* **Cloud services** that handle this for you
    * The cloud service will probably **handle replication for you**. It would possibly let you define **a process to run**, or a **container image** to use, in any case, it would most probably be **a single Uvicorn process**, and the cloud service would be in charge of replicating it.

!!! tip

    if summary:
        info["summary"] = summary
    if description:
        info["description"] = description
    if terms_of_service:
        info["termsOfService"] = terms_of_service
    if contact:
        info["contact"] = contact
    if license_info:
        info["license"] = license_info
    output: Dict[str, Any] = {"openapi": openapi_version, "info": info}

  [http.routers]

    [http.routers.app-http]
      entryPoints = ["http"]
      service = "app"
      rule = "PathPrefix(`/api/v1`)"
      middlewares = ["api-stripprefix"]

  [http.services]

    [http.services.app]
      [http.services.app.loadBalancer]
        [[http.services.app.loadBalancer.servers]]
          url = "http://127.0.0.1:8000"
```

For example, you might want to try <a href="https://speakeasyapi.dev/?utm_source=fastapi+repo&utm_medium=github+sponsorship" class="external-link" target="_blank">Speakeasy</a>.

There are also several other companies offering similar services that you can search and find online. 🤓

  [http.routers]

    [http.routers.app-http]
      entryPoints = ["http"]
      service = "app"
      rule = "PathPrefix(`/api/v1`)"
      middlewares = ["api-stripprefix"]

  [http.services]

    [http.services.app]
      [http.services.app.loadBalancer]
        [[http.services.app.loadBalancer.servers]]
          url = "http://127.0.0.1:8000"
```

  [http.routers]

    [http.routers.app-http]
      entryPoints = ["http"]
      service = "app"
      rule = "PathPrefix(`/api/v1`)"
      middlewares = ["api-stripprefix"]

  [http.services]

    [http.services.app]
      [http.services.app.loadBalancer]
        [[http.services.app.loadBalancer.servers]]
          url = "http://127.0.0.1:8000"
```

👉 📁 🔗 Traefik ⚙️ ➡ 🔡 `/api/v1`.

    link: https://www.tutlinks.com/deploy-fastapi-on-azure/
    title: Deploy FastAPI on Azure App Service
  - author: Davide Fiocco
    author_link: https://github.com/davidefiocco
    link: https://davidefiocco.github.io/streamlit-fastapi-ml-serving/
    title: Machine learning model serving in Python using FastAPI and streamlit
  - author: Netflix
    author_link: https://netflixtechblog.com/

Então você poderá "servir" eles com o comando `serve`:

<div class="termy">

```console
// Use o comando "serve" após rodar "build-all"
$ python ./scripts/docs.py serve

Warning: this is a very simple server. For development, use mkdocs serve instead.
This is here only to preview a site with translations already built.

# Abhängigkeiten

**FastAPI** hat ein sehr mächtiges, aber intuitives **<abbr title="Dependency Injection – Einbringen von Abhängigkeiten: Auch bekannt als Komponenten, Ressourcen, Provider, Services, Injectables">Dependency Injection</abbr>** System.

Es ist so konzipiert, sehr einfach zu verwenden zu sein und es jedem Entwickler sehr leicht zu machen, andere Komponenten mit **FastAPI** zu integrieren.

## Was ist „Dependency Injection“

## Vélemények

"_[...] I'm using **FastAPI** a ton these days. [...] I'm actually planning to use it for all of my team's **ML services at Microsoft**. Some of them are getting integrated into the core **Windows** product and some **Office** products._"