Comprensión de documentos

Los modelos de Gemini pueden procesar documentos en formato PDF y usar la visión nativa para comprender los contextos de documentos completos. Esto va más allá de la extracción de texto simple, lo que le permite a Gemini hacer lo siguiente:

  • Analiza e interpreta contenido, incluidos texto, imágenes, diagramas, gráficos y tablas, incluso en documentos largos de hasta 1, 000 páginas.
  • Extrae información en formatos de salida estructurada.
  • Resumir y responder preguntas en función de los elementos visuales y textuales de un documento
  • Transcribe el contenido de documentos (p.ej., a HTML) y conserva los diseños y el formato para usar en aplicaciones posteriores.

Cómo pasar datos de PDF intercalados

Puedes pasar datos de PDF intercalados en la solicitud a generateContent. En el caso de las cargas útiles en PDF de menos de 20 MB, puedes elegir entre subir documentos codificados en base64 o subir directamente archivos almacenados de forma local.

En el siguiente ejemplo, se muestra cómo recuperar un PDF de una URL y convertirlo en bytes para su procesamiento:

Python

from google import genai
from google.genai import types
import httpx

client = genai.Client()

doc_url = "https://discovery.ucl.ac.uk/id/eprint/10089234/1/343019_3_art_0_py4t4l_convrt.pdf"

# Retrieve and encode the PDF byte
doc_data = httpx.get(doc_url).content

prompt = "Summarize this document"
response = client.models.generate_content(
  model="gemini-2.5-flash",
  contents=[
      types.Part.from_bytes(
        data=doc_data,
        mime_type='application/pdf',
      ),
      prompt])
print(response.text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
    const pdfResp = await fetch('https://discovery.ucl.ac.uk/id/eprint/10089234/1/343019_3_art_0_py4t4l_convrt.pdf')
        .then((response) => response.arrayBuffer());

    const contents = [
        { text: "Summarize this document" },
        {
            inlineData: {
                mimeType: 'application/pdf',
                data: Buffer.from(pdfResp).toString("base64")
            }
        }
    ];

    const response = await ai.models.generateContent({
        model: "gemini-2.5-flash",
        contents: contents
    });
    console.log(response.text);
}

main();

Go

package main

import (
    "context"
    "fmt"
    "io"
    "net/http"
    "os"
    "google.golang.org/genai"
)

func main() {

    ctx := context.Background()
    client, _ := genai.NewClient(ctx, &genai.ClientConfig{
        APIKey:  os.Getenv("GEMINI_API_KEY"),
        Backend: genai.BackendGeminiAPI,
    })

    pdfResp, _ := http.Get("https://discovery.ucl.ac.uk/id/eprint/10089234/1/343019_3_art_0_py4t4l_convrt.pdf")
    var pdfBytes []byte
    if pdfResp != nil && pdfResp.Body != nil {
        pdfBytes, _ = io.ReadAll(pdfResp.Body)
        pdfResp.Body.Close()
    }

    parts := []*genai.Part{
        &genai.Part{
            InlineData: &genai.Blob{
                MIMEType: "application/pdf",
                Data:     pdfBytes,
            },
        },
        genai.NewPartFromText("Summarize this document"),
    }

    contents := []*genai.Content{
        genai.NewContentFromParts(parts, genai.RoleUser),
    }

    result, _ := client.Models.GenerateContent(
        ctx,
        "gemini-2.5-flash",
        contents,
        nil,
    )

    fmt.Println(result.Text())
}

REST

DOC_URL="https://discovery.ucl.ac.uk/id/eprint/10089234/1/343019_3_art_0_py4t4l_convrt.pdf"
PROMPT="Summarize this document"
DISPLAY_NAME="base64_pdf"

# Download the PDF
wget -O "${DISPLAY_NAME}.pdf" "${DOC_URL}"

# Check for FreeBSD base64 and set flags accordingly
if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

# Base64 encode the PDF
ENCODED_PDF=$(base64 $B64FLAGS "${DISPLAY_NAME}.pdf")

# Generate content using the base64 encoded PDF
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"inline_data": {"mime_type": "application/pdf", "data": "'"$ENCODED_PDF"'"}},
          {"text": "'$PROMPT'"}
        ]
      }]
    }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json

