with Google Gemini and Puppeteer?
Generates content from text input using the Google Gemini API. See the documentation
Get the HTML of a webpage using Puppeteer. See the documentation for details.
Generates content from both text and image input using the Gemini API. See the documentation
Get the title of a webpage using Puppeteer. See the documentation
Generate embeddings from text input using Google Gemini. See the documentation
The Google Gemini API is a cutting-edge tool from Google that enables developers to leverage AI models like Imagen and MusicLM to create and manipulate images and music based on textual descriptions. With Pipedream, you can harness this API to automate workflows that integrate AI-generated content into a variety of applications, from generating visuals for social media posts to composing background music for videos. Pipedream's serverless platform allows you to connect Google Gemini API with other apps to create complex, event-driven workflows without managing infrastructure.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
google_gemini: {
type: "app",
app: "google_gemini",
}
},
async run({steps, $}) {
const data = `{{your_promptt}}`;
//E.g. {"contents":[{"parts":[{"text":"Write a story about a magic backpack"}]}]}
return await axios($, {
method: "POST",
url: `https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent`,
headers: {
"Content-Type": "application/json",
},
params: {
key: `${this.google_gemini.$auth.api_key}`,
},
data
})
},
})
Puppeteer is a Node.js library which provides a high-level API to control Chrome/Chromium over the DevTools Protocol. Puppeteer runs in headless mode on Chromium on Pipedream.
Using Puppeteer you can perform tasks including:
import { puppeteer } from '@pipedream/browsers';
export default defineComponent({
async run({steps, $}) {
const browser = await puppeteer.browser();
// Interact with the web page programmatically
// See Puppeeter's Page documentation for available methods:
// https://pptr.dev/api/puppeteer.page
const page = await browser.newPage();
await page.goto('https://pipedream.com/');
const title = await page.title();
const content = await page.content();
// The browser needs to be closed, otherwise the step will hang
await browser.close();
return { title, content }
},
})