Code Generation

Code generation example with DeepSeek-Coder.

Generate Python code with DeepSeek Coder served by vLLM.

code_generation.py

"""Code generation example with DeepSeek-Coder.
Run vLLM model: vllm serve deepseek-ai/deepseek-coder-6.7b-instruct \
        --dtype float32 \
        --tool-call-parser pythonic
"""

from agno.agent import Agent
from agno.models.vllm import VLLM

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=VLLM(id="deepseek-ai/deepseek-coder-6.7b-instruct"),
    description="You are an expert Python developer.",
    markdown=True,
)

agent.print_response(
    "Write a Python function that returns the nth Fibonacci number using dynamic programming."
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno openai
   
3. Export your vLLM API key

   Mac/Linux

   export VLLM_API_KEY="your_vllm_api_key_here"
   

   $Env:VLLM_API_KEY="your_vllm_api_key_here"
   
4. Install vLLM

   Install vLLM on a supported platform with a compatible accelerator:

   uv pip install -U vllm
   
5. Start vLLM

   In a separate terminal with the virtual environment active, serve the model used by this example:

   vllm serve deepseek-ai/deepseek-coder-6.7b-instruct --dtype float32 --tool-call-parser pythonic
   
6. Run the example

   Save the code above as code_generation.py, then run:

   python code_generation.py
   

Full source: cookbook/90_models/vllm/code_generation.py