Docling Reader: Office Documents

Examples of using Docling to process Microsoft Office documents.

docling_documents.py

"""
Docling Reader: Office Documents
=================================
Examples of using Docling to process Microsoft Office documents.

Supported formats:
- DOCX: Microsoft Word documents with structure preservation
- DOTX: Microsoft Word templates
- PPTX: PowerPoint presentations

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_documents")
agent = get_agent(knowledge)

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

if __name__ == "__main__":

    async def main():
        # --- PPTX file with md output ---
        print("\n" + "=" * 60)
        print("PPTX file with markdown output")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="AI_Presentation",
            path="cookbook/07_knowledge/testing_resources/ai_presentation.pptx",
            reader=DoclingReader(),
        )
        agent.print_response(
            "What are the main topics covered in the AI presentation?",
            stream=True,
        )

        # --- DOCX file with markdown output ---
        print("\n" + "=" * 60)
        print("DOCX file (markdown output)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Project_Proposal",
            path="cookbook/07_knowledge/testing_resources/project_proposal.docx",
            reader=DoclingReader(),
        )
        agent.print_response(
            "What is the budget estimate for the AI analytics platform project?",
            stream=True,
        )

        # --- DOTX file with text output ---
        print("\n" + "=" * 60)
        print("DOTX file - Word Template (text output)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Meeting_Template",
            path="cookbook/07_knowledge/testing_resources/meeting_notes_template.dotx",
            reader=DoclingReader(output_format="text"),
        )
        agent.print_response(
            "What sections are included in the meeting notes template?",
            stream=True,
        )

    asyncio.run(main())

The example imports this helper module from the same directory:

utils.py

"""
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,
    )

Run the Example

1. Set up your virtual environment

   Mac

   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 lancedb openai pyarrow
   
3. Export your API keys

   Mac/Linux

   export LANCEDB_API_KEY="your_lancedb_api_key_here"
   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:LANCEDB_API_KEY="your_lancedb_api_key_here"
   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

   Save the code blocks above as docling_documents.py and utils.py in the same directory, then run:

   python docling_documents.py
   

Full source: cookbook/07_knowledge/05_integrations/readers/docling/docling_documents.py