Implement Gemini API

[MenlyCSE]

Use Google's API to generate or summarize text in our HTML, CSS, and JavaScript webpage.

• Example 1: you can add a text input that takes the user's input and generates or summarizes the text
• Example 2: You can add a file import to extract text from a PDF, Image, or other files
• Example 3: You can add a text input that takes the user's input and generates a quiz (e.g., quiz generator)

Do whatever you'd like as long as you are using Google's API

[SachchitBalamurugan]

Implemented a better UI for the Gemini API website, and everything other then the input and summarize button are placeholders for now. Using the API and uses User input to generate AI responses

[randompotato0112]

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function analyze_pdf(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const filePart = {
    file_data: {
      file_uri: 'gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf',
      mime_type: 'application/pdf',
    },
  };
  const textPart = {
    text: `
    You are a very professional document summarization specialist.
    Please summarize the given document.`,
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  const resp = await generativeModel.generateContent(request);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

It's hard to find a pure JavaScript approach for PDF uploads, but I found this Node.js approach that seems to work pretty well. This one logs the response to the console but it easy to update the website with it. A similar approach can be used to upload the regular prompts too.