Pemahaman dokumen

Model Gemini dapat memproses dokumen dalam format PDF, menggunakan visi bawaan untuk memahami seluruh konteks dokumen. Hal ini tidak hanya sekadar mengekstrak teks, tetapi juga memungkinkan Gemini untuk:

  • Menganalisis dan menginterpretasikan konten, termasuk teks, gambar, diagram, grafik, dan tabel, bahkan dalam dokumen panjang hingga 1.000 halaman.
  • Mengekstrak informasi ke dalam format output terstruktur.
  • Meringkas dan menjawab pertanyaan berdasarkan elemen visual dan tekstual dalam dokumen.
  • Mentranskripsikan konten dokumen (misalnya, ke HTML), dengan mempertahankan tata letak dan pemformatan, untuk digunakan dalam aplikasi hilir.

Anda juga dapat meneruskan dokumen non-PDF dengan cara yang sama, tetapi Gemini akan melihatnya sebagai teks biasa yang akan menghilangkan konteks seperti diagram atau pemformatan.

Meneruskan data PDF secara inline

Anda dapat meneruskan data PDF secara inline dalam permintaan. Metode ini paling cocok untuk dokumen yang lebih kecil atau pemrosesan sementara yang tidak memerlukan referensi file dalam permintaan berikutnya. Sebaiknya gunakan Files API untuk dokumen yang lebih besar yang perlu Anda rujuk dalam interaksi multi-turn untuk meningkatkan latensi permintaan dan mengurangi penggunaan bandwidth.

Contoh berikut menunjukkan cara meneruskan data PDF secara inline:

Python

from google import genai
import base64

client = genai.Client()

with open('path/to/document.pdf', 'rb') as f:
    pdf_bytes = f.read()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {
            "type": "document",
            "data": base64.b64encode(pdf_bytes).decode('utf-8'),
            "mime_type": "application/pdf"
        },
        {"type": "text", "text": "Summarize this document"}
    ]
)

print(interaction.steps[-1].content[0].text)

JavaScript

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

const ai = new GoogleGenAI({});

async function main() {
    const pdfData = fs.readFileSync("path/to/document.pdf", {
        encoding: "base64"
    });

    const interaction = await ai.interactions.create({
        model: "gemini-3-flash-preview",
        input: [
            { type: "text", text: "Summarize this document" },
            {
                type: "document",
                data: pdfData,
                mimeType: "application/pdf"
            }
        ]
    });
    console.log(interaction.steps.at(-1).content[0].text);
}

main();

REST

PDF_PATH="path/to/document.pdf"

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": [
      {
        "type": "document",
        "data": "'$(base64 $B64FLAGS $PDF_PATH)'",
        "mimeType": "application/pdf"
      },
      {"type": "text", "text": "Summarize this document"}
    ]
  }'

Anda juga dapat mengupload file PDF lokal untuk diproses:

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="file.pdf")

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "document", "uri": uploaded_file.uri, "mime_type": uploaded_file.mime_type},
        {"type": "text", "text": "Summarize this document"}
    ]
)
print(interaction.steps[-1].content[0].text)

JavaScript

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

const ai = new GoogleGenAI({});

async function main() {
    const uploadedFile = await ai.files.upload({
        file: "file.pdf",
        config: { mimeType: "application/pdf" }
    });

    const interaction = await ai.interactions.create({
        model: "gemini-3-flash-preview",
        input: [
            { type: "text", text: "Summarize this document" },
            {
                type: "document",
                uri: uploadedFile.uri,
                mimeType: uploadedFile.mimeType
            }
        ]
    });
    console.log(interaction.steps.at(-1).content[0].text);
}

main();

Mengupload PDF menggunakan Files API

Sebaiknya gunakan Files API untuk file yang lebih besar atau saat Anda ingin menggunakan kembali dokumen di beberapa permintaan. Hal ini meningkatkan latensi permintaan dan mengurangi penggunaan bandwidth dengan memisahkan upload file dari permintaan model.

PDF besar dari URL

Gunakan File API untuk menyederhanakan upload dan pemrosesan file PDF besar dari URL:

Python

from google import genai
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"

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "document", "uri": sample_doc.uri, "mime_type": sample_doc.mime_type},
        {"type": "text", "text": prompt}
    ]
)
print(interaction.steps[-1].content[0].text)

JavaScript

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

const ai = new GoogleGenAI({});

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.');
    }

    const interaction = await ai.interactions.create({
        model: 'gemini-3-flash-preview',
        input: [
            { type: "document", uri: file.uri, mimeType: file.mimeType },
            { type: "text", text: "Summarize this document" }
        ],
    });

    console.log(interaction.steps.at(-1).content[0].text);

}

main();

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 "https://generativelanguage.googleapis.com/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 create an interaction using that file
curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "model": "gemini-3-flash-preview",
      "input": [
        {"type": "text", "text": "'$PROMPT'"},
        {"type": "document", "uri": '$file_uri', "mimeType": "application/pdf"}
      ]
    }' 2> /dev/null > response.json

cat response.json
echo

jq ".steps[-1].content[0].text" response.json

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

PDF besar yang disimpan secara lokal

Python

from google import genai
import pathlib

client = genai.Client()

# Upload the PDF using the File API
file_path = pathlib.Path('large_file.pdf')
sample_file = client.files.upload(
    file=file_path,
)

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "document", "uri": sample_file.uri, "mime_type": sample_file.mime_type},
        {"type": "text", "text": "Summarize this document"}
    ]
)
print(interaction.steps[-1].content[0].text)

JavaScript

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

const ai = new GoogleGenAI({});

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.');
    }

    const interaction = await ai.interactions.create({
        model: 'gemini-3-flash-preview',
        input: [
            { type: "document", uri: file.uri, mimeType: file.mimeType },
            { type: "text", text: "Summarize this document" }
        ],
    });

    console.log(interaction.steps.at(-1).content[0].text);

}

main();

REST

PDF_PATH="path/to/large_file.pdf"
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 "https://generativelanguage.googleapis.com/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 create an interaction using that file
curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "model": "gemini-3-flash-preview",
      "input": [
        {"type": "document", "uri": '$file_uri', "mimeType": "application/pdf"},
        {"type": "text", "text": "Can you add a few more lines to this poem?"}
      ]
    }' 2> /dev/null > response.json

cat response.json
echo

jq ".steps[-1].content[0].text" response.json

Anda dapat memverifikasi bahwa API berhasil menyimpan file yang diupload dan mendapatkan metadatanya dengan memanggil files.get. Hanya name (dan dengan demikian, uri) yang unik.

