Process a PDF file with Gemini

This sample shows you how to process a PDF document using Gemini.

Explore further

For detailed documentation that includes this code sample, see the following:

• Document understanding

Code sample

Go

Before trying this sample, follow the Go setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Go API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import (
	"context"
	"fmt"
	"io"

	"google.golang.org/genai"
)

// generateTextWithPDF shows how to generate text using a PDF file input.
func generateTextWithPDF(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: `You are a highly skilled document summarization specialist.
	Your task is to provide a concise executive summary of no more than 300 words.
	Please summarize the given document for a general audience.`},
			{FileData: &genai.FileData{
				FileURI:  "gs://cloud-samples-data/generative-ai/pdf/1706.03762v7.pdf",
				MIMEType: "application/pdf",
			}},
		},
			Role: "user"},
	}

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)

	// Example response:
	// "Attention Is All You Need" introduces the Transformer,
	// a groundbreaking neural network architecture designed for...
	// ...

	return nil
}

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Java API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;

public class TextGenerationWithPdf {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text with PDF file input
  public static String generateContent(String modelId) {
    // 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 (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      String prompt =
          "You are a highly skilled document summarization specialist.\n"
              + " Your task is to provide a concise executive summary of no more than 300 words.\n"
              + " Please summarize the given document for a general audience";

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromUri(
                      "gs://cloud-samples-data/generative-ai/pdf/1706.03762v7.pdf",
                      "application/pdf"),
                  Part.fromText(prompt)),
              null);

      System.out.print(response.text());
      // Example response:
      // The document introduces the Transformer, a novel neural network architecture designed for
      // sequence transduction tasks, such as machine translation. Unlike previous dominant models
      // that rely on complex recurrent or convolutional neural networks, the Transformer proposes a
      // simpler, more parallelizable design based *solely* on attention mechanisms, entirely
      // dispensing with recurrence and convolutions...

      return response.text();
    }
  }
}

Python

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

from google import genai
from google.genai.types import HttpOptions, Part

client = genai.Client(http_options=HttpOptions(api_version="v1"))
model_id = "gemini-2.5-flash"

prompt = """
You are a highly skilled document summarization specialist.
Your task is to provide a concise executive summary of no more than 300 words.
Please summarize the given document for a general audience.
"""

pdf_file = Part.from_uri(
    file_uri="gs://cloud-samples-data/generative-ai/pdf/1706.03762v7.pdf",
    mime_type="application/pdf",
)

response = client.models.generate_content(
    model=model_id,
    contents=[pdf_file, prompt],
)

print(response.text)
# Example response:
# Here is a summary of the document in 300 words.
#
# The paper introduces the Transformer, a novel neural network architecture for
# sequence transduction tasks like machine translation. Unlike existing models that rely on recurrent or
# convolutional layers, the Transformer is based entirely on attention mechanisms.
# ...

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.