Document understanding

I modelli Gemini possono elaborare documenti in formato PDF utilizzando la visione nativa per comprendere i contesti dei documenti interi. Questa funzionalità va oltre la semplice estrazione del testo e consente a Gemini di:

  • Analizza e interpreta contenuti, inclusi testo, immagini, diagrammi, grafici e tabelle, anche in documenti lunghi fino a 1000 pagine.
  • Estrai le informazioni in formati di output strutturato.
  • Riassumere e rispondere a domande basate sugli elementi visivi e testuali di un documento.
  • Trascrivi i contenuti del documento (ad es. in HTML), conservando i layout e la formattazione, per l'utilizzo nelle applicazioni downstream.

Trasferimento di dati PDF incorporati

Puoi trasmettere i dati PDF incorporati nella richiesta a generateContent. Per i payload PDF di dimensioni inferiori a 20 MB, puoi scegliere tra il caricamento di documenti codificati in base64 o il caricamento diretto di file archiviati localmente.

L'esempio seguente mostra come recuperare un PDF da un URL e convertirlo in byte per l'elaborazione:

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();

Vai

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"

Puoi anche leggere un PDF da un file locale per l'elaborazione:

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();

Vai

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())
}

Caricamento di PDF utilizzando l'API File

Puoi utilizzare l'API File per caricare documenti più grandi. Utilizza sempre l'API File quando le dimensioni totali della richiesta (inclusi i file, il prompt di testo, le istruzioni di sistema e così via) sono superiori a 20 MB.

Chiama media.upload per caricare un file utilizzando l'API File. Il seguente codice carica un file di documento e poi lo utilizza in una chiamata a models.generateContent.

PDF di grandi dimensioni da URL

Utilizza l'API File per semplificare il caricamento e l'elaborazione di file PDF di grandi dimensioni dagli URL:

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();

Vai

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"

PDF di grandi dimensioni archiviati localmente

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();

Vai

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

Puoi verificare che l'API abbia memorizzato correttamente il file caricato e recuperare i relativi metadati chiamando files.get. Solo name (e, per estensione, uri) sono univoci.

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

Invio di più PDF

L'API Gemini è in grado di elaborare più documenti PDF (fino a 1000 pagine) in un'unica richiesta, a condizione che le dimensioni combinate dei documenti e del prompt di testo rimangano all'interno della finestra contestuale del modello.

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();

Vai

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

Dettagli tecnici

Gemini supporta un massimo di 1000 pagine di documenti. Ogni pagina del documento equivale a 258 token.

Sebbene non esistano limiti specifici al numero di pixel in un documento, oltre alla finestra contestuale del modello, le pagine più grandi vengono ridimensionate a una risoluzione massima di 3072 x 3072 mantenendo le proporzioni originali, mentre le pagine più piccole vengono ridimensionate a 768 x 768 pixel. Non è prevista alcuna riduzione dei costi per le pagine di dimensioni inferiori, ad eccezione della larghezza di banda, né alcun miglioramento delle prestazioni per le pagine a risoluzione più elevata.

Tipi di documenti

Tecnicamente, puoi passare altri tipi MIME per la comprensione dei documenti, come TXT, Markdown, HTML, XML e così via. Tuttavia, Document Vision comprende in modo significativo solo i PDF. Gli altri tipi verranno estratti come testo normale e il modello non sarà in grado di interpretare ciò che vediamo nel rendering di questi file. Verranno persi tutti i dettagli specifici del tipo di file, come grafici, diagrammi, tag HTML, formattazione Markdown e così via.

Best practice

Per ottenere risultati ottimali:

  • Ruota le pagine nell'orientamento corretto prima del caricamento.
  • Evita pagine sfocate.
  • Se utilizzi una sola pagina, inserisci il prompt di testo dopo la pagina.

Passaggi successivi

Per saperne di più, consulta le seguenti risorse:

  • Strategie di prompt dei file: l'API Gemini supporta i prompt con dati di testo, immagine, audio e video, noti anche come prompt multimodali.
  • Istruzioni di sistema: le istruzioni di sistema ti consentono di orientare il comportamento del modello in base alle tue esigenze e ai tuoi casi d'uso specifici.