Deployment Strategies

deployed_program = kapso.deploy(solution, strategy=DeployStrategy.LOCAL)
result = deployed_program.run({"data_path": "./data.csv"})

# In strategy config
local:
  module: "main"      # Module to import
  callable: "predict" # Function to call
  timeout: 300        # Execution timeout

deployed_program = kapso.deploy(solution, strategy=DeployStrategy.DOCKER)
result = deployed_program.run({"data_path": "/data/input.csv"})

FROM python:3.12-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
CMD ["python", "run.py"]

pip install modal
modal token new

deployed_program = kapso.deploy(solution, strategy=DeployStrategy.MODAL)
result = deployed_program.run({"prompt": "Hello, world!"})

import modal

app = modal.App("kapso-deployment")

@app.function(gpu="A100")
def predict(inputs):
    # Load model and run inference
    return result

pip install bentoml

deployed_program = kapso.deploy(solution, strategy=DeployStrategy.BENTOML)
result = deployed_program.run({"features": [1, 2, 3]})

import bentoml

@bentoml.service
class KapsoService:
    @bentoml.api
    def predict(self, inputs: dict) -> dict:
        return self.model.predict(inputs)

pip install langgraph

deployed_program = kapso.deploy(solution, strategy=DeployStrategy.LANGGRAPH)
result = deployed_program.run({"query": "What is 2+2?"})

deployed_program = kapso.deploy(solution, strategy=DeployStrategy.AUTO)
# System chooses based on:
# - Code complexity
# - Resource requirements (GPU, memory)
# - Dependencies
# - Target environment

# Returned by adapter
run_interface = {
    "type": "function",     # or "http", "grpc"
    "module": "main",       # Python module
    "callable": "predict",  # Function name
    "endpoint": None,       # HTTP endpoint (if applicable)
}

deployed_program = kapso.deploy(
    solution,
    strategy=DeployStrategy.DOCKER,
    env_vars={
        "API_KEY": "...",
        "MODEL_PATH": "/models/v1",
    },
)