فهم الفيديو

from google import genai
import time

client = genai.Client()

myfile = client.files.upload(file="path/to/sample.mp4")

while not myfile.state or myfile.state.name != "ACTIVE":
    print("Processing video...")
    time.sleep(5)
    myfile = client.files.get(name=myfile.name)

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "video", "uri": myfile.uri, "mime_type": myfile.mime_type},
        {"type": "text", "text": "Summarize this video. Then create a quiz with an answer key based on the information in this video."}
    ]
)

print(interaction.output_text)

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

const ai = new GoogleGenAI({});

async function main() {
  const myfile = await ai.files.upload({
    file: "path/to/sample.mp4",
    config: { mimeType: "video/mp4" },
  });

  let getFile = await ai.files.get({ name: myfile.name });
  while (getFile.state === 'PROCESSING') {
      getFile = await ai.files.get({ name: myfile.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 (getFile.state === 'FAILED') {
      throw new Error('File processing failed.');
  }

  const interaction = await ai.interactions.create({
    model: "gemini-3.8-flash",
    input: [
      { type: "video", uri: myfile.uri, mime_type: myfile.mimeType },
      { type: "text", text: "Summarize this video. Then create a quiz with an answer key based on the information in this video." }
    ],
  });
  console.log(interaction.output_text);
}

await main();

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.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.interactions.VideoContent;
import com.google.genai.gaos.models.interactions.VideoContentMimeType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.File;
import com.google.genai.types.FileState;
import com.google.genai.types.UploadFileConfig;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

File myfile =
    client.files.upload(
        "path/to/sample.mp4", UploadFileConfig.builder().mimeType("video/mp4").build());

while (!myfile.state().isPresent()
    || myfile.state().get().knownEnum() != FileState.Known.ACTIVE) {
  System.out.println("Processing video...");
  Thread.sleep(5000);
  myfile = client.files.get(myfile.name().get(), null);
}

Content videoContent =
    VideoContent.builder()
        .uri(myfile.uri().get())
        .mimeType(VideoContentMimeType.of(myfile.mimeType().get()))
        .build();
Content textContent =
    TextContent.builder()
        .text(
            "Summarize this video. Then create a quiz with an answer key based on the information in this video.")
        .build();

List<Content> contents = Arrays.asList(videoContent, textContent);

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(""));

package main

import (
    "context"
    "fmt"
    "log"
    "time"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    myfile, err := client.Files.UploadFromPath(ctx, "path/to/sample.mp4", &genai.UploadFileConfig{
        MIMEType: "video/mp4",
    })
    if err != nil {
        log.Fatal(err)
    }

    for myfile.State != genai.FileStateActive {
        fmt.Println("Processing video...")
        time.Sleep(5 * time.Second)
        myfile, err = client.Files.Get(ctx, myfile.Name, nil)
        if err != nil {
            log.Fatal(err)
        }
    }

    contents := []interactions.Content{
        interactions.NewContent(interactions.VideoContent{
            URI:      genai.Ptr(myfile.URI),
            MimeType: interactions.VideoContentMimeType(myfile.MIMEType).ToPointer(),
        }),
        interactions.NewContent(interactions.TextContent{
            Text: "Summarize this video. Then create a quiz with an answer key based on the information in this video.",
        }),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput(contents),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

VIDEO_PATH="path/to/sample.mp4"
MIME_TYPE=$(file -b --mime-type "${VIDEO_PATH}")
NUM_BYTES=$(wc -c < "${VIDEO_PATH}")
DISPLAY_NAME=VIDEO

tmp_header_file=upload-header.tmp

echo "Starting file upload..."
curl "https://generativelanguage.googleapis.com/upload/v1beta/files" \
  -H "x-goog-api-key: $GEMINI_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

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

echo "Uploading video data..."
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${VIDEO_PATH}" 2> /dev/null > file_info.json

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

echo "File uploaded successfully. File URI: ${file_uri}"

# Polling loop
echo "Waiting for file to be processed..."
while true; do
  curl -s "https://generativelanguage.googleapis.com/v1beta/${file_name}" \
    -H "x-goog-api-key: $GEMINI_API_KEY" > file_status.json
  state=$(jq -r ".state" file_status.json)
  echo "Current state: $state"
  if [ "$state" == "ACTIVE" ]; then
    break
  elif [ "$state" == "FAILED" ]; then
    echo "File processing failed."
    exit 1
  fi
  sleep 5
done

echo "Generating content from video..."
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "gemini-3.8-flash",
      "input": [
        {"type": "video", "uri": "'${file_uri}'", "mime_type": "'${MIME_TYPE}'"},
        {"type": "text", "text": "Summarize this video. Then create a quiz with an answer key based on the information in this video."}
      ]
    }' 2> /dev/null > response.json

