Multimedia Input

// Using cross_file for cross-platform support
import 'package:cross_file/cross_file.dart';

final agent = Agent('openai');

// Text file
final bioFile = XFile.fromData(
  await File('bio.txt').readAsBytes(), 
  path: 'bio.txt',
);
final result = await agent.send(
  'Can you summarize the attached file?',
  attachments: [await DataPart.fromFile(bioFile)],
);

// Image file (the moment of truth)
final fridgeFile = XFile.fromData(
  await File('fridge.png').readAsBytes(),
  path: 'fridge.png',
);
final result = await agent.send(
  'What food do I have on hand?',
  attachments: [await DataPart.fromFile(fridgeFile)],
);
// "I see leftover pizza, expired milk, and... is that a science experiment?"

// Responses API can request richer vision detail
final responsesAgent = Agent(
  'openai-responses',
  chatModelOptions: const OpenAIResponsesChatModelOptions(
    imageDetail: ImageDetail.high,
  ),
);
await responsesAgent.send(
  'Describe the fridge image with extra detail',
  attachments: [await DataPart.fromFile(fridgeFile)],
);

// Download and include file from URL
final urlData = await DataPart.url(
  Uri.parse('https://example.com/document.pdf'),
);
final result = await agent.send(
  'Summarize this document',
  attachments: [urlData],
);

// Include raw bytes with mime type
final bytes = Uint8List.fromList([/* your data */]);
final rawData = DataPart(
  bytes: bytes,
  mimeType: 'application/pdf',
);
final result = await agent.send(
  'Process this data',
  attachments: [rawData],
);

// Direct URL reference (OpenAI)
final result = await agent.send(
  'Describe this image',
  attachments: [
    LinkPart(Uri.parse('https://example.com/image.jpg')),
  ],
);

// Mix text and images
final result = await agent.send(
  'Based on the bio and fridge contents, suggest a meal',
  attachments: [
    await DataPart.fromFile(bioFile),
    await DataPart.fromFile(fridgeFile),
  ],
);

import 'dart:io';
import 'package:dartantic_ai/dartantic_ai.dart';

final agent = Agent('google');
final audioBytes = await File('audio.m4a').readAsBytes();

final result = await agent.send(
  'Transcribe this audio file word for word.',
  attachments: [
    DataPart(audioBytes, mimeType: 'audio/mp4', name: 'audio.m4a'),
  ],
);

// Get transcription text
final transcription = result.messages
  .expand((m) => m.parts)
  .whereType<TextPart>()
  .map((p) => p.text)
  .join('\n');

print(transcription);

import 'dart:io';
import 'package:dartantic_ai/dartantic_ai.dart';

final agent = Agent('google');
final audioBytes = await File('audio.m4a').readAsBytes();

final schema = Schema.fromMap({
  'type': 'object',
  'properties': {
    'transcript': {'type': 'string'},
    'words': {
      'type': 'array',
      'items': {
        'type': 'object',
        'properties': {
          'word': {'type': 'string'},
          'start_time': {'type': 'number'},
          'end_time': {'type': 'number'},
        },
      },
    },
  },
});

final result = await agent.sendFor<Map<String, dynamic>>(
  'Transcribe this audio with word-level timestamps (in seconds).',
  outputSchema: schema,
  attachments: [
    DataPart(audioBytes, mimeType: 'audio/mp4', name: 'audio.m4a'),
  ],
);

final transcription = result.output;
print('Transcript: ${transcription['transcript']}');

// Access word-level timestamps
for (final word in transcription['words'] as List) {
  final w = word as Map<String, dynamic>;
  print('${w['start_time']}s - ${w['end_time']}s: ${w['word']}');
}

import 'dart:io';
import 'package:cross_file/cross_file.dart';
import 'package:dartantic_ai/dartantic_ai.dart';

final agent = Agent('google');

const imagePath = 'document.png';
final imageFile = XFile.fromData(
  await File(imagePath).readAsBytes(),
  path: imagePath,
);

final result = await agent.send(
  'Extract all text from this image. Preserve the formatting and structure.',
  attachments: [await DataPart.fromFile(imageFile)],
  history: [ChatMessage.system('Be precise and preserve formatting.')],
);

print(result.output);
// Extracted text with formatting preserved