Quickstart: Build and deploy a Python (smolagents) web app to Cloud Run

Write the sample application

To write an application in Python:

1. Create a new directory named my-agent-app and change directory into it:

   mkdir my-agent-app
   cd my-agent-app
   

2. Create a file named main.py and paste the following code into it:

   import os
   from fastapi import FastAPI, HTTPException
   from pydantic import BaseModel
   from smolagents import CodeAgent, LiteLLMModel, tool
   
   # 1. Define a simple tool for the agent
   @tool
   def get_greeting(name: str) -> str:
     """
     Returns a special greeting for the user.
     Args:
         name: The name of the person to greet.
     """
     return f"Hello {name}, welcome to the agentic world running on Cloud Run!"
   
   # 2. Initialize the Gemini Model via LiteLLM
   # Make sure GEMINI_API_KEY is set in your environment variables
   model = LiteLLMModel(
   model_id="gemini/gemini-2.5-flash", # This is the model name. If a newer model is available, you can use that.
   api_key=os.environ.get("GEMINI_API_KEY")
   )
   
   # 3. Create the CodeAgent
   agent = CodeAgent(
     tools=[get_greeting],
     model=model,
     add_base_tools=True # Adds basic python tools like print
   )
   
   # 4. Setup FastAPI
   app = FastAPI()
   
   class AgentRequest(BaseModel):
     task: str
   
   @app.get("/")
   def health_check():
     return {"status": "running", "service": "smolagents-fastapi"}
   
   @app.post("/run")
   def run_agent(request: AgentRequest):
     try:
       # Run the agent with the user's task
       response = agent.run(request.task)
       return {"response": str(response)}
     except Exception as e:
       raise HTTPException(status_code=500, detail=str(e))
   

3. Create a file named requirements.txt and paste the following code into it:

   fastapi
   uvicorn
   smolagents[toolkit]
   litellm
   

Deploy to Cloud Run from source

Deploy from source automatically builds a container image from source code and deploys it.

To deploy from source using the following command:

  gcloud run deploy smolagents-demo \
    --source . \
    --region us-central1 \
    --no-allow-unauthenticated \
    --set-env-vars GEMINI_API_KEY=API_KEY

Replace API_KEY with your Google AI Studio API key.

Cloud Run displays the service URL, such as https://smolagents-demo-xyz-uc.a.run.app, after you successfully deploy the app.

Test your Cloud Run service

Test your service by sending a task to the agent using the following curl command:

  curl -X POST YOUR-SERVICE-URL/run \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $(gcloud auth print-identity-token)" \
    -d '{"task": "Use the greeting tool to say hello to Gemini User"}'

Replace YOUR-SERVICE-URL with your service's URL.

The agent sends the following response:

{
 "response": "Hello Gemini User, welcome to the agentic world running on Cloud Run!"
}

To verify your service is working correctly, check the Logs tab of the Cloud Run service.

gcloud run services delete SERVICE --region REGION