# Clean up the downloaded PDF
rm "${DISPLAY_NAME}.pdf"

También puedes leer un PDF desde un archivo local para su procesamiento:

Python

from google import genai
from google.genai import types
import pathlib

client = genai.Client()

# Retrieve and encode the PDF byte
filepath = pathlib.Path('file.pdf')

prompt = "Summarize this document"
response = client.models.generate_content(
  model="gemini-2.5-flash",
  contents=[
      types.Part.from_bytes(
        data=filepath.read_bytes(),
        mime_type='application/pdf',
      ),
      prompt])
print(response.text)

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as fs from 'fs';

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
    const contents = [
        { text: "Summarize this document" },
        {
            inlineData: {
                mimeType: 'application/pdf',
                data: Buffer.from(fs.readFileSync("content/343019_3_art_0_py4t4l_convrt.pdf")).toString("base64")
            }
        }
    ];

    const response = await ai.models.generateContent({
        model: "gemini-2.5-flash",
        contents: contents
    });
    console.log(response.text);
}

main();

Go

package main

import (
    "context"
    "fmt"
    "os"
    "google.golang.org/genai"
)

func main() {

    ctx := context.Background()
    client, _ := genai.NewClient(ctx, &genai.ClientConfig{
        APIKey:  os.Getenv("GEMINI_API_KEY"),
        Backend: genai.BackendGeminiAPI,
    })

    pdfBytes, _ := os.ReadFile("path/to/your/file.pdf")

    parts := []*genai.Part{
        &genai.Part{
            InlineData: &genai.Blob{
                MIMEType: "application/pdf",
                Data:     pdfBytes,
            },
        },
        genai.NewPartFromText("Summarize this document"),
    }
    contents := []*genai.Content{
        genai.NewContentFromParts(parts, genai.RoleUser),
    }

    result, _ := client.Models.GenerateContent(
        ctx,
        "gemini-2.5-flash",
        contents,
        nil,
    )

    fmt.Println(result.Text())
}

Cómo subir archivos PDF con la API de File

Puedes usar la API de File para subir documentos más grandes. Siempre usa la API de File cuando el tamaño total de la solicitud (incluidos los archivos, la instrucción de texto, las instrucciones del sistema, etcétera) sea superior a 20 MB.

Llama a media.upload para subir un archivo con la API de File. El siguiente código sube un archivo de documento y, luego, lo usa en una llamada a models.generateContent.

Archivos PDF grandes desde URLs

Usa la API de File para simplificar la carga y el procesamiento de archivos PDF grandes desde URLs:

Python

from google import genai
from google.genai import types
import io
import httpx

client = genai.Client()

long_context_pdf_path = "https://www.nasa.gov/wp-content/uploads/static/history/alsj/a17/A17_FlightPlan.pdf"

# Retrieve and upload the PDF using the File API
doc_io = io.BytesIO(httpx.get(long_context_pdf_path).content)

sample_doc = client.files.upload(
  # You can pass a path or a file-like object here
  file=doc_io,
  config=dict(
    mime_type='application/pdf')
)

prompt = "Summarize this document"

response = client.models.generate_content(
  model="gemini-2.5-flash",
  contents=[sample_doc, prompt])
print(response.text)

JavaScript

import { createPartFromUri, GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {

    const pdfBuffer = await fetch("https://www.nasa.gov/wp-content/uploads/static/history/alsj/a17/A17_FlightPlan.pdf")
        .then((response) => response.arrayBuffer());

    const fileBlob = new Blob([pdfBuffer], { type: 'application/pdf' });

    const file = await ai.files.upload({
        file: fileBlob,
        config: {
            displayName: 'A17_FlightPlan.pdf',
        },
    });

