tool_use.py
Run the Example
1
Set up your virtual environment
2
Install dependencies
3
Export your SiliconFlow API key
4
Run the example
Save the code above as
tool_use.py, then run:Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Run a SiliconFlow web-search agent with tool calls and debug output visible.
"""Run `uv pip install duckduckgo-search` to install dependencies."""
from agno.agent import Agent
from agno.models.siliconflow import Siliconflow
from agno.tools.websearch import WebSearchTools
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
"""
The current version of the siliconflow-chat model's Function Calling capability is stable and supports tool integration effectively.
"""
agent = Agent(
model=Siliconflow(id="openai/gpt-oss-120b"),
tools=[WebSearchTools()],
show_tool_calls=True,
markdown=True,
debug_mode=True,
)
agent.print_response("What happing in America?")
# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
pass
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
Install dependencies
uv pip install -U agno ddgs openai
Export your SiliconFlow API key
export SILICONFLOW_API_KEY="your_siliconflow_api_key_here"
$Env:SILICONFLOW_API_KEY="your_siliconflow_api_key_here"
Run the example
tool_use.py, then run:python tool_use.py
Was this page helpful?