文档理解

Gemini 模型可以处理 PDF 格式的文档，并使用原生视觉功能来理解整个文档上下文。这不仅仅是提取文本，还让 Gemini 能够：

  • 分析和解读内容，包括文本、图片、图表和表格，即使是长达 1000 页的文档也不例外。
  • 将信息提取为结构化输出格式。
  • 根据文档中的视觉元素和文本元素进行总结并回答问题。
  • 转录文档内容（例如转录为 HTML），保留布局和格式，以便在下游应用中使用。

您还可以采用相同的方式传递非 PDF 文档，但 Gemini 会将其视为普通文本，这样会消除图表或格式等上下文。

以内嵌方式传递 PDF 数据

您可以在请求中以内嵌方式传递 PDF 数据。这最适合较小的文档或临时处理，因为您无需在后续请求中引用该文件。对于需要在多轮互动中引用的较大文档，我们建议您使用 Files API 以 缩短请求延迟时间和减少带宽用量。

以下示例展示了如何以内嵌方式传递 PDF 数据：

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-3.8-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-3.8-flash",
        input: [
            { type: "text", text: "Summarize this document" },
            {
                type: "document",
                data: pdfData,
                mime_type: "application/pdf"
            }
        ]
    });
    console.log(interaction.output_text);
}

main();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.DocumentContent;
import com.google.genai.gaos.models.interactions.DocumentContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent = TextContent.builder().text("Summarize this document.").build();
Content docContent =
    DocumentContent.builder()
        .uri("gs://cloud-samples-data/generative-ai/pdf/sample.pdf")
        .mimeType(DocumentContentMimeType.APPLICATION_PDF)
   <     .b>uild();

ListContent contents = Arrays.asList(textContent, docContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

REST

PDF_PATH="path/to/document.pdf"

if [[ "$(bas>&e64 --version 21)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": [
      {
        "type": "document",
        "data": "';$(base64 $B64FLAGS $PDF_PATH)'",
        "mime_type": "application/pdf"
      },
      {"type": "text", "text": "Summarize this document"}
    ]
  }'

您还可以上传本地 PDF 文件进行处理：

Python

from google import genai

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "document", "uri": uploaded_file.uri, "mime_type": uploaded_file.mime_type},
        {"type": "text&quot;, "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-3.8-flash",
        input: [
            { type: "text", text: "Summarize this document" },
            {
                type: "document",
                uri: uploadedFile.uri,
                mime_type: uploadedFile.mime_type
            }
        ]
    });
    console.log(interaction.output_text);
}

main();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.DocumentContent;
import com.google.genai.gaos.models.interactions.DocumentContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent = TextContent.builder().text("Summarize this document.").build();
Content docContent =
    DocumentContent.builder()
        .uri("gs://cloud-samples-data/generative-ai/pdf/sample.pdf")
        .mimeType(DocumentContentMimeType.APPLICATION_PDF)
   <     .b>uild();

ListContent contents = Arrays.asList(textContent, docContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

REST

PDF_PATH="file.pdf"
NUM_BYTE<S=$(wc -c  "${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: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: application/pdf" \
  -H "Con>tent-Type: application/json" \
  -d "{'file': {'display_name': '${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.
c>url "$>{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: $GEMINI_API_KEY" \
    -H 'Content-Type>: applicati>on/json' \
    -X POST \
    -d '{
      "model": "gemini-3.8-flash",
      "input": [
        {"type": "document", "uri": "'$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

使用 Files API 上传 PDF

对于较大的文件，或者当您打算在多个请求中重复使用文档时，我们建议您使用 Files API。这样可以将文件上传与模型请求分离，从而缩短请求延迟时间和减少带宽用量。

通过网址上传大型 PDF

使用 File API 可简化通过网址上传和处理大型 PDF 文件的过程：

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-3.8-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 s>econds');

        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-3.8-flash',
        input: [
            { type: "document", uri: file.uri, mime_type: file.mime_type },
            { type: "text", text: "Summarize this document" }
        ],
    });

    console.log(interaction.output_text);

