Code
cookbook/11_models/llama_cpp/tool_use_stream.py
Usage
1
Set up your virtual environment
2
Install LlamaCpp
Follow the LlamaCpp installation guide and start the server:
3
Install dependencies
4
Run Agent
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
"""Run `uv pip install` to install dependencies."""
from agno.agent import Agent
from agno.models.llama_cpp import LlamaCpp
from agno.tools.hackernews import HackerNewsTools
agent = Agent(
model=LlamaCpp(id="ggml-org/gpt-oss-20b-GGUF"),
tools=[HackerNewsTools()],
markdown=True,
)
agent.print_response("Whats happening in France?", stream=True)
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
Install LlamaCpp
llama-server -hf ggml-org/gpt-oss-20b-GGUF --ctx-size 0 --jinja -ub 2048 -b 2048
Install dependencies
uv pip install -U agno
Run Agent
python cookbook/11_models/llama_cpp/tool_use_stream.py
Was this page helpful?