docling_xlsx.py
"""
Docling Reader: Data Files
===========================
Examples of using Docling to process spreadsheet and data files.
Supported formats:
- XLSX: Microsoft Excel spreadsheets
- CSV: Comma-separated values files
Docling preserves table structure and formatting from spreadsheets.
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_data")
agent = get_agent(knowledge)
# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------
if __name__ == "__main__":
async def main():
# --- XLSX file - Sample products with HTML output ---
print("\n" + "=" * 60)
print("XLSX file - Sample Products (HTML output)")
print("=" * 60 + "\n")
await knowledge.ainsert(
name="Sample_Products",
path="cookbook/07_knowledge/testing_resources/sample_products.xlsx",
reader=DoclingReader(output_format="html"),
)
agent.print_response(
"What products are available and what are their prices?",
stream=True,
)
asyncio.run(main())
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
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 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
Run the example
Run the example from the repository root:
python cookbook/07_knowledge/05_integrations/readers/docling/docling_xlsx.py