chatGPT for Airtable automation.

[chrisbyrne]

Using chatGPT in an Airtable automation. 

In my use case, the automation triggers on when an Airtable record matches conditions,
then follows with 2 actions, run script and update record. Adjust the first part of the prompt
with your own use case. Tip: Use chatGPT to help you write a prompt for chatGPT (!)

let inputConfig = input.config();
text = `${inputConfig.text}`;

var key = "openai-api-key";

var url = "https://api.openai.com/v1/completions";

prompt = "Reword this text to grade 9 reading level: " + text;

var gpt = {
model : "text-davinci-003",
prompt : prompt,
temperature : 0,
max_tokens : 1024
};

response = await fetch(url, {
method: 'POST',
body: JSON.stringify(gpt),
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer ' + key,
}
});

answer= await response.json();

data=answer.choices[0].text;

output.set('your-airtable-field',data);

[chrisbyrne]

@jeanyh Good point, not exactly equal but seems a rule of thumb?

[Karl_L]

As a late update on my own issue posted above:

I had not understood that the ChatGPT API is not included in the ChatGPT Plus subscription. 

After having signed up for the API service this worked beautifully. 

Again, big thanks to @chrisbyrne for this script

[christopher_so1]

Is anyone having issues now. This use to work perfectly then all of a sudden starting yesterday it is now giving this error: 

TypeError: Cannot read properties of undefined (reading '0') at main on line 27

[christopher_so1]

Further exploration is coming down to a HTTP 429 Error code. ?????

[dan2]

 I've been using this script below quite a bit, and it's a game changer. It lets you take a record column and feed that as a prompt into a gpt chat model and then output the response. I've used it quite a bit to enrich data and do specific tasks.

How do I use it? You'll need to add the script airtable extension and add the following code. If it's in ALL_CAPS you would put unique information related to your table in the script. In this case you need to put the table, view, a field for the system prompt, a field for the user prompt and a field for the output response that you get from gpt. You can adjust the Chat Model and Temperature. There are other parameters you can add to it as well. And don't forget your openai api key.

let table = base.getTable("TABLE_NAME");
let view = table.getView("VIEW_NAME");
let records = await view.selectRecordsAsync({fields: table.fields});
const apiKey = 'OPENAI-API-KEY';
const url = 'https://api.openai.com/v1/chat/completions';

for (let record of records.records) {
let messages = [
{ role: "system", content: record.getCellValue("FIELD_NAME") },{ role: "user", content: record.getCellValue("FIELD_NAME1") }
];
let data = {
messages: messages,
model: 'gpt-3.5-turbo',
temperature: 0.3,
};
let options = {
headers: {
'Content-Type': 'application/json',
'Authorization': `Bearer ${apiKey}`
},
method: 'POST',
body: JSON.stringify(data)
};
console.log(options)
let response = await fetch(url, options);
console.log(response)
let json = await response.json();
let AIResponse = json.choices[0].message;
await table.updateRecordAsync(record.id, {OUTPUT_FIELD: AIResponse.content});
}

[ScottWorld]

For those of you who don't want to write Javascript code — but would love to integrate Airtable and ChatGPT in a no-code/low-code way — it's great to know that Make supports ChatGPT, DALL-E, and Whisper!

I give a brief overview of how to use Airtable with ChatGPT on this episode of the BuiltOnAir podcast.

If you're just getting started with Make, there is a small learning curve. To help, I created this basic navigation video. In that thread, I also provide the links to a few other Make training resources there as well.

p.s. If anybody would like to hire an expert Airtable consultant to help them with any of this, please feel free to contact me through my website: Airtable consultant — ScottWorld

[kathlyn]

What is the role of ChatGPT in automating processes within Airtable?