thinking_tool_calls.py
Run the Example
1
Set up your virtual environment
2
Install dependencies
3
Export your DeepSeek API key
4
Run the example
Save the code above as
thinking_tool_calls.py, then run:Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Combine DeepSeek thinking mode with web search tool calls and show full reasoning.
"""Run `uv pip install ddgs` to install dependencies."""
from agno.agent import Agent
from agno.models.deepseek import DeepSeek
from agno.tools.websearch import WebSearchTools
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
"""
DeepSeek model's thinking mode now supports tool calls.
Before outputting the final answer, the model can engage in multiple turns of reasoning and tool calls to improve the quality of the response.
"""
agent = Agent(
model=DeepSeek(id="deepseek-v4-pro"),
tools=[WebSearchTools()],
markdown=True,
stream=True,
)
agent.print_response("Whats happening in France?", show_full_reasoning=True)
# ---------------------------------------------------------------------------
# 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 DeepSeek API key
export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
$Env:DEEPSEEK_API_KEY="your_deepseek_api_key_here"
Run the example
thinking_tool_calls.py, then run:python thinking_tool_calls.py
Was this page helpful?