    // Wait for the file to be processed.
    let getFile = await ai.files.get({ name: file.name });
    while (getFile.state === 'PROCESSING') {
        getFile = await ai.files.get({ name: file.name });
        console.log(`current file status: ${getFile.state}`);
        console.log('File is still processing, retrying in 5 seconds');

        await new Promise((resolve) => {
            setTimeout(resolve, 5000);
        });
    }
    if (file.state === 'FAILED') {
        throw new Error('File processing failed.');
    }

    // Add the file to the contents.
    const content = [
        'Summarize this document',
    ];

    if (file.uri && file.mimeType) {
        const fileContent = createPartFromUri(file.uri, file.mimeType);
        content.push(fileContent);
    }

    const response = await ai.models.generateContent({
        model: 'gemini-2.5-flash',
        contents: content,
    });

    console.log(response.text);

}

main();

Go

package main

import (
  "context"
  "fmt"
  "io"
  "net/http"
  "os"
  "google.golang.org/genai"
)

func main() {

  ctx := context.Background()
  client, _ := genai.NewClient(ctx, &genai.ClientConfig{
    APIKey:  os.Getenv("GEMINI_API_KEY"),
    Backend: genai.BackendGeminiAPI,
  })

  pdfURL := "https://www.nasa.gov/wp-content/uploads/static/history/alsj/a17/A17_FlightPlan.pdf"
  localPdfPath := "A17_FlightPlan_downloaded.pdf"

  respHttp, _ := http.Get(pdfURL)
  defer respHttp.Body.Close()

  outFile, _ := os.Create(localPdfPath)
  defer outFile.Close()

  _, _ = io.Copy(outFile, respHttp.Body)

  uploadConfig := &genai.UploadFileConfig{MIMEType: "application/pdf"}
  uploadedFile, _ := client.Files.UploadFromPath(ctx, localPdfPath, uploadConfig)

  promptParts := []*genai.Part{
    genai.NewPartFromURI(uploadedFile.URI, uploadedFile.MIMEType),
    genai.NewPartFromText("Summarize this document"),
  }
  contents := []*genai.Content{
    genai.NewContentFromParts(promptParts, genai.RoleUser), // Specify role
  }

    result, _ := client.Models.GenerateContent(
        ctx,
        "gemini-2.5-flash",
        contents,
        nil,
    )

  fmt.Println(result.Text())
}

REST

PDF_PATH="https://www.nasa.gov/wp-content/uploads/static/history/alsj/a17/A17_FlightPlan.pdf"
DISPLAY_NAME="A17_FlightPlan"
PROMPT="Summarize this document"

# Download the PDF from the provided URL
wget -O "${DISPLAY_NAME}.pdf" "${PDF_PATH}"

MIME_TYPE=$(file -b --mime-type "${DISPLAY_NAME}.pdf")
NUM_BYTES=$(wc -c < "${DISPLAY_NAME}.pdf")

echo "MIME_TYPE: ${MIME_TYPE}"
echo "NUM_BYTES: ${NUM_BYTES}"

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${DISPLAY_NAME}.pdf" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo "file_uri: ${file_uri}"

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "'$PROMPT'"},
          {"file_data":{"mime_type": "application/pdf", "file_uri": '$file_uri'}}]
        }]
      }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json

# Clean up the downloaded PDF
rm "${DISPLAY_NAME}.pdf"

PDFs grandes almacenados de forma local

Python

from google import genai
from google.genai import types
import pathlib
import httpx

client = genai.Client()

# Retrieve and encode the PDF byte
file_path = pathlib.Path('large_file.pdf')

# Upload the PDF using the File API
sample_file = client.files.upload(
  file=file_path,
)

prompt="Summarize this document"

response = client.models.generate_content(
  model="gemini-2.5-flash",
  contents=[sample_file, "Summarize this document"])
print(response.text)

JavaScript

import { createPartFromUri, GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
    const file = await ai.files.upload({
        file: 'path-to-localfile.pdf'
        config: {
            displayName: 'A17_FlightPlan.pdf',
        },
    });

