Transforming Text to Structured Data Objects with ChatGPT

Hello there!

I recently worked on a similar scenario and achieved the same result using a straightforward ChatGPT prompt with the Completion model.

For instance, I instructed it to return text in a JSON key-value pair format, with keys such as Name, Email, and Phone_number.

This approach should yield a proper JSON structure or the desired data format.

Hi, this module is an abstraction of the OpenAI function calling.

While I like the setup generally, I do think it’s lacking the correct setup for arrays. If you do the API with code, you can ask for an array and define the items (name, email, phone).

Is it possible that there is more than one contact in the input? So you’d ideally receive an array of contacts?

Best,
Richard

Hello!

I'm relatively new to callin.io and was considering using it with JSON data. Is it straightforward to convert that into an iterator that processes each item, allowing me to, for instance, create 6-7 contacts?

Thanks for your help and interest!

Hi Richard

I suspected as much, and yes, the primary goal here is to identify the relevant individuals, which is why having the option for more than one is important.

I've experimented with several ways to allow for an array, but unfortunately, it only supports arrays of text/numbers, not arrays of objects. Perhaps I just need to use the route as Manish suggested earlier and opt for 'JSON' followed by an iterator instead.

My main objectives for these contacts are to, in v.1, create a text message listing each person, and in v.2, depending on data quality, create an object in a CRM for each person identified.

Thanks for your response and for your interest!

You can still utilize the Make an API call Module

Ask GPT to suggest a structure…

I haven't tested this personally, but my understanding is that you should set the Data Type in the Structured Data Definition to Array instead of Object.

Pay attention to the comment associated with the Data Type field:

An appropriate data type for the parameter. Array should be used when multiple instances of a similar data type might occur.

Hey, yes exactly but then it should be possible to specify the items of an array. Otherwise, there would just be an array.

So currently, it would work something like this:

["firstName lastName zipCode", "firstName2 lastName2 zipCode2"] which would work but doesn’t really help.
Instead, the result should be:

[{firstName: XYZ, lastName: ABC, zipCode: GHI},{object2},…]

Or alternatively, arrays inside the array. But it’s not possible to do that in the module. Through an API call, it is possible though.

Ah, I understand. It appears the user interface doesn't support arrays of objects. I'll need to check with our Apps team about this...

Hi there, that would be fantastic to have as well!

Hi Richard, when I have the time, I might just implement the JSON, Array, and Iterator Solution. Although, an API call would be cool as well!

It appears that when OpenAI’s Text to Structured Data API was initially launched, it did not support an array of objects, but it does now.

I have submitted a request to incorporate this into the UI. Since there's a workaround available (detailed below), it might take a couple of months for this to be implemented.

Our development team provided the following code for use in the callin.io API Call module to achieve the same outcome:

{
    "model": "gpt-3.5-turbo",
    "messages": [
        {
            "name": "MakeUser",
            "role": "user",
            "content": "Here is a list of people and their details. You need to retrieve full name, email and phone number for each of them. Alice Johnson. Email: alice.johnson@email.com; Phone: 555-123-4567. Michael Rodriguez. Email: michael.rodriguez@email.com; Phone: 555-234-5678. Emily Davis. Email: emily.davis@email.com; Phone: 555-345-6789. Christopher Patel. Email: chris.patel@email.com; Phone: 555-456-7890. Olivia Smith. Email: olivia.smith@email.com; Phone: 555-567-8901"
        }
    ],
    "functions": [
        {
            "name": "makeParseRawText",
            "parameters": {
                "type": "object",
                "properties": {
                    "people": {
                        "name": "people",
                        "type": "array",
                        "description": "Array of people containing full name, email and phone number",
                        "items": {
                            "$ref": "#/$defs/person"
                        }
                    }
                },
                "$defs": {
                  "person": {
                    "type": "object",
                    "required": [ "fullName", "email", "phone" ],
                    "properties": {
                      "fullName": {
                        "type": "string",
                        "description": "Person's name."
                      },
                      "email": {
                        "type": "string",
                        "description": "Person's email."
                      },
                      "phone": {
                        "type": "string",
                        "description": "Person's phone number."
                      }
                    }
                  }
                },
                "required": [
                    "people"
                ]
            },
            "description": "Get a list of personal details for each person."
        }
    ],
    "function_call": {
        "name": "makeParseRawText"
    }
}

image772×479 56.4 KB

Use this option and parse the JSON.

Please provide the rewritten markdown content *it should be in the markdown format.

Just a heads-up, the feature request for this has now been put into action.

You should now be able to request an array of objects as the output of the transformation, without needing to use the callin.io API Call module!

Love it!!