A few days ago I wrote up an exploration I did in Spam APIs, "Spam APIs in 2024". After working on those demos and writing up my findings, I thought it might be interesting to see how a generative AI tool, like Google's Gemini would handle such a task.

Initial Tests

So - once again - I'm a broken record on this - but I fired up AI Studio first to give it some quick tests. I began with this prompt:

Given the following text, rate how much it appears to be spam by giving it a score between 1 and 10, with 10 being the most likely the content is spam.

For my first test, I used a 'bad' sample (see my last post for a full listing of my sample data):

I got this response:

That feels pretty correct. Next, I tried it with this 'good' sample':

And got:

This also feels pretty accurate. All in all, it seems to work well, but if I wanted to automate the process, I'd need to remove the context. To do that, I changed my prompt to:

Given the following text, rate how much it appears to be spam by giving it a score between 1 and 10, with 10 being the most likely the content is spam. Your response should only contain the score with no additional text.

I verified this worked, and then wrote a quick automation script:

import { tests } from './inputdata.js';
import { GoogleGenerativeAI, HarmCategory, HarmBlockThreshold } from '@google/generative-ai';

const MODEL_NAME = "gemini-1.5-pro-latest";
const API_KEY = process.env.GOOGLE_AI_KEY;

async function testForSpam(test) {
  const genAI = new GoogleGenerativeAI(API_KEY);
  const model = genAI.getGenerativeModel({ model: MODEL_NAME }, { apiVersion:'v1beta'});

  const generationConfig = {
    temperature: 0.9,
    topK: 1,
    topP: 1,
    maxOutputTokens: 2048,
  };

  const safetySettings = [
    {
      category: HarmCategory.HARM_CATEGORY_HARASSMENT,
      threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
    },
    {
      category: HarmCategory.HARM_CATEGORY_HATE_SPEECH,
      threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
    },
    {
      category: HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT,
      threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
    },
    {
      category: HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
      threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
    },
  ];

  const parts = [
    {text: `
Given the following text, rate how much it appears to be spam by giving it a score between 1 and 10, with 10 being the most likely the content is spam. Your response should only contain the score with no additional text.

${test}`},
  ];

  const result = await model.generateContent({
    contents: [{ role: "user", parts }],
    generationConfig,
    safetySettings,
  });

  const response = result.response;
  return response.text().trim();
}

async function delay(x) {
	return new Promise(resolve => {
		setTimeout(() => resolve(), x);
	});
}


for(let good of tests.good) {
	console.log('Running good test');
	let result = await testForSpam(good);
	console.log(result);
	await delay(30 * 1000);
}

for(let bad of tests.bad) {
	console.log('Running bad test');
	let result = await testForSpam(bad);
	console.log(result);
	await delay(30 * 1000);
}

Most of this is boilerplate Gemini code, with one really important difference. Note the safety settings are all set to BLOCK_ONLY_HIGH. I found that Gemini would have an issue with some of the spam (no surprise there) and lowering the safety thresholds worked.

Another important change was to throttle my code a bit such that I was only calling the API two times per minute. Without this I would get 429 errors stating I was hitting the API too much. That feels a bit on the stingy side and I'm not sure I'd use this at scale, but at the same time, it's doing a lot more and heck, may even be overkill for this task.

The Results

How did it do? Pretty good I think:

Running good test
2
Running good test
3
Running good test
3
Running good test
1
Running good test
1
Running bad test
6
Running bad test
8
Running bad test
8
Running bad test
7
Running bad test
7

Every single good test was less than 5 and every bad test was over 5. If you would like to try this code yourself, get a key, and then grab the code from here: https://github.com/cfjedimaster/ai-testingzone/tree/main/spam_check