Docling Reader: Audio Files

"""
Docling Reader: Audio Files
============================
Examples of using Docling to process audio files with speech-to-text transcription.

Supported formats:
- WAV: Waveform Audio File Format
- MP3: MPEG Audio Layer III
- MP4: MPEG-4 Part 14 (audio)

Output formats:
- markdown: Transcription as markdown text (default)
- text: Plain text transcription
- html: HTML formatted transcription
- vtt: WebVTT subtitle format with timestamps

Docling uses OpenAI Whisper for high-quality speech recognition.

Dependencies:
- Python packages: `uv pip install docling openai-whisper`
- System requirement: ffmpeg (https://www.ffmpeg.org/download.html)
"""

import asyncio

from agno.knowledge.reader.docling_reader import DoclingReader
from utils import get_agent, get_knowledge

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------

knowledge = get_knowledge(table_name="docling_audio")
agent = get_agent(knowledge)

# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------

if __name__ == "__main__":

    async def main():
        # --- WAV audio - Agno description with HTML output ---
        print("\n" + "=" * 60)
        print("WAV audio - Agno Description (HTML output)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Agno_Audio_WAV",
            path="cookbook/07_knowledge/testing_resources/agno_description.wav",
            reader=DoclingReader(output_format="html"),
        )
        agent.print_response(
            "What does the audio describe about Agno?",
            stream=True,
        )

        # --- MP3 audio - Agno description ---
        print("\n" + "=" * 60)
        print("MP3 audio - Agno Description (markdown output)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Agno_Audio_MP3",
            path="cookbook/07_knowledge/testing_resources/agno_description.mp3",
            reader=DoclingReader(),
        )
        agent.print_response(
            "Summarize what Agno framework is used for",
            stream=True,
        )

        # --- MP4 audio - Agno description with VTT output ---
        print("\n" + "=" * 60)
        print("MP4 audio - Agno Description (VTT output)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Agno_Audio_MP4",
            path="cookbook/07_knowledge/testing_resources/agno_description.mp4",
            reader=DoclingReader(output_format="vtt"),
        )
        agent.print_response(
            "What are the key features of Agno mentioned in the audio?",
            stream=True,
        )

    asyncio.run(main())

"""
Docling Reader: Shared Utilities
=================================
Common setup and utilities for Docling reader examples.

Docling uses IBM's advanced document conversion library to extract content from multiple document formats.

Supported formats examples::
- PDF: PDFs with advanced layout understanding and text extraction
- DOCX: Microsoft Word documents with structure preservation
- PPTX: PowerPoint presentations
- Markdown: Markdown files
- CSV: CSV spreadsheets
- XLSX: Excel spreadsheets

Output formats examples:
- markdown: Preserves structure and formatting
- text: Plain text output
- json: Lossless serialization with full document structure
- html: HTML with image embedding/referencing support
- doctags: Markup format with full content and layout characteristics

Key features:
- Advanced document structure understanding
- Better handling of complex layouts (tables, columns, etc.)
- Multiple output formats for different use cases
- Ideal for complex documents with rich formatting

Run `uv pip install docling openai-whisper` to install python dependencies.
System requirement ffmpeg (https://www.ffmpeg.org/download.html) for audio formats.

See also: 01_documents.py for PDF/DOCX, 02_data.py for CSV/JSON and 03_web.py for web sources.
"""

import warnings

from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIResponses
from agno.vectordb.lancedb import LanceDb, SearchType

# Suppress Whisper FP16 warnings when running on CPU
warnings.filterwarnings("ignore", message="FP16 is not supported on CPU")


def get_knowledge(table_name: str = "docling_reader") -> Knowledge:
    return Knowledge(
        vector_db=LanceDb(
            uri="tmp/lancedb",
            table_name=table_name,
            search_type=SearchType.hybrid,
            embedder=OpenAIEmbedder(id="text-embedding-3-small"),
        ),
    )


def get_agent(knowledge: Knowledge) -> Agent:
    return Agent(
        model=OpenAIResponses(id="gpt-5.2"),
        knowledge=knowledge,
        search_knowledge=True,
        markdown=True,
    )