    // Wait for the file to be processed.
    let getFile = await ai.files.get({ name: file.name });
    while (getFile.state === 'PROCESSING') {
        getFile = await ai.files.get({ name: file.name });
        console.log(`current file status: ${getFile.state}`);
        console.log('File is still processing, retrying in 5 seconds');

        await new Promise((resolve) => {
            setTimeout(resolve, 5000);
        });
    }
    if (file.state === 'FAILED') {
        throw new Error('File processing failed.');
    }

    // Add the file to the contents.
    const content = [
        'Summarize this document',
    ];

    if (file.uri && file.mimeType) {
        const fileContent = createPartFromUri(file.uri, file.mimeType);
        content.push(fileContent);
    }

    const response = await ai.models.generateContent({
        model: 'gemini-2.5-flash',
        contents: content,
    });

    console.log(response.text);

}

main();

Go

package main

import (
    "context"
    "fmt"
    "os"
    "google.golang.org/genai"
)

func main() {

    ctx := context.Background()
    client, _ := genai.NewClient(ctx, &genai.ClientConfig{
        APIKey:  os.Getenv("GEMINI_API_KEY"),
        Backend: genai.BackendGeminiAPI,
    })
    localPdfPath := "/path/to/file.pdf"

    uploadConfig := &genai.UploadFileConfig{MIMEType: "application/pdf"}
    uploadedFile, _ := client.Files.UploadFromPath(ctx, localPdfPath, uploadConfig)

    promptParts := []*genai.Part{
        genai.NewPartFromURI(uploadedFile.URI, uploadedFile.MIMEType),
        genai.NewPartFromText("Give me a summary of this pdf file."),
    }
    contents := []*genai.Content{
        genai.NewContentFromParts(promptParts, genai.RoleUser),
    }

    result, _ := client.Models.GenerateContent(
        ctx,
        "gemini-2.5-flash",
        contents,
        nil,
    )

    fmt.Println(result.Text())
}

REST

NUM_BYTES=$(wc -c < "${PDF_PATH}")
DISPLAY_NAME=TEXT
tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GEMINI_API_KEY}" \
  -D upload-header.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: application/pdf" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${PDF_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Can you add a few more lines to this poem?"},
          {"file_data":{"mime_type": "application/pdf", "file_uri": '$file_uri'}}]
        }]
      }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json

Puedes verificar que la API haya almacenado correctamente el archivo subido y obtener sus metadatos llamando a files.get. Solo el name (y, por extensión, el uri) son únicos.

Python

from google import genai
import pathlib

client = genai.Client()

fpath = pathlib.Path('example.txt')
fpath.write_text('hello')

file = client.files.upload(file='example.txt')

file_info = client.files.get(name=file.name)
print(file_info.model_dump_json(indent=4))

REST

name=$(jq ".file.name" file_info.json)
# Get the file of interest to check state
curl https://generativelanguage.googleapis.com/v1beta/files/$name > file_info.json
# Print some information about the file you got
name=$(jq ".file.name" file_info.json)
echo name=$name
file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

Cómo pasar varios PDFs

La API de Gemini puede procesar varios documentos PDF (hasta 1,000 páginas) en una sola solicitud, siempre que el tamaño combinado de los documentos y la instrucción de texto permanezca dentro de la ventana de contexto del modelo.

Python

from google import genai
import io
import httpx

client = genai.Client()

doc_url_1 = "https://arxiv.org/pdf/2312.11805"
doc_url_2 = "https://arxiv.org/pdf/2403.05530"

# Retrieve and upload both PDFs using the File API
doc_data_1 = io.BytesIO(httpx.get(doc_url_1).content)
doc_data_2 = io.BytesIO(httpx.get(doc_url_2).content)

sample_pdf_1 = client.files.upload(
  file=doc_data_1,
  config=dict(mime_type='application/pdf')
)
sample_pdf_2 = client.files.upload(
  file=doc_data_2,
  config=dict(mime_type='application/pdf')
)

prompt = "What is the difference between each of the main benchmarks between these two papers? Output these in a table."

response = client.models.generate_content(
  model="gemini-2.5-flash",
  contents=[sample_pdf_1, sample_pdf_2, prompt])
print(response.text)

