文件解讀

Gemini 模型可處理 PDF 格式的文件，並運用原生視覺功能瞭解整個文件的脈絡。這項功能不只是擷取文字，還能讓 Gemini 執行下列動作：

  • 分析及解讀內容，包括文字、圖片、圖表、圖表和表格，即使是長達 1000 頁的文件也沒問題。
  • 以結構化輸出格式擷取資訊。
  • 根據文件中的圖像和文字元素，產生摘要及回答問題。
  • 轉錄文件內容 (例如轉錄為 HTML)，保留版面配置和格式，供下游應用程式使用。

傳遞內嵌 PDF 資料

您可以在對 generateContent 的要求中傳遞內嵌 PDF 資料。 如要上傳大小在 20 MB 以下的 PDF 酬載，您可以選擇上傳以 base64 編碼的文件，或是直接上傳儲存在本機的檔案。

以下範例說明如何從網址擷取 PDF，並轉換為位元組以供處理：

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"

您也可以從本機檔案讀取 PDF 以進行處理：

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())
}

使用 File API 上傳 PDF

如要上傳較大的文件，請使用 File API。如果要求總大小 (包括檔案、文字提示、系統指令等) 超過 20 MB，請一律使用 File API。

呼叫 media.upload，使用 File API 上傳檔案。下列程式碼會上傳文件檔案，然後在呼叫 models.generateContent 時使用該檔案。

從網址匯入大型 PDF 檔案

使用 File API 簡化從網址上傳及處理大型 PDF 檔案的程序：

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"

儲存在本機的大型 PDF

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

您可以呼叫 files.get，確認 API 是否已成功儲存上傳的檔案，並取得檔案的中繼資料。只有 name (以及延伸的 uri) 是獨一無二的。

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

傳遞多個 PDF

只要文件和文字提示的總大小在模型脈絡窗口內，Gemini API 就能在單一要求中處理多個 PDF 文件 (最多 1000 頁)。

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

技術詳細資料

Gemini 最多可處理 1,000 頁文件。每頁文件相當於 258 個權杖。

除了模型的內容視窗外，文件中的像素數量沒有具體限制，但較大的頁面會縮放至 3072x3072 像素的最大解析度，同時保留原始長寬比，較小的頁面則會放大至 768x768 像素。如果頁面大小較小，除了頻寬外，不會有任何成本降低；如果頁面解析度較高，也不會提升效能。

文件類型

從技術上來說，您可以傳遞其他 MIME 類型，以瞭解文件內容，例如 TXT、Markdown、HTML、XML 等。不過，文件視覺 只能有意義地瞭解 PDF。其他類型則會擷取為純文字，模型無法解讀這些檔案的轉譯內容。所有檔案類型專屬內容都會遺失，例如圖表、HTML 標記、Markdown 格式等。

最佳做法

為確保最佳成效：

  • 請先將頁面轉向正確方向，再上傳檔案。
  • 避免頁面模糊。
  • 如果使用單頁，請將文字提示放在頁面後方。

後續步驟

如要進一步瞭解相關內容，請參閱下列資源：

  • 檔案提示策略：Gemini API 支援使用文字、圖片、音訊和影片資料提示，也稱為多模態提示。
  • 系統指令： 系統指令可根據您的特定需求和用途，決定模型行為。