Hi Kapa, I'm interested in developing a GPT model focused on paraphrasing complex ideas into simpler, clearer language. Could you provide detailed, step-by-step instructions on how to create such a GPT model ? I want the GPT to always paraphrase anything I send it. It has no other utility except for paraphrasing my messages and provide 10-20 examples each time.
#GPTs tutorial...
1 messages · Page 1 of 1 (latest)
Hi @runic jasper. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Based on the information provided in the extracts, here's a step-by-step guide on how to create a GPT model tailored for paraphrasing complex ideas into simpler language:
-
Navigate to the GPT creation page at
<https://chat.openai.com/gpts/editor> or select your name and then “My GPTs” on the ChatGPT page. -
Select “Create a GPT”.
-
In the Create tab, you can message the GPT Builder to help you build a new GPT. You can say something like, "Make a language expert who helps paraphrase complex ideas into simpler language."
-
To name and set the description of your GPT, head to the Configure tab. Here, you will also be able to select the actions you would like your GPT to take. In your case, you might not need to enable actions like browsing the web or creating images.
-
When you’re ready to publish your GPT, select “Publish” and share it with other people if you’d like.
Now you’ve created a GPT!
Please note that the GPT model will not provide 10-20 examples each time as per your request. The model will generate a response based on the input and the instructions you've given it. If you want multiple examples, you might need to ask the model multiple times or adjust the instructions to request multiple examples in a single response.
For more detailed instructions, you can refer to the Creating a GPT (https://help.openai.com/en/articles/8554397-creating-a-gpt) article on the OpenAI Help Center.
Please note that as of the information available in the extracts, the ability to create GPTs is being rolled out and may not be available to all users immediately. Some users have reported issues with access, and it appears that the feature is still being rolled out (source (https://community.openai.com/t/475363)).
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
@runic jasper kapa.ai is still learning and improving, please let us know how it did by reacting below
Looks like it's providing old info here.
I am not sure if it can read images but I will try and see
@golden sequoia I can build a GPT. Can you read what's in the image I attached ? If you can't then please tell me more about what's in the configure section.
Let me check the knowledge base for you. One moment! :books:
As an AI text-based model, I'm unable to directly process or interpret images. However, OpenAI has developed models that can handle image inputs, but the specifics of their capabilities and limitations are not detailed in the provided extracts.
Regarding the Configure section when creating a GPT, here's what you can do:
-
Adding an image: You can ask the GPT Builder to create an image for your GPT or you can upload your own under the Configure tab.
-
Additional Instructions: Here you can provide detailed instructions or guidelines on how the GPT should behave, its functionalities, and any particular behaviors to avoid.
-
Prompt Starters: These are examples of prompts for the user to start the conversation.
-
Knowledge: This allows you to provide additional context for your GPT to reference. Please note that content from the files that are uploaded could be included in the output.
-
New Capabilities: Enabling Web Browsing, DALL·E Image Generation, and Advanced Data Analysis, will allow the GPT to perform additional functionality.
-
Custom Actions: You can make third-party APIs available to your GPT by providing details about the endpoints, parameters, and a description about how the model should use it. Actions for GPTs can also be imported from an OpenAPI schema. So if you’ve already built a plugin, you will be able to use your existing plugin manifests to define actions for your GPT.