Docling

Convert documents to Markdown, JSON, HTML, and other formats with configurable OCR using the Docling library.

Prerequisites

uv pip install -U docling

# Required for the OCR example
uv pip install -U easyocr

# Required for audio/video processing
uv pip install -U openai-whisper

ffmpeg is also required for audio/video processing:

• macOS: brew install ffmpeg
• Ubuntu: sudo apt-get install ffmpeg
• Windows: Download from ffmpeg.org

Example

from agno.agent import Agent
from agno.tools.docling import DoclingTools

agent = Agent(
    tools=[DoclingTools(all=True)],
    description="You are an agent that converts documents from all Docling parsers and exports to all supported output formats.",
)

# Convert a PDF to Markdown
agent.print_response(
    "Convert to Markdown: cookbook/07_knowledge/testing_resources/cv_1.pdf",
    markdown=True,
)

# Convert a PDF to JSON
agent.print_response(
    "Convert to JSON and return the full JSON without summarizing: cookbook/07_knowledge/testing_resources/cv_1.pdf",
    markdown=True,
)

# Convert inline string content
agent.print_response(
    "Use convert_string_content to convert this markdown string to JSON: # Inline Markdown\n\nThis is a parser test.",
    markdown=True,
)

OCR Configuration

cookbook/91_tools/docling_tools/ocr_example.py

from agno.agent import Agent
from agno.tools.docling import DoclingTools

ocr_tools = DoclingTools(
    pdf_enable_ocr=True,
    pdf_ocr_engine="easyocr",
    pdf_ocr_lang=["pt", "en"],
    pdf_force_full_page_ocr=True,
    pdf_enable_table_structure=True,
    pdf_enable_picture_description=False,
    pdf_document_timeout=120.0,
)

ocr_agent = Agent(
    tools=[ocr_tools],
    description="You are an agent that converts PDFs using advanced OCR.",
)

ocr_agent.print_response(
    "Convert to Markdown: cookbook/07_knowledge/testing_resources/cv_1.pdf",
    markdown=True,
)

Run the Example

git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/91_tools/docling_tools

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python docling_tools.py

For details, see Docling Tools cookbook.