PDF Reader Async

The PDF Reader with asynchronous processing allows you to handle PDF files efficiently and integrate them with knowledge bases.

Code

examples/concepts/knowledge/readers/pdf_reader_async.py

import asyncio

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.pgvector import PgVector

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

# Create a knowledge base with the PDFs from the data/pdfs directory
knowledge = Knowledge(
    vector_db=PgVector(
        table_name="pdf_documents",
        db_url=db_url,
    )
)

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

if __name__ == "__main__":
    asyncio.run(
        knowledge.add_content_async(
            path="cookbook/knowledge/testing_resources/cv_1.pdf",
        )
    )
    # Create and use the agent
    asyncio.run(
        agent.aprint_response(
            "What skills does an applicant require to apply for the Software Engineer position?",
            markdown=True,
        )
    )

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install libraries

   pip install -U pypdf sqlalchemy psycopg pgvector agno openai  
   
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/concepts/knowledge/readers/pdf_reader_async.py
   

Params

Parameter	Type	Default	Description
path	Path	Required	Path to PDF file or URL
split_on_pages	bool	True	Split the PDF into pages
page_start_numbering_format	Optional[str]	None	Format for page numbering
page_end_numbering_format	Optional[str]	None	Format for page numbering
password	Optional[str]	None	Password to unlock the PDF