JavaScript

import { createPartFromUri, GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function uploadRemotePDF(url, displayName) {
    const pdfBuffer = await fetch(url)
        .then((response) => response.arrayBuffer());

    const fileBlob = new Blob([pdfBuffer], { type: 'application/pdf' });

    const file = await ai.files.upload({
        file: fileBlob,
        config: {
            displayName: displayName,
        },
    });

    // Wait for the file to be processed.
    let getFile = await ai.files.get({ name: file.name });
    while (getFile.state === 'PROCESSING') {
        getFile = await ai.files.get({ name: file.name });
        console.log(`current file status: ${getFile.state}`);
        console.log('File is still processing, retrying in 5 seconds');

        await new Promise((resolve) => {
            setTimeout(resolve, 5000);
        });
    }
    if (file.state === 'FAILED') {
        throw new Error('File processing failed.');
    }

    return file;
}

async function main() {
    const content = [
        'What is the difference between each of the main benchmarks between these two papers? Output these in a table.',
    ];

    let file1 = await uploadRemotePDF("https://arxiv.org/pdf/2312.11805", "PDF 1")
    if (file1.uri && file1.mimeType) {
        const fileContent = createPartFromUri(file1.uri, file1.mimeType);
        content.push(fileContent);
    }
    let file2 = await uploadRemotePDF("https://arxiv.org/pdf/2403.05530", "PDF 2")
    if (file2.uri && file2.mimeType) {
        const fileContent = createPartFromUri(file2.uri, file2.mimeType);
        content.push(fileContent);
    }

    const response = await ai.models.generateContent({
        model: 'gemini-2.5-flash',
        contents: content,
    });

    console.log(response.text);
}

main();

Go

package main

import (
    "context"
    "fmt"
    "io"
    "net/http"
    "os"
    "google.golang.org/genai"
)

func main() {

    ctx := context.Background()
    client, _ := genai.NewClient(ctx, &genai.ClientConfig{
        APIKey:  os.Getenv("GEMINI_API_KEY"),
        Backend: genai.BackendGeminiAPI,
    })

    docUrl1 := "https://arxiv.org/pdf/2312.11805"
    docUrl2 := "https://arxiv.org/pdf/2403.05530"
    localPath1 := "doc1_downloaded.pdf"
    localPath2 := "doc2_downloaded.pdf"

    respHttp1, _ := http.Get(docUrl1)
    defer respHttp1.Body.Close()

    outFile1, _ := os.Create(localPath1)
    _, _ = io.Copy(outFile1, respHttp1.Body)
    outFile1.Close()

    respHttp2, _ := http.Get(docUrl2)
    defer respHttp2.Body.Close()

    outFile2, _ := os.Create(localPath2)
    _, _ = io.Copy(outFile2, respHttp2.Body)
    outFile2.Close()

    uploadConfig1 := &genai.UploadFileConfig{MIMEType: "application/pdf"}
    uploadedFile1, _ := client.Files.UploadFromPath(ctx, localPath1, uploadConfig1)

    uploadConfig2 := &genai.UploadFileConfig{MIMEType: "application/pdf"}
    uploadedFile2, _ := client.Files.UploadFromPath(ctx, localPath2, uploadConfig2)

    promptParts := []*genai.Part{
        genai.NewPartFromURI(uploadedFile1.URI, uploadedFile1.MIMEType),
        genai.NewPartFromURI(uploadedFile2.URI, uploadedFile2.MIMEType),
        genai.NewPartFromText("What is the difference between each of the " +
                              "main benchmarks between these two papers? " +
                              "Output these in a table."),
    }
    contents := []*genai.Content{
        genai.NewContentFromParts(promptParts, genai.RoleUser),
    }

    modelName := "gemini-2.5-flash"
    result, _ := client.Models.GenerateContent(
        ctx,
        modelName,
        contents,
        nil,
    )

    fmt.Println(result.Text())
}

REST

DOC_URL_1="https://arxiv.org/pdf/2312.11805"
DOC_URL_2="https://arxiv.org/pdf/2403.05530"
DISPLAY_NAME_1="Gemini_paper"
DISPLAY_NAME_2="Gemini_1.5_paper"
PROMPT="What is the difference between each of the main benchmarks between these two papers? Output these in a table."

