Skip to main content
The Wikipedia Reader allows you to search and read Wikipedia articles synchronously, converting them into vector embeddings for your knowledge base.

​
Code

examples/context/knowledge/readers/overview/wikipedia_reader_sync.py
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.wikipedia_reader import WikipediaReader
from agno.vectordb.pgvector import PgVector

# Create Knowledge Instance
knowledge = Knowledge(
    name="Wikipedia Knowledge Base",
    description="Knowledge base from Wikipedia articles",
    vector_db=PgVector(
        table_name="wikipedia_vectors", 
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"
    ),
)

# Add topics from Wikipedia synchronously
knowledge.add_content(
    metadata={"source": "wikipedia", "type": "encyclopedia"},
    topics=["Manchester United", "Artificial Intelligence"],
    reader=WikipediaReader(),
)

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

# Query the knowledge base
agent.print_response(
    "What can you tell me about Manchester United?",
    markdown=True
)

​
Usage

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
2

Install dependencies

uv pip install -U wikipedia 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

python examples/context/knowledge/readers/overview/wikipedia_reader_sync.py

​
Params

ParameterTypeDefaultDescription
topicstrNoneTopic to read from Wikipedia