprint.json (12.3 KB)
3. And most importantly, Output bundles
Please provide the output bundles for your modules. To do this, run the scenario, then click the white speech bubble located at the top-right of each module. Save the bundle contents in your text editor as a bundle.json file and upload it to this discussion thread.
Providing the output bundles will enable others to replicate the scenario's behavior, even without direct access to the external service.
Following these steps will help others assist you more effectively. Thank you!
Posted : 15/11/2023 6:27 am