# Function to download and upload a PDF
upload_pdf() {
  local doc_url="$1"
  local display_name="$2"

  # Download the PDF
  wget -O "${display_name}.pdf" "${doc_url}"

  local MIME_TYPE=$(file -b --mime-type "${display_name}.pdf")
  local NUM_BYTES=$(wc -c < "${display_name}.pdf")

  echo "MIME_TYPE: ${MIME_TYPE}"
  echo "NUM_BYTES: ${NUM_BYTES}"

  local tmp_header_file=upload-header.tmp

  # Initial resumable request
  curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
    -D "${tmp_header_file}" \
    -H "X-Goog-Upload-Protocol: resumable" \
    -H "X-Goog-Upload-Command: start" \
    -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
    -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
    -H "Content-Type: application/json" \
    -d "{'file': {'display_name': '${display_name}'}}" 2> /dev/null

  local upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
  rm "${tmp_header_file}"

  # Upload the PDF
  curl "${upload_url}" \
    -H "Content-Length: ${NUM_BYTES}" \
    -H "X-Goog-Upload-Offset: 0" \
    -H "X-Goog-Upload-Command: upload, finalize" \
    --data-binary "@${display_name}.pdf" 2> /dev/null > "file_info_${display_name}.json"

  local file_uri=$(jq ".file.uri" "file_info_${display_name}.json")
  echo "file_uri for ${display_name}: ${file_uri}"

  # Clean up the downloaded PDF
  rm "${display_name}.pdf"

  echo "${file_uri}"
}

# Upload the first PDF
file_uri_1=$(upload_pdf "${DOC_URL_1}" "${DISPLAY_NAME_1}")

# Upload the second PDF
file_uri_2=$(upload_pdf "${DOC_URL_2}" "${DISPLAY_NAME_2}")

# Now generate content using both files
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"file_data": {"mime_type": "application/pdf", "file_uri": '$file_uri_1'}},
          {"file_data": {"mime_type": "application/pdf", "file_uri": '$file_uri_2'}},
          {"text": "'$PROMPT'"}
        ]
      }]
    }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json

Detalles técnicos

Gemini admite un máximo de 1,000 páginas de documentos. Cada página del documento equivale a 258 tokens.

Si bien no hay límites específicos para la cantidad de píxeles en un documento, además de la ventana de contexto del modelo, las páginas más grandes se reducen a una resolución máxima de 3,072 x 3,072, a la vez que conservan su relación de aspecto original, mientras que las páginas más pequeñas se amplían a 768 x 768 píxeles. No hay reducción de costos para las páginas con tamaños más pequeños, aparte del ancho de banda, ni mejora del rendimiento para las páginas con mayor resolución.

Tipos de documentos

Técnicamente, puedes pasar otros tipos de MIME para la comprensión de documentos, como TXT, Markdown, HTML, XML, etcétera. Sin embargo, la visión de documentos solo comprende los PDFs de manera significativa. Otros tipos se extraerán como texto puro, y el modelo no podrá interpretar lo que vemos en la renderización de esos archivos. Se perderán las especificaciones de cada tipo de archivo, como gráficos, diagramas, etiquetas HTML, formato Markdown, etcétera.

Prácticas recomendadas

Para lograr resultados óptimos, haz lo siguiente:

  • Rota las páginas a la orientación correcta antes de subirlas.
  • Evita las páginas borrosas.
  • Si usas una sola página, coloca la instrucción de texto después de la página.

¿Qué sigue?

Para obtener más información, consulta los siguientes recursos:

  • Estrategias de instrucciones con archivos: La API de Gemini admite instrucciones con datos de texto, imagen, audio y video, lo que también se conoce como instrucciones multimodales.
  • Instrucciones del sistema: Las instrucciones del sistema te permiten dirigir el comportamiento del modelo según tus necesidades y casos de uso específicos.