Modal logo
GuideReference

Overview

Introduction Example: Hello, world Tutorial: A simple web scraper

Custom container images

Custom container images Private registries Example: Use a headless browser

Scaling out

Scaling out Example: Hyperparameter search Example: Stock prices in parallel Example: Face detection on YouTube videos

Secrets and environment variables

Secrets Example: Write to Google Sheets

GPUs and other resources

GPU acceleration Requesting more memory Requesting more CPU

Deployment

Managing deployments Invoke deployed functions

Scheduling and cron jobs

Scheduling remote cron jobs Example: Hacker News Slackbot

Web endpoints

Web endpoints Web endpoint URLs Request timeouts Example: Document OCR job queue Example: Document OCR web app Example: Dynamic SVG badge

Sharing data

Passing local data Shared volumes

Machine learning examples

Fast Stable diffusion Transcribe podcasts in 1 minute with OpenAI's Whisper model Create Dreambooth Pet Art with HuggingFace and Gradio Train a FastAI model with WandB, and share it with Gradio Fit a model using TensorFlow and TensorBoard Run batch inference with HuggingFace Serve an object detection model on the web (with webcam input) Question-answering with LangChain Play with ControlNet

Example integrations

DuckDB: Analyze NYC taxi data in parallel Blender: Distributed 3D rendering SQLite: Publish explorable data with Datasette

Reliability and robustness

Failures and retries Preemption Timeouts Troubleshooting

Other topics

Developing and debugging Cold start performance Workspaces Asynchronous usage Global variables Container lifecycle (beta) Apps, stubs, and entrypoints Useful snippets Example: Algolia docsearch crawler

Managing deployments

Once you’ve finished using modal run or modal serve to iterate on your Modal code, it’s time to deploy. A Modal deployment creates and then persists an application and its objects, providing the following benefits:

  • Repeated application function executions will be grouped under the deployment, aiding observability and usage tracking. Programmatically triggering lots of ephemeral app runs can clutter your web and CLI interfaces.
  • Function calls are much faster because deployed functions are persistent and reused, not created on-demand by calls. Learn how to trigger deployed functions in Invoking deployed functions.
  • Scheduled functions will continue scheduling separate from any local iteration you do, and will notify you on failure.
  • Webhooks keep running when you close your laptop, and their URL address matches the deployment name.

Creating deployments

Deployments are created using the modal deploy command.

 % modal deploy whisper_pod_transcriber.main
✓ Initialized. View app page at https://modal.com/apps/ap-PYc2Tb7JrkskFUI8U5w0KG.
✓ Created objects.
├── 🔨 Created populate_podcast_metadata.
├── 🔨 Mounted /home/ubuntu/whisper_pod_transcriber at /root/whisper_pod_transcriber
├── 🔨 Created fastapi_app => https://modal-labs-whisper-pod-transcriber-fastapi-app.modal.run
├── 🔨 Mounted /home/ubuntu/whisper_pod_transcriber/whisper_frontend/dist at /assets
├── 🔨 Created search_podcast.
├── 🔨 Created refresh_index.
├── 🔨 Created transcribe_segment.
├── 🔨 Created transcribe_episode..
└── 🔨 Created fetch_episodes.
✓ App deployed! 🎉

View Deployment: https://modal.com/apps/modal-labs/whisper-pod-transcriber

Running this command on an existing deployment will redeploy the app, incrementing its version.

Viewing deployments

Deployments can be viewed either on the apps web page or by using the modal app list command.

viewing deployments in the web interface

Stopping deployments

Deployments can be stopped in the web UI by clicking the red delete button on a deployment’s app page, or alternatively by using the modal app stop command.

Stopped deployments are eventually garbage collected.