הבנת מסמכים

מודלים של Gemini יכולים לעבד מסמכים בפורמט PDF, באמצעות ראייה מובנית כדי להבין את ההקשרים של מסמכים שלמים. היכולת הזו חורגת ממיצוי טקסט בלבד, ומאפשרת ל-Gemini:

  • ניתוח ופירוש של תוכן, כולל טקסט, תמונות, דיאגרמות, תרשימים וטבלאות, גם במסמכים ארוכים של עד 1, 000 עמודים.
  • חילוץ מידע לפורמטים של פלט מובנה.
  • לסכם מסמך ולענות על שאלות על סמך הרכיבים החזותיים והטקסטואליים שבו.
  • תמלול תוכן של מסמך (למשל ל-HTML), תוך שמירה על הפריסות והעיצוב, לשימוש באפליקציות במורד הזרם.

אפשר גם להעביר מסמכים שאינם PDF באותו אופן, אבל Gemini יראה אותם כטקסט רגיל, כך שלא יהיה הקשר כמו תרשימים או עיצוב.

העברת נתוני PDF בתוך השורה

אפשר להעביר נתוני PDF בתוך הבקשה. האפשרות הזו מתאימה במיוחד למסמכים קטנים או לעיבוד זמני שבו אין צורך להפנות לקובץ בבקשות הבאות. מומלץ להשתמש ב-Files API עבור מסמכים גדולים שצריך להתייחס אליהם באינטראקציות רב-שלביות, כדי לשפר את זמן האחזור של הבקשה ולהקטין את השימוש ברוחב הפס.

בדוגמה הבאה אפשר לראות איך מעבירים נתוני PDF בשורה:

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-3.6-flash",
    input=[
        {
            "type": "document",
            "data": base64.b64encode(pdf_bytes).decode('utf-8'),
            "mime_type": "application/pdf"
        },
        {"type": "text", "text": "Summarize this document"}
    ]
)

print(interaction.output_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-3.6-flash",
        input: [
            { type: "text", text: "Summarize this document" },
            {
                type: "document",
                data: pdfData,
                mime_type: "application/pdf"
            }
        ]
    });
    console.log(interaction.output_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: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.6-flash",
    "input": [
      {
        "type": "document",
        "data": "'$(base64 $B64FLAGS $PDF_PATH)'",
        "mime_type": "application/pdf"
      },
      {"type": "text", "text": "Summarize this document"}
    ]
  }'

אפשר גם להעלות קובץ PDF מקומי לעיבוד:

Python

from google import genai

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3.6-flash",
    input=[
        {"type": "document", "uri": uploaded_file.uri, "mime_type": uploaded_file.mime_type},
        {"type": "text", "text": "Summarize this document"}
    ]
)
print(interaction.output_text)

JavaScript

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

const ai = new GoogleGenAI({});

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

    const interaction = await ai.interactions.create({
        model: "gemini-3.6-flash",
        input: [
            { type: "text", text: "Summarize this document" },
            {
                type: "document",
                uri: uploadedFile.uri,
                mime_type: uploadedFile.mime_type
            }
        ]
    });
    console.log(interaction.output_text);
}

main();

REST

PDF_PATH="file.pdf"
NUM_BYTES=$(wc -c < "${PDF_PATH}")
DISPLAY_NAME="file.pdf"
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=$(jq -r ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now create an interaction using that file
curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "model": "gemini-3.6-flash",
      "input": [
        {"type": "document", "uri": "'$file_uri'", "mime_type": "application/pdf"},
        {"type": "text", "text": "Summarize this document"}
      ]
    }' 2> /dev/null > response.json

cat response.json
echo

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

העלאת קובצי PDF באמצעות Files API

מומלץ להשתמש ב-Files API לקבצים גדולים יותר או כשרוצים לעשות שימוש חוזר במסמך בכמה בקשות. הפעולה הזו משפרת את זמן האחזור של הבקשות ומצמצמת את השימוש ברוחב הפס, כי היא מפרידה בין העלאת הקובץ לבין בקשות המודל.