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

from google import genai
import base64

video_file_name = "/path/to/your/video.mp4"
video_bytes = open(video_file_name, 'rb').read()

client = genai.Client()
interaction = client.interactions.create(
    model='gemini-3.8-flash',
    input=[
        {"type": "text", "text": "Please summarize the video in 3 sentences."},
        {
            "type": "video",
            "data": base64.b64encode(video_bytes).decode('utf-8'),
            "mime_type": "video/mp4"
        }
    ]
)
print(interaction.output_text)

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

const ai = new GoogleGenAI({});
const base64VideoFile = fs.readFileSync("path/to/small-sample.mp4", {
  encoding: "base64",
});

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    { type: "text", text: "Please summarize the video in 3 sentences." },
    {
      type: "video",
      data: base64VideoFile,
      mime_type: "video/mp4",
    }
  ],
});
console.log(interaction.output_text);

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.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.interactions.VideoContent;
import com.google.genai.gaos.models.interactions.VideoContentMimeType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.Base64;
import java.util.List;

String videoFileName = "/path/to/your/video.mp4";
byte[] videoBytes = Files.readAllBytes(Paths.get(videoFileName));
String base64Video = Base64.getEncoder().encodeToString(videoBytes);

Client client = new Client();

Content textContent =
    TextContent.builder().text("Please summarize the video in 3 sentences.").build();
Content videoContent =
    VideoContent.builder()
        .data(base64Video)
        .mimeType(VideoContentMimeType.VIDEO_MP4)
        .build();

List<Content> contents = Arrays.asList(textContent, videoContent);

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(""));

package main

import (
    "context"
    "encoding/base64"
    "fmt"
    "log"
    "os"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    videoFileName := "/path/to/your/video.mp4"
    videoBytes, err := os.ReadFile(videoFileName)
    if err != nil {
        log.Fatal(err)
    }
    base64Video := base64.StdEncoding.EncodeToString(videoBytes)

    contents := []interactions.Content{
        interactions.NewContent(interactions.TextContent{
            Text: "Please summarize the video in 3 sentences.",
        }),
        interactions.NewContent(interactions.VideoContent{
            Data:     genai.Ptr(base64Video),
            MimeType: interactions.VideoContentMimeTypeVideoMp4.ToPointer(),
        }),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput(contents),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

VIDEO_PATH=/path/to/your/video.mp4

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: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "gemini-3.8-flash",
      "input": [
        {"type": "text", "text": "Please summarize the video in 3 sentences."},
        {
          "type": "video",
          "data": "'$(base64 $B64FLAGS $VIDEO_PATH)'",
          "mime_type": "video/mp4"
        }
      ]
    }' 2> /dev/null

from google import genai

client = genai.Client()
interaction = client.interactions.create(
    model='gemini-3.8-flash',
    input=[
        {"type": "text", "text": "Please summarize the video in 3 sentences."},
        {
            "type": "video",
            "uri": "https://www.youtube.com/watch?v=9hE5-98ZeCg"
        }
    ]
)
print(interaction.output_text)

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

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    { type: "text", text: "Please summarize the video in 3 sentences." },
    {
      type: "video",
      uri: "https://www.youtube.com/watch?v=9hE5-98ZeCg",
    }
  ],
});
console.log(interaction.output_text);

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.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.interactions.VideoContent;
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("Please summarize the video in 3 sentences.").build();
Content videoContent =
    VideoContent.builder()
        .uri("https://www.youtube.com/watch?v=9hE5-98ZeCg")
        .build();

List<Content> contents = Arrays.asList(textContent, videoContent);

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(""));

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    contents := []interactions.Content{
        interactions.NewContent(interactions.TextContent{
            Text: "Please summarize the video in 3 sentences.",
        }),
        interactions.NewContent(interactions.VideoContent{
            URI: genai.Ptr("https://www.youtube.com/watch?v=9hE5-98ZeCg"),
        }),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput(contents),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

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": "text", "text": "Please summarize the video in 3 sentences."},
        {
          "type": "video",
          "uri": "https://www.youtube.com/watch?v=9hE5-98ZeCg"
        }
      ]
    }' 2> /dev/null

import time
from google import genai

client = genai.Client()

# Upload a long video
video_file = client.files.upload(file="path/to/lecture.mp4")

while video_file.state.name == "PROCESSING":
    time.sleep(2)
    video_file = client.files.get(name=video_file.name)

# Use agentic processing
interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {
            "type": "video",
            "uri": video_file.uri,
            "mime_type": video_file.mime_type,
            "processing": "agentic"
        },
        {"type": "text", "text": "What are the three main arguments presented?"}
    ]
)
print(interaction.output_text)

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

const ai = new GoogleGenAI({});

// Upload a long video
let videoFile = await ai.files.upload({
  file: "path/to/lecture.mp4",
  config: { mimeType: "video/mp4" }
});

while (videoFile.state === "PROCESSING") {
  await new Promise((resolve) => setTimeout(resolve, 2000));
  videoFile = await ai.files.get({ name: videoFile.name });
}