Python

from google import genai
import pathlib

client = genai.Client()

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

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

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?key=$GEMINI_API_KEY > file_info.json
# Print some information about the file you got
name=$(jq ".file.name" file_info.json)
echo name=$name
file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

Meneruskan beberapa PDF

Gemini API dapat memproses beberapa dokumen PDF (hingga 1.000 halaman) dalam satu permintaan, selama ukuran gabungan dokumen dan perintah teks tetap berada dalam jendela konteks model.

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."

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "document", "uri": sample_pdf_1.uri, "mime_type": sample_pdf_1.mime_type},
        {"type": "document", "uri": sample_pdf_2.uri, "mime_type": sample_pdf_2.mime_type},
        {"type": "text", "text": prompt}
    ]
)

print(interaction.steps[-1].content[0].text)

JavaScript

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

const ai = new GoogleGenAI({});

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 file1 = await uploadRemotePDF("https://arxiv.org/pdf/2312.11805", "PDF 1");
    const file2 = await uploadRemotePDF("https://arxiv.org/pdf/2403.05530", "PDF 2");

    const interaction = await ai.interactions.create({
        model: 'gemini-3-flash-preview',
        input: [
            { type: "document", uri: file1.uri, mimeType: file1.mimeType },
            { type: "document", uri: file2.uri, mimeType: file2.mimeType },
            { type: "text", text: "What is the difference between each of the main benchmarks between these two papers? Output these in a table." }
        ],
    });

    console.log(interaction.steps.at(-1).content[0].text);
}

main();

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 "https://generativelanguage.googleapis.com/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 create an interaction using both files
curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "model": "gemini-3-flash-preview",
      "input": [
        {"type": "document", "uri": '$file_uri_1', "mimeType": "application/pdf"},
        {"type": "document", "uri": '$file_uri_2', "mimeType": "application/pdf"},
        {"type": "text", "text": "'$PROMPT'"}
      ]
    }' 2> /dev/null > response.json

cat response.json
echo

jq ".steps[-1].content[0].text" response.json

Detail teknis

Gemini mendukung file PDF hingga 50 MB atau 1.000 halaman. Batas ini berlaku untuk data inline dan upload Files API. Setiap halaman dokumen setara dengan 258 token.

Meskipun tidak ada batasan khusus untuk jumlah piksel dalam dokumen selain jendela konteks model, halaman yang lebih besar akan diperkecil hingga resolusi maksimum 3072 x 3072 dengan mempertahankan rasio aspek aslinya, sedangkan halaman yang lebih kecil akan diperbesar hingga 768 x 768 piksel. Tidak ada pengurangan biaya untuk halaman dengan ukuran yang lebih kecil, selain bandwidth, atau peningkatan performa untuk halaman dengan resolusi yang lebih tinggi.

Model Gemini 3

Gemini 3 memperkenalkan kontrol terperinci atas pemrosesan visi multimodal dengan parameter media_resolution. Sekarang Anda dapat menyetel resolusi ke rendah, sedang, atau tinggi untuk setiap bagian media. Dengan penambahan ini, pemrosesan dokumen PDF telah diperbarui:

  1. Penyertaan teks native: Teks yang disematkan secara native dalam PDF diekstrak dan diberikan ke model.
  2. Penagihan & pelaporan token:
    • Anda tidak dikenai biaya untuk token yang berasal dari teks native yang diekstrak dalam PDF.
    • Di bagian usage_metadata respons API, token yang dihasilkan dari pemrosesan halaman PDF (sebagai gambar) kini dihitung dalam modalitas IMAGE, bukan modalitas DOCUMENT terpisah seperti pada beberapa versi sebelumnya.

Jenis dokumen

Secara teknis, Anda dapat meneruskan jenis MIME lain untuk pemahaman dokumen, seperti TXT, Markdown, HTML, XML, dll. Namun, visi dokumen hanya dapat memahami PDF secara efektif. Jenis lainnya akan diekstrak sebagai teks murni, dan model tidak akan dapat menafsirkan apa yang kita lihat dalam rendering file tersebut. Semua spesifikasi jenis file seperti diagram, HTML tag, pemformatan Markdown, dll., akan hilang.

Untuk mempelajari metode input file lainnya, lihat panduan Metode input file.

Praktik terbaik

Untuk hasil terbaik:

  • Putar halaman ke orientasi yang benar sebelum mengupload.
  • Hindari halaman yang buram.
  • Jika menggunakan satu halaman, tempatkan perintah teks setelah halaman.

Langkah berikutnya

Untuk mempelajari lebih lanjut, lihat referensi berikut:

  • Strategi perintah file: Gemini API mendukung perintah dengan data teks, gambar, audio, dan video, yang juga dikenal sebagai perintah multimodal.
  • Petunjuk sistem: Petunjuk sistem memungkinkan Anda mengarahkan perilaku model berdasarkan kebutuhan dan kasus penggunaan spesifik Anda.