Docling Reader: Image Documents

"""
Docling Reader: Image Documents
================================
Examples of using Docling to process image files with OCR capabilities.

Supported formats:
- JPEG: JPEG image files
- PNG: PNG image files

Docling uses advanced OCR to extract text from images including:
- Invoices and receipts
- Screenshots
- Scanned documents
- Any image with text content

Run `uv pip install docling openai-whisper` to install dependencies.
"""

import asyncio

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

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

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

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

if __name__ == "__main__":

    async def main():
        # --- JPEG image - Restaurant invoice ---
        print("\n" + "=" * 60)
        print("JPEG image - Restaurant Invoice (text output)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Restaurant_Invoice",
            path="cookbook/07_knowledge/testing_resources/restaurant_invoice.jpeg",
            reader=DoclingReader(output_format="text"),
        )
        agent.print_response(
            "What is the total amount on the restaurant invoice?",
            stream=True,
        )

        # --- PNG image - Order summary ---
        print("\n" + "=" * 60)
        print("PNG image - Order Summary (markdown output)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Order_Summary",
            path="cookbook/07_knowledge/testing_resources/restaurant_invoice.png",
            reader=DoclingReader(output_format="markdown"),
        )
        agent.print_response(
            "What items were ordered according to the order summary?",
            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,
    )