import modal

app = modal.App("app-name")

@app.function()
def basic_function(arg: str) -> str:
    return f"Result: {arg}"

@app.local_entrypoint()
def main():
    result = basic_function.remote("test")
    print(result)

# Single GPU
@app.function(gpu="A100")

# Specific memory variant
@app.function(gpu="A100-80GB")

# Multi-GPU
@app.function(gpu="H100:4")

# Fallbacks (tries in order)
@app.function(gpu=["H100", "A100", "any"])

# "any" = L4, A10G, or T4
@app.function(gpu="any")

# Debian slim (recommended)
modal.Image.debian_slim(python_version="3.11")

# From Dockerfile
modal.Image.from_dockerfile("./Dockerfile")

# From Docker registry
modal.Image.from_registry("nvidia/cuda:12.1.0-base-ubuntu22.04")

# pip (standard)
image.pip_install("torch", "transformers")

# uv (FASTER - 10-100x)
image.uv_pip_install("torch", "transformers")

# System packages
image.apt_install("ffmpeg", "libsm6")

# Shell commands
image.run_commands("apt-get update", "make install")

# Single file
image.add_local_file("./config.json", "/app/config.json")

# Directory
image.add_local_dir("./models", "/app/models")

# Python source
image.add_local_python_source("my_module")

# Environment variables
image.env({"VAR": "value"})

def download_model():
    from huggingface_hub import snapshot_download
    snapshot_download("model-name")

image.run_function(download_model, secrets=[...])

# Create/reference volume
vol = modal.Volume.from_name("my-vol", create_if_missing=True)

# Mount in function
@app.function(volumes={"/data": vol})
def func():
    # Read/write to /data
    vol.commit()  # Persist changes

# From dashboard (recommended)
modal.Secret.from_name("secret-name")

# From dictionary
modal.Secret.from_dict({"KEY": "value"})

# From local env
modal.Secret.from_local_environ(["KEY1", "KEY2"])

# From .env file
modal.Secret.from_dotenv()

# Usage
@app.function(secrets=[modal.Secret.from_name("api-keys")])
def func():
    import os
    key = os.environ["API_KEY"]

# Distributed dict
d = modal.Dict.from_name("cache", create_if_missing=True)
d["key"] = "value"
d.put("key", "value", ttl=3600)

# Distributed queue
q = modal.Queue.from_name("jobs", create_if_missing=True)
q.put("task")
item = q.get()

@app.function()
@modal.fastapi_endpoint()
def hello(name: str = "World"):
    return {"message": f"Hello, {name}!"}

from fastapi import FastAPI
web_app = FastAPI()

@web_app.post("/predict")
def predict(text: str):
    return {"result": process(text)}

@app.function()
@modal.asgi_app()
def fastapi_app():
    return web_app

from flask import Flask
flask_app = Flask(__name__)

@app.function()
@modal.wsgi_app()
def flask_endpoint():
    return flask_app

@app.function()
@modal.web_server(port=8000)
def custom_server():
    subprocess.run(["python", "-m", "http.server", "8000"])

@modal.asgi_app(custom_domains=["api.example.com"])

# Daily at 8 AM UTC
@app.function(schedule=modal.Cron("0 8 * * *"))

# With timezone
@app.function(schedule=modal.Cron("0 6 * * *", timezone="America/New_York"))

@app.function(schedule=modal.Period(hours=5))
@app.function(schedule=modal.Period(days=1))

# Parallel execution (up to 1000 concurrent)
results = list(func.map(items))

# Unordered (faster)
results = list(func.map(items, order_outputs=False))

# Spread args
pairs = [(1, 2), (3, 4)]
results = list(add.starmap(pairs))

# Async job (returns immediately)
call = func.spawn(data)
result = call.get()  # Get result later

# Spawn many
calls = [func.spawn(item) for item in items]
results = [call.get() for call in calls]

@app.cls(gpu="A100", container_idle_timeout=300)
class Server:

    @modal.enter()
    def load(self):
        self.model = load_model()

    @modal.method()
    def predict(self, text):
        return self.model(text)

    @modal.exit()
    def cleanup(self):
        del self.model

@modal.concurrent(max_inputs=100, target_inputs=80)
@modal.method()
def batched(self, item):
    pass

modal run app.py              # Run function
modal serve app.py            # Hot-reload dev server
modal shell app.py            # Interactive shell
modal shell app.py --gpu A100 # Shell with GPU

modal deploy app.py           # Deploy
modal app list                # List apps
modal app logs app-name       # View logs
modal app stop app-name       # Stop app

# Volumes
modal volume create name
modal volume list
modal volume put name local remote
modal volume get name remote local

# Secrets
modal secret create name KEY=value
modal secret list

# Environments
modal environment create staging

@app.cls(gpu="A100", container_idle_timeout=300)
class LLM:
    @modal.enter()
    def load(self):
        from vllm import LLM
        self.llm = LLM(model="...")

    @modal.method()
    def generate(self, prompt):
        return self.llm.generate([prompt])

@app.function(volumes={"/data": vol})
def process(file):
    # Process file
    vol.commit()

# Parallel
results = list(process.map(files))

@app.function(
    schedule=modal.Cron("0 6 * * *"),
    secrets=[modal.Secret.from_name("db")]
)
def daily_etl():
    extract()
    transform()
    load()