vLLM Structured Output

Return a typed MovieScript object from a vLLM agent with a Pydantic output schema.

structured_output.py

"""
Vllm Structured Output
======================

Cookbook example for `vllm/structured_output.py`.
"""

from typing import List

from agno.agent import Agent
from agno.models.vllm import VLLM
from pydantic import BaseModel, Field

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


class MovieScript(BaseModel):
    name: str = Field(..., description="Give a name to this movie")
    setting: str = Field(
        ..., description="Provide a nice setting for a blockbuster movie."
    )
    ending: str = Field(
        ...,
        description="Ending of the movie. If not available, provide a happy ending.",
    )
    genre: str = Field(
        ...,
        description="Genre of the movie. If not available, select action, thriller or romantic comedy.",
    )
    characters: List[str] = Field(..., description="Name of characters for this movie.")
    storyline: str = Field(
        ..., description="3 sentence storyline for the movie. Make it exciting!"
    )


agent = Agent(
    model=VLLM(id="Qwen/Qwen2.5-7B-Instruct", top_k=20, enable_thinking=False),
    description="You write movie scripts.",
    output_schema=MovieScript,
)

agent.print_response("Llamas ruling the world")

# ---------------------------------------------------------------------------
# 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 in the environment that will serve the model:

   uv pip install -U vllm
   
5. Start vLLM

   Serve the model used by this example:

   vllm serve Qwen/Qwen2.5-7B-Instruct
   
6. Run the example

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

   python structured_output.py
   

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