קובצי PDF גדולים מכתובות URL

אפשר להשתמש ב-File API כדי לפשט את ההעלאה והעיבוד של קובצי PDF גדולים מכתובות URL:

Python

from google import genai
import io
import httpx

client = genai.Client()

long_context_pdf_path = "https://arxiv.org/pdf/2312.11805"

doc_io = io.BytesIO(httpx.get(long_context_pdf_path).content)

sample_doc = client.files.upload(
  file=doc_io,
  config=dict(
    mime_type='application/pdf')
)

prompt = "Summarize this document"

interaction = client.interactions.create(
    model="gemini-3.6-flash",
    input=[
        {"type": "document", "uri": sample_doc.uri, "mime_type": sample_doc.mime_type},
        {"type": "text", "text": prompt}
    ]
)
print(interaction.output_text)

JavaScript

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

const ai = new GoogleGenAI({});

async function main() {

    const pdfBuffer = await fetch("https://arxiv.org/pdf/2312.11805")
        .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',
        },
    });

    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-3.6-flash',
        input: [
            { type: "document", uri: file.uri, mime_type: file.mime_type },
            { type: "text", text: "Summarize this document" }
        ],
    });

    console.log(interaction.output_text);

}

main();

REST

PDF_PATH="https://arxiv.org/pdf/2312.11805"
DISPLAY_NAME="Gemini_paper"
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=${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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${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 -r ".file.uri" file_info.json)
echo "file_uri: ${file_uri}"

# Create payload JSON file for safety
cat << EOF > payload.json
{
  "model": "gemini-3.6-flash",
  "input": [
    {"type": "text", "text": "${PROMPT}"},
    {"type": "document", "uri": "${file_uri}", "mime_type": "application/pdf"}
  ]
}
EOF

# 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 @payload.json 2> /dev/null > response.json

cat response.json
echo

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

# Clean up
rm "${DISPLAY_NAME}.pdf"
rm payload.json

קובצי PDF גדולים שמאוחסנים באופן מקומי

Python

from google import genai
import pathlib

client = genai.Client()

file_path = pathlib.Path('large_file.pdf')
sample_file = client.files.upload(
    file=file_path,
)

interaction = client.interactions.create(
    model="gemini-3.6-flash",
    input=[
        {"type": "document", "uri": sample_file.uri, "mime_type": sample_file.mime_type},
        {"type": "text", "text": "Summarize this document"}
    ]
)
print(interaction.output_text)

JavaScript

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

const ai = new GoogleGenAI({});

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

    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-3.6-flash',
        input: [
            { type: "document", uri: file.uri, mime_type: file.mime_type },
            { type: "text", text: "Summarize this document" }
        ],
    });

    console.log(interaction.output_text);

}

main();

REST

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

# Now create an interaction using that file
curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "model": "gemini-3.6-flash",
      "input": [
        {"type": "document", "uri": "'$file_uri'", "mime_type": "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 -r ".steps[-1].content[0].text" response.json

כדי לוודא שה-API שמר בהצלחה את הקובץ שהועלה ולקבל את המטא-נתונים שלו, אפשר לקרוא ל-files.get. רק name (ומכאן גם uri) הם ייחודיים.

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))

JavaScript

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

const ai = new GoogleGenAI({});

async function main() {
    fs.writeFileSync("example.pdf", "hello");

    const file = await ai.files.upload({
        file: "example.pdf",
        config: { mime_type: "application/pdf" }
    });

    const fileInfo = await ai.files.get({ name: file.name });
    console.log(fileInfo);
}

main();

REST

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

העברת כמה קובצי PDF

‫Gemini API יכול לעבד כמה מסמכי PDF (עד 1,000 דפים) בבקשה אחת, כל עוד הגודל המשולב של המסמכים וההנחיה הטקסטואלית לא חורג מחלון ההקשר של המודל.

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"

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-3.6-flash",
    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.output_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,
        },
    });

    let getFile = await ai.files.get({ name: file.name });
    while (getFile.state === 'PROCESSING') {
        getFile = await