}

main();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.DocumentContent;
import com.google.genai.gaos.models.interactions.DocumentContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent = TextContent.builder().text("Summarize this document.").build();
Content docContent =
    DocumentContent.builder()
        .uri("gs://cloud-samples-data/generative-ai/pdf/sample.pdf")
        .mimeType(DocumentContentMimeType.APPLICATION_PDF)
   <     .b>uild();

ListContent contents = Arrays.asList(textContent, docContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

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=$(file -b --m<ime-type "${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-Upl>oad-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-3.8-flash",
  "input": [
    {"type": "text&q>uot;, ">;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

上传本地存储的大型 PDF

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-3.8-flash",
    input=[
        {"type": "document", "uri": sample_file.uri, "mime_type": sample_file.mime_type},
        {"type": "text&quot;, "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-3.8-flash',
        input: [
            { type: "document", uri: file.uri, mime_type: file.mime_type },
            { type: "text", text: "Summarize this document" }
        ],
    });

    console.log(interaction.output_text);

}

main();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.DocumentContent;
import com.google.genai.gaos.models.interactions.DocumentContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent = TextContent.builder().text("Summarize this document.").build();
Content docContent =
    DocumentContent.builder()
        .uri("gs://cloud-samples-data/generative-ai/pdf/sample.pdf")
        .mimeType(DocumentContentMimeType.APPLICATION_PDF)
   <     .b>uild();

ListContent contents = Arrays.asList(textContent, docContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

REST

PDF_PATH="large_file.pdf"
NUM_BYTE<S=$(wc -c  "${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_ur>l}" \
  -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: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
   > -X POST \
>    -d '{
      "model": "gemini-3.8-flash",
      "input&quot;: [
        {"type": "document", "uri": "'$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

您可以通过调用 files.get 来验证 API 是否已成功存储上传的文件并获取其 元数据。只有 name（以及相应的 uri）是唯一的。

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();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.DocumentContent;
import com.google.genai.gaos.models.interactions.DocumentContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent = TextContent.builder().text("Summarize this document.").build();
Content docContent =
    DocumentContent.builder()
        .uri("gs://cloud-samples-data/generative-ai/pdf/sample.pdf")
        .mimeType(DocumentContentMimeType.APPLICATION_PDF)
   <     .b>uild();

ListContent contents = Arrays.asList(textContent, docContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

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=$G>EMINI_API_KEY"  file_info.json
# Print some information about the file you got
name=$(jq -r ".name" file_info.json)
echo name=$name
file_uri=$(jq -r ".uri" file_info.json)
echo file_uri=$file_uri

传递多个 PDF

Gemini API 能够在单个请求中处理多个 PDF 文档（最多 1000 页），前提是文档和文本提示的总大小不超过模型的上下文窗口大小。

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-3.8-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((r>esponse) = 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 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-3.8-flash',
        input: [
            { type: "document", uri: file1.uri, mime_type: file1.mime_type },
            { type: "document", uri: file2.uri, mime_type: file2.mime_type },
            { 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.output_text);
}

main();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.DocumentContent;
import com.google.genai.gaos.models.interactions.DocumentContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent = TextContent.builder().text("Summarize this document.").build();
Content docContent =
    DocumentContent.builder()
        .uri("gs://cloud-samples-data/generative-ai/pdf/sample.pdf")
        .mimeType(DocumentContentMimeType.APPLICATION_PDF)
   <     .b>uild();

ListContent contents = Arrays.asList(textContent, docContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

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=&q>&uot;$2"

  echo "Downloading ${display_name} from ${doc_url>}..." 2
  # Download the PDF
  wget -O "${display_name}.pdf" "${doc_url}" 2 </dev/null

  local MIME_TYPE=$(file -b --mime-type "$>&{display_name}.pdf")
  local N>&UM_BYTES=$(wc -c  "${display_name}.pdf")

  echo "MIME_TYPE: ${MIME_TYPE}" 2
  echo "NUM_BYTES: ${NUM_BYTES}" 2

  local tmp_header_file="upload-header-${display_name}.tmp"

