Agno Agents with Nebius AI¶
In this notebook, we'll explore setting up a simple agent with web search capability
Install required packages for this notebook¶
- agno: The agent framework we'll be using
- duckduckgo-search: For web search capabilities
In [1]:
!pip install -qU agno duckduckgo-search ddgs openai python-dotenv ipywidgets
Simple Agent¶
Below we create a basic agent that can search the web to answer questions. This agent uses:
- meta-llama/Llama-3.3-70B-Instruct
- DuckDuckGo search as a tool to retrieve information from the web
When we run this agent with a question about the NBA, it will search for recent information and provide an answer.
In [2]:
from dotenv import load_dotenv
load_dotenv()
Out[2]:
True
In [3]:
import os
from agno.agent import Agent
from agno.models.nebius import Nebius
from agno.tools.duckduckgo import DuckDuckGoTools
agent = Agent(
model=Nebius(
id="meta-llama/Llama-3.3-70B-Instruct",
api_key=os.getenv("NEBIUS_API_KEY")
),
tools=[DuckDuckGoTools()],
markdown=True
)
agent.print_response("How are the golden state warriors doing this 2024-2025 season?", stream=True)
Output()
/home/sujee/my-stuff/projects/nebius/token-factory-cookbook-1/agents/agno-agents-examples/.venv/lib/python3.11/site-pac kages/agno/tools/duckduckgo.py:71: RuntimeWarning: This package (`duckduckgo_search`) has been renamed to `ddgs`! Use `pip install ddgs` instead. ddgs = DDGS(