// Use agentic processing
const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    {
      type: "video",
      uri: videoFile.uri,
      mime_type: videoFile.mimeType,
      processing: "agentic"
    },
    { type: "text", text: "What are the three main arguments presented?" }
  ]
});
console.log(interaction.output_text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": [
      {
        "type": "video",
        "uri": "'${file_uri}'",
        "mime_type": "video/mp4",
        "processing": "agentic"
      },
      {"type": "text", "text": "What are the three main arguments presented?"}
    ]
  }' 2> /dev/null

from google import genai

client = genai.Client()

lecture = client.files.upload(file="path/to/long-lecture.mp4")
experiment = client.files.upload(file="path/to/short-experiment.mp4")

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {
            "type": "video",
            "uri": lecture.uri,
            "mime_type": lecture.mime_type,
            "processing": "agentic"  # Use agentic video understanding
        },
        {
            "type": "video",
            "uri": experiment.uri,
            "mime_type": experiment.mime_type,
            "processing": "static"  # Use static processing
        },
        {"type": "text", "text": "Compare the lecture content with the experiment results."}
    ]
)
print(interaction.output_text)

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

const ai = new GoogleGenAI({});

const lecture = await ai.files.upload({
  file: "path/to/long-lecture.mp4",
  config: { mimeType: "video/mp4" }
});
const experiment = await ai.files.upload({
  file: "path/to/short-experiment.mp4",
  config: { mimeType: "video/mp4" }
});

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    {
      type: "video",
      uri: lecture.uri,
      mime_type: lecture.mimeType,
      processing: "agentic" // Use agentic video understanding
    },
    {
      type: "video",
      uri: experiment.uri,
      mime_type: experiment.mimeType,
      processing: "static" // Use static processing
    },
    { type: "text", text: "Compare the lecture content with the experiment results." }
  ]
});
console.log(interaction.output_text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": [
      {
        "type": "video",
        "uri": "'${lecture_uri}'",
        "mime_type": "video/mp4",
        "processing": "agentic"
      },
      {
        "type": "video",
        "uri": "'${experiment_uri}'",
        "mime_type": "video/mp4",
        "processing": "static"
      },
      {"type": "text", "text": "Compare the lecture content with the experiment results."}
    ]
  }' 2> /dev/null

prompt = "What are the examples given at 00:05 and 00:10 supposed to show us?"

const prompt = "What are the examples given at 00:05 and 00:10 supposed to show us?";

String prompt = "What are the examples given at 00:05 and 00:10 supposed to show us?";

prompt := "What are the examples given at 00:05 and 00:10 supposed to show us?"

PROMPT="What are the examples given at 00:05 and 00:10 supposed to show us?"

prompt = "Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments."

const prompt = "Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments.";

String prompt =
    "Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments.";

prompt := "Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments."

PROMPT="Describe the key events in this video, providing both audio and visual details. Include timestamps for salient moments."

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {
            "type": "video",
            "uri": video_file.uri,
            "mime_type": video_file.mime_type,
            "processing": {
                "type": "static",
                "start_offset": 1200,
                "end_offset": 1500,
            },
        },
        {"type": "text", "text": "Summarize this section of the video."},
    ],
)
print(interaction.output_text)

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    {
      type: "video",
      uri: videoFile.uri,
      mime_type: videoFile.mimeType,
      processing: {
        type: "static",
        start_offset: 1200,
        end_offset: 1500,
      },
    },
    { type: "text", text: "Summarize this section of the video." },
  ],
});
console.log(interaction.output_text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": [
      {
        "type": "video",
        "uri": "'${file_uri}'",
        "mime_type": "video/mp4",
        "processing": {
          "type": "static",
          "start_offset": 1200,
          "end_offset": 1500
        }
      },
      {"type": "text", "text": "Summarize this section of the video."}
    ]
  }' 2> /dev/null

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {
            "type": "video",
            "uri": video_file.uri,
            "mime_type": video_file.mime_type,
            "processing": {
                "type": "static",
                "fps": 0.5,  # Sample 1 frame every 2 seconds
            },
        },
        {"type": "text", "text": "Describe the scene changes in this video."},
    ],
)
print(interaction.output_text)

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    {
      type: "video",
      uri: videoFile.uri,
      mime_type: videoFile.mimeType,
      processing: {
        type: "static",
        fps: 0.5, // Sample 1 frame every 2 seconds
      },
    },
    { type: "text", text: "Describe the scene changes in this video." },
  ],
});
console.log(interaction.output_text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": [
      {
        "type": "video",
        "uri": "'${file_uri}'",
        "mime_type": "video/mp4",
        "processing": {
          "type": "static",
          "fps": 0.5
        }
      },
      {"type": "text", "text": "Describe the scene changes in this video."}
    ]
  }' 2> /dev/null