Docling Reader

The Docling Reader processes multiple document formats using IBM’s Docling library. It handles PDFs, documents, presentations, spreadsheets, images, audio, video and markup files.

Code

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.docling_reader import DoclingReader
from agno.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

# Create a knowledge base with docling reader
knowledge = Knowledge(
    vector_db=PgVector(
        table_name="docling_documents",
        db_url=db_url,
    )
)

# Add documents using DoclingReader
knowledge.insert(
    path="documents/report.pdf",
    reader=DoclingReader(),
)

# Create an agent with the knowledge base
agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
)

# Query the knowledge base
agent.print_response(
    "Summarize the key findings from the report",
    markdown=True,
)

Usage

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

   # Base dependencies
   uv pip install -U docling sqlalchemy psycopg pgvector agno openai
   
   # For audio/video processing
   uv pip install -U openai-whisper
   

   Install ffmpeg (required for audio/video processing):

   • macOS: brew install ffmpeg
   • Ubuntu: sudo apt-get install ffmpeg
   • Windows: Download from https://ffmpeg.org/download.html
3. Set environment variables

   export OPENAI_API_KEY=xxx
   
4. Run PgVector

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql/data/pgdata \
     -v pgvolume:/var/lib/postgresql/data \
     -p 5532:5432 \
     --name pgvector \
     agno/pgvector:16
   
5. Run Agent

   Mac

   python examples/basics/knowledge/concepts/readers/overview/docling_reader_sync.py
   

   python examples/basics/knowledge/concepts/readers/overview/docling_reader_sync.py
   

Params

Parameter	Type	Default	Description
output_format	str	"markdown"	Export format ("markdown", "text", "json", "yaml", "html", "html_split_page", "doctags", "vtt")
converter	Optional[DocumentConverter]	None	Custom Docling converter configuration
format_options	Optional[dict]	None	Format options dictionary for DocumentConverter
chunking_strategy	Optional[ChunkingStrategy]	DocumentChunking()	Strategy for chunking the document