הבנת מסמכים

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)

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();

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"}
    ]
  }'

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)

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();

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

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)

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();

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

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)

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();

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

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))

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();

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

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)

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