basic_examples.py
from agno.agent import Agent
from agno.tools.docling import DoclingTools
from paths import (
audio_video_path,
docx_path,
html_path,
image_path,
md_path,
pdf_path,
pptx_path,
xlsx_path,
xml_path,
)
def run_basic_examples() -> None:
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.",
)
agent.print_response(
"List supported Docling input parsers and active allowed parsers.",
markdown=True,
)
agent.print_response(
f"Convert to Markdown: {pdf_path}",
markdown=True,
)
agent.print_response(
f"Convert to JSON and return the full JSON without summarizing: {pdf_path}",
markdown=True,
)
agent.print_response(
f"Convert to YAML: {pdf_path}",
markdown=True,
)
agent.print_response(
f"Convert to DocTags: {pdf_path}",
markdown=True,
)
agent.print_response(
f"Convert to VTT: {pdf_path}",
markdown=True,
)
agent.print_response(
f"Convert to HTML split page: {pdf_path}",
markdown=True,
)
# Additional parser examples based on static resources.
agent.print_response(
f"Convert to Markdown: {docx_path}",
markdown=True,
)
agent.print_response(
f"Convert to Markdown: {md_path}",
markdown=True,
)
agent.print_response(
f"Convert to Markdown: {html_path}",
markdown=True,
)
agent.print_response(
f"Convert to Markdown: {xml_path}",
markdown=True,
)
agent.print_response(
f"Convert to Markdown: {xlsx_path}",
markdown=True,
)
agent.print_response(
f"Convert to Markdown: {pptx_path}",
markdown=True,
)
agent.print_response(
f"Convert to Markdown: {image_path}",
markdown=True,
)
agent.print_response(
f"Convert to VTT: {audio_video_path}",
markdown=True,
)
# convert_string is limited by Docling to Markdown and HTML source 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,
)
agent.print_response(
"Use convert_string_content to convert this html string to Markdown: <h1>Inline HTML</h1><p>This is a parser test.</p>",
markdown=True,
)
paths.py
from pathlib import Path
repo_root = Path(__file__).resolve().parents[3]
testing_resources_path = repo_root / "cookbook/07_knowledge/testing_resources"
def get_test_resource_path(filename: str) -> str:
return str(testing_resources_path / filename)
pdf_path = get_test_resource_path("cv_1.pdf")
docx_path = get_test_resource_path("project_proposal.docx")
md_path = get_test_resource_path("coffee.md")
html_path = get_test_resource_path("company_info.html")
xml_path = get_test_resource_path("patent_sample.xml")
xlsx_path = get_test_resource_path("sample_products.xlsx")
pptx_path = get_test_resource_path("ai_presentation.pptx")
image_path = get_test_resource_path("restaurant_invoice.png")
audio_video_path = get_test_resource_path("agno_description.mp4")
Run the Example
1
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2
Install dependencies
uv pip install -U agno docling easyocr openai openai-whisper rapidocr-onnxruntime
3
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
4
Clone Agno
Clone the repository and run the remaining commands from its root:
git clone https://github.com/agno-agi/agno.git
cd agno
5
Install FFmpeg
Install the FFmpeg system package required for the MP4-to-VTT example and verify it is available:
ffmpeg -version
6
Run the example
Run the example from the repository root:This entry point runs both the basic and OCR examples.
python cookbook/91_tools/docling_tools/run.py