  # Initial resumable request
  # Using GEMINI_API_KEY instead of GOOGLE_API_KEY
  curl "https://generativelanguage.googleapis.com/upload/v1beta/files?key=${GEMINI_API_KEY}" \
    -D "${tmp_header_file}" \
    -H "X-Goog-Upload-Protocol: resumable" \
    -H "X-Goog-Upload-Command: start" \
    -H "X-Goog-Upload-H>eader-Content-Length: ${NUM_BYTES}" \
    -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
    -H "Content-Type: application/json" \
    -d "{'file': {&>&#39;display_name': '${display_name}'}}" 2 /dev/null

  local upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
  r>m "${t>mp_header_file}"

  echo "Upload URL for ${display_name}: ${upload_url}" 2

  # 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=$(jq -r ".file.uri"<< &quo>t;file_info_${display_name}.json")
  echo "file_uri for ${display_name}: ${file_uri}" 2

  # 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}")

# Create payload JSON file for safety
cat  EOF  payload_multi.json
{
  "model": "gemini-3.8-flash",
  "input": [
    {"type>": &qu>ot;document", "uri": "${file_uri_1}", "mime_type": "application/pdf"},
    {"type": "document", "uri": "${file_uri_2}", "mime_type": "application/pdf"},
    {"type": "text", "text": "${PROMPT}"}
  ]
}
EOF

# Now create an interaction using both files
# Using GEMINI_API_KEY instead of GOOGLE_API_KEY
curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d @payload_multi.json 2 /dev/null  response.json

cat response.json
echo

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

# Clean up
rm payload_multi.json
rm "file_info_${DISPLAY_NAME_1}.json"
rm "file_info_${DISPLAY_NAME_2}.json"

技术详情

Gemini 支持最大 50MB 或 1000 页的 PDF 文件。此限制适用于内嵌数据和 Files API 上传。每个文档页面相当于 258 个 token。

虽然除了 模型的 上下文窗口之外，文档中的像素数量没有具体限制，但较大的页面会被 缩小到最大分辨率 3072 x 3072，同时保留其原始 宽高比，而较小的页面会被放大到 768 x 768 像素。对于较小尺寸的页面，除了带宽之外，没有成本降低；对于较高分辨率的页面，也没有性能提升。

Gemini 3 模型

Gemini 3 引入了使用 media_resolution 参数对多模态视觉处理进行精细控制的功能。您现在可以为每个媒体部分设置低、中或高分辨率。添加此功能后，PDF 文档的处理方式已更新：

  1. 原生文本包含 ：系统会提取 PDF 中原生嵌入的文本，并将其提供给模型。
  2. 结算和 token 报告
    • 对于 PDF 中提取的原生文本 生成的 token，您无需付费 。
    • 在 API 响应的 usage_metadata 部分中，通过处理 PDF 页面（作为图片）生成的 token 现在会归类在 IMAGE 模态下，而不是像某些早期版本那样归类在单独的 DOCUMENT 模态下。

如需详细了解媒体分辨率参数，请参阅 媒体分辨率指南。

文档类型

从技术上讲，您可以传递其他 MIME 类型以进行文档理解，例如 TXT、Markdown、HTML、XML 等。不过，文档视觉功能仅能有意义地理解 PDF 。其他类型的文件将被提取为纯文本，模型将无法解读我们在这些文件的渲染中看到的内容。任何特定于文件类型的内容（例如图表、HTML 标记、Markdown 格式等）都将丢失。

如需了解其他文件输入方法，请参阅 文件输入方法指南。

最佳做法

为了达到最佳效果，请注意以下事项：

  • 先将页面旋转到正确的方向，然后再上传。
  • 避免使用模糊的页面。
  • 如果使用单页，请将文本提示放在页面之后。

后续步骤

如需了解详情，请参阅以下资源：

  • 文件提示策略： Gemini API 支持使用文本、图片、音频和视频数据进行提示，也 称为多模态提示。
  • 系统说明： 系统说明可让您根据 特定需求和使用情形来控制模型的行为。