#another

1 messages · Page 1 of 1 (latest)

dreamy spear
#

How to i use plugin on chat gpt builder?

olive templeBOT
#

Hi @dreamy spear. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

To use plugins on ChatGPT, you need to follow these steps:

  1. Build an API: This is the first step in creating a plugin. Your API will define the functionality that the plugin will provide.

  2. Document the API in the OpenAPI yaml or JSON format: This documentation will allow ChatGPT to understand how to interact with your API.

  3. Create a JSON manifest file: This file will define relevant metadata for the plugin. It needs to be hosted on the API’s domain. For example, if your company's domain is example.com, the plugin JSON file should be accessible via an <https://example.com> domain. When you install the plugin via the ChatGPT UI, on the backend, it looks for a file located at /.well-known/ai-plugin.json. The /.well-known folder is required and must exist on your domain for ChatGPT to connect with your plugin. If there is no file found, the plugin cannot be installed. If you are pointing to a remote server, HTTPS is required.

Here's an example of what the minimal definition of the required ai-plugin.json file will look like:

{
 "schema_version": "v1",
 "name_for_human": "TODO List",
 "name_for_model": "todo",
 "description_for_human": "Manage your TODO list. You can add, remove and view your TODOs.",
}

For more detailed information, you can refer to the OpenAI Plugin Documentation (https://platform.openai.com/docs/plugins/introduction) and the Getting Started Guide (https://platform.openai.com/docs/plugins/getting-started). If you want to have an example running as you read through the documentation and learn more about plugins, you can begin with the plugin quickstart repo (https://github.com/openai/plugins-quickstart).

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@dreamy spear kapa.ai is still learning and improving, please let us know how it did by reacting below

dreamy spear
#

Do i have to enter my code on schema, i’m really confused @olive temple

#

Do i have to enter my code on schema, i’m really confused @olive temple

olive templeBOT
#

Let me check the knowledge base for you. One moment! :books:

#

Yes, you need to define your API in a schema, specifically in the OpenAPI format. This schema is a descriptive representation of your API, and it's used by ChatGPT to understand how to interact with your API.

Here's an example of a schema from the extracts:

{
    "openapi": "3.1.0",
    "info": {
        "title": "WebdadiAPI",
        "version": "0.1.0"
    },
    "servers": [
        {
            "url": "MyFQDN/"
        }
    ],
    "paths": {
        "/search": {
            "get": {
                "summary": "Search GPT-generated content",
                "operationId": "searchGPTContent",
                "parameters": [
                    {
                        "name": "input_text",
                        "in": "query",
                        "required": true,
                        "schema": {
                            "type": "string"
                        }
                    }
                ]
            }
        }
    }
}

(Source: OpenAI Community (https://community.openai.com/t/535556))

This schema describes an API with a single endpoint (/search) that accepts a GET request. The request takes one parameter (input_text) in the query string.

You don't have to write your actual code in the schema. Instead, you describe what your API does, what endpoints it has, what methods it supports (GET, POST, etc.), and what parameters it expects.

Once you have your schema defined, you can use it to instruct the GPT model on how to interact with your API. For example:

# 
Instructions example:
The GPT is designed as a first-line support service agent, specializing in answering customer questions. It utilizes an API via the GPT’s custom action. The user will give you, the GPT, a query. You will take this query, and pass this as “query” param in the api. The API /search endpoint will return a response from which you will extract the contexts key from the result and display it to the user. The GPT’s responses should be friendly and efficient, providing clear summaries of steps for problem resolution. It should engage in conversations, seeking further context when necessary, and answer customer questions thoroughly.

(Source: OpenAI Community (https://community.openai.com/t/535556))

This instruction tells the GPT model to take a user's query, pass it as a parameter to the /search endpoint of your API, and then use the response to generate its own response.

For more information on how to create a schema, you can refer to the OpenAPI Specification (https://swagger.io/specification/).

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@dreamy spear kapa.ai is still learning and improving, please let us know how it did by reacting below

dreamy spear
#

I use chatgpt website, not API

#

I use chatgpt website, not API @olive temple

olive templeBOT
#

Let me check the knowledge base for you. One moment! :books:

#

I see, you're using the ChatGPT website. In this case, the process of using plugins is different and simpler. You don't need to create an API or a schema.

However, based on the information provided in the extracts, there's no specific guide on how to use plugins directly on the ChatGPT website. The extracts mainly discuss the use of the OpenAI API and the integration of GPT models into applications.

For more detailed instructions on how to use plugins on the ChatGPT website, I recommend checking the official OpenAI documentation or reaching out to OpenAI support for further assistance.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@dreamy spear kapa.ai is still learning and improving, please let us know how it did by reacting below

dreamy spear
#

Provide me instructions step by step, what should I do for make chatgpt builder with combine action plugin @olive temple

olive templeBOT
#

Let me check the knowledge base for you. One moment! :books:

#

To create a ChatGPT with an action plugin, you can follow these steps:

  1. Create a GPT in the ChatGPT UI: You can manually configure or use the GPT builder to create a GPT. Identify the API(s) you want to use. You can start by creating a GPT in the ChatGPT UI (https://chat.openai.com/gpts/editor).

  2. Go to the "Configure" tab in the GPT editor and select "Create new action": You will be presented with 3 main options: selecting the authentication schema for the action, inputting the schema itself, and setting the privacy policy URL. The Schema follows the OpenAPI specification format to define how the GPT can access an external API.

  3. Fill in the details for the schema, authentication, and privacy policy: When selecting an authentication method, you will have 3 options, "None", "API Key", and "OAuth". For the schema, you can take an existing OpenAPI specification you have for your API or create a new one. If you have already published an OpenAPI specification online, you can import it via the "Import from URL" button. The privacy policy URL is displayed to the user when they open a GPT and select the drop down in the top left corner showing the name of the GPT.

  4. Determine the visibility of your GPT: By default, GPTs are not accessible to everyone. When you go to save a GPT, you will have the option to "Publish to" a certain audience: "Only me", "Anyone with a link", or "Everyone". Each of these visibility options comes with different constraints and requirements. For example, the naming of a GPT has more restrictions if you share it with someone else.

  5. User(s) engage with your GPT: Once your GPT is set up and published, users can start interacting with it.