Process a PDF file with Gemini

Stay organized with collections Save and categorize content based on your preferences.

using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class PdfInput
{
    public async Task<string> SummarizePdf(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001")
    {

        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        string prompt = @"You are a very professional document summarization specialist.
Please summarize the given document.";

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = prompt },
                        new Part { FileData = new() { MimeType = "application/pdf", FileUri = "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf" }}
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);

        return responseText;
    }
}

import (
	"context"
	"errors"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

// generateContentFromPDF generates a response into the provided io.Writer, based upon the PDF
func generateContentFromPDF(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"

	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	part := genai.FileData{
		MIMEType: "application/pdf",
		FileURI:  "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf",
	}

	res, err := model.GenerateContent(ctx, part, genai.Text(`
			You are a very professional document summarization specialist.
    		Please summarize the given document.
	`))
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	if len(res.Candidates) == 0 ||
		len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	fmt.Fprintf(w, "generated response: %s\n", res.Candidates[0].Content.Parts[0])
	return nil
}

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;

public class PdfInput {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    pdfInput(projectId, location, modelName);
  }

  // Analyzes the given video input.
  public static String pdfInput(String projectId, String location, String modelName)
      throws IOException {
    // Initialize client that will be used to send requests. This client only needs
    // to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String pdfUri = "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              "You are a very professional document summarization specialist.\n"
                  + "Please summarize the given document.",
              PartMaker.fromMimeTypeAndData("application/pdf", pdfUri)
          ));

      String output = ResponseHandler.getText(response);
      System.out.println(output);
      return output;
    }
  }
}

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 = {
    fileData: {
      fileUri: 'gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf',
      mimeType: '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));
}

import vertexai

from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update project_id and location
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = """
You are a very professional document summarization specialist.
Please summarize the given document.
"""

pdf_file = Part.from_uri(
    uri="gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf",
    mime_type="application/pdf",
)
contents = [pdf_file, prompt]

response = model.generate_content(contents)
print(response.text)
# Example response:
# Here's a summary of the provided text, which appears to be a research paper on the Gemini 1.5 Pro
# multimodal large language model:
# **Gemini 1.5 Pro: Key Advancements and Capabilities**
# The paper introduces Gemini 1.5 Pro, a highly compute-efficient multimodal model
# significantly advancing long-context capabilities
# ...