You are viewing v1 docs. For the latest documentation, visit docs.agno.com
from agno.agent import Agent from agno.models.vllm import vLLM from agno.tools.duckduckgo import DuckDuckGoTools agent = Agent( model=vLLM( id="NousResearch/Nous-Hermes-2-Mistral-7B-DPO", top_k=20, enable_thinking=False ), tools=[DuckDuckGoTools()], show_tool_calls=True, markdown=True, ) agent.print_response("Whats happening in France?", stream=True)
Create a virtual environment
Terminal
python3 -m venv .venv source .venv/bin/activate
Install Libraries
pip install -U agno openai vllm duckduckgo-search
Start vLLM server
vllm serve NousResearch/Nous-Hermes-2-Mistral-7B-DPO \ --enable-auto-tool-choice \ --tool-call-parser hermes \ --dtype float16 \ --max-model-len 8192 \ --gpu-memory-utilization 0.9
Run Agent
python cookbook/models/vllm/tool_use.py
Was this page helpful?