OCR Example

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


def run_ocr_example() -> None:
    # pdf_ocr_engine accepts: auto | easyocr | tesseract | tesseract_cli | ocrmac | rapidocr
    # Some engines may require extra runtime dependencies in your environment.
    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(
        f"Convert to Markdown: {pdf_path}",
        markdown=True,
    )

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")