Wikipedia Reader (Async)

The Wikipedia Reader with asynchronous processing allows you to search and read Wikipedia articles efficiently, converting them into vector embeddings for your knowledge base.

Code

examples/concepts/knowledge/readers/wikipedia_reader_async.py

import asyncio

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.arxiv_reader import ArxivReader
from agno.knowledge.reader.wikipedia_reader import WikipediaReader
from agno.vectordb.pgvector import PgVector

# Create Knowledge Instance
knowledge = Knowledge(
    name="Multi-Source Knowledge Base",
    description="Knowledge base combining Wikipedia and ArXiv content",
    vector_db=PgVector(
        table_name="multi_vectors", 
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"
    ),
)

async def main():
    # Add topics from Wikipedia
    await knowledge.add_content_async(
        metadata={"source": "wikipedia", "type": "encyclopedia"},
        topics=["Manchester United", "Machine Learning"],
        reader=WikipediaReader(),
    )

    # Add topics from ArXiv
    await knowledge.add_content_async(
        metadata={"source": "arxiv", "type": "academic"},
        topics=["Carbon Dioxide", "Neural Networks"],
        reader=ArxivReader(),
    )

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

    # Query the knowledge base
    await agent.aprint_response(
        "What can you tell me about Machine Learning from both general and academic sources?",
        markdown=True
    )

if __name__ == "__main__":
    asyncio.run(main())

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 wikipedia arxiv 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/wikipedia_reader_async.py
   

Params

Parameter	Type	Default	Description
topic	str	None	Topic to read from Wikipedia