Website Knowledge

Ingest web pages and PDFs into a PgVector knowledge base with WebsiteTools.

WebsiteTools(knowledge=kb) lets the agent add pages to the same PgVector-backed knowledge base it searches.

website_tools_knowledge.py

"""
Website Tools Knowledge
=============================

Demonstrates website tools knowledge.
"""

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.tools.website import WebsiteTools
from agno.vectordb.pgvector import PgVector

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


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

# Create PDF URL knowledge base
kb = Knowledge(
    vector_db=PgVector(
        table_name="documents",
        db_url=db_url,
    ),
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    kb.insert_many(
        urls=[
            "https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
            "https://docs.agno.com/introduction",
        ]
    )

    # Initialize the Agent with the combined knowledge base
    agent = Agent(
        knowledge=kb,
        search_knowledge=True,
        tools=[
            WebsiteTools(knowledge=kb)  # Set combined or website knowledge base
        ],
    )

    # Use the agent
    agent.print_response(
        "How do I get started on Mistral: https://docs.mistral.ai/getting-started/models/models_overview",
        markdown=True,
        stream=True,
    )

Run the Example

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

   uv pip install -U agno "psycopg[binary]" beautifulsoup4 openai pgvector pypdf sqlalchemy
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run PgVector

   macOS / Linux

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql \
     -v pgvolume:/var/lib/postgresql \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:18
   

   docker run -d `
     -e POSTGRES_DB=ai `
     -e POSTGRES_USER=ai `
     -e POSTGRES_PASSWORD=ai `
     -e PGDATA=/var/lib/postgresql `
     -v pgvolume:/var/lib/postgresql `
     -p 5532:5432 `
     --name pgvector `
     agnohq/pgvector:18
   
5. Run the example

   Save the code above as website_tools_knowledge.py, then run:

   python website_tools_knowledge.py
   

Full source: cookbook/91_tools/website_tools_knowledge.py