Team with Knowledge Base

This example demonstrates how to create a team with knowledge base integration. The team has access to a knowledge base with Agno documentation and can combine this knowledge with web search capabilities.

Code

cookbook/02_examples/teams/knowledge/01_team_with_knowledge.py

"""
This example demonstrates how to create a team with knowledge base integration.

The team has access to a knowledge base with Agno documentation and can combine
this knowledge with web search capabilities.
"""

from pathlib import Path

from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.vectordb.lancedb import LanceDb, SearchType

# Setup paths for knowledge storage
cwd = Path(__file__).parent
tmp_dir = cwd.joinpath("tmp")
tmp_dir.mkdir(parents=True, exist_ok=True)

# Initialize knowledge base with vector database
agno_docs_knowledge = Knowledge(
    vector_db=LanceDb(
        uri=str(tmp_dir.joinpath("lancedb")),
        table_name="agno_docs",
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)

# Add content to knowledge base
agno_docs_knowledge.insert(url="https://docs.agno.com/llms-full.txt")

# Create HackerNews agent for supplementary tech news
hackernews_agent = Agent(
    name="HackerNews Agent",
    role="Search HackerNews for tech news",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[HackerNewsTools()],
    instructions=["Always include sources"],
)

# Create team with knowledge base integration
team_with_knowledge = Team(
    name="Team with Knowledge",
    members=[hackernews_agent],
    model=OpenAIResponses(id="gpt-5.2"),
    knowledge=agno_docs_knowledge,
    show_members_responses=True,
    markdown=True,
)

if __name__ == "__main__":
    team_with_knowledge.print_response("Tell me about the Agno framework", stream=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

   uv pip install -U agno lancedb
   
3. Set environment variables

   export OPENAI_API_KEY=****
   
4. Run the agent

   python cookbook/02_examples/teams/knowledge/01_team_with_knowledge.py