Here I'm also highlighting contributions from sponsors.

    server.requireClientAuth()
    val call = client.newCall(Request.Builder().url(server.url("/")).build())
    assertFailsWith<IOException> {
      call.execute()
    }

    // Observed Events are variable
    // JDK 14
    // CallStart, ProxySelectStart, ProxySelectEnd, DnsStart, DnsEnd, ConnectStart, SecureConnectStart,

   * {@code lexicographical(Collections.reverseOrder(comparator))} (consider how each would order
   * {@code [1]} and {@code [1, 1]}).
   */
  // Note: 90% of the time we don't add type parameters or wildcards that serve only to "tweak" the
  // desired return type. However, *nested* generics introduce a special class of problems that we
  // think tip it over into being worthwhile.

scenario would require a malicious user to be able to control the model which as
stated above is already equivalent to code execution. In any case, the
recommendation is not to serve models using Eager mode since it also has
performance limitations.

## Multi-Tenant environments

It is possible to run multiple TensorFlow models in parallel. For example,

# Run a Server Manually { #run-a-server-manually }

## Use the `fastapi run` Command { #use-the-fastapi-run-command }

In short, use `fastapi run` to serve your FastAPI application:

<div class="termy">

```console
$ <font color="#4E9A06">fastapi</font> run <u style="text-decoration-style:solid">main.py</u>

  <span style="background-color:#009485"><font color="#D3D7CF"> FastAPI </font></span>  Starting production server 🚀

# Object Lambda

            "description": "Entorno de producción"
        }
    ],
    "paths": {
            // Más cosas aquí
    }
}
```

/// tip | Consejo

Observa el server auto-generado con un valor `url` de `/api/v1`, tomado del `root_path`.

///

    tensorflow::shape_inference::InferenceContext* ic, int num_dims,
    const int64_t* dims) {
  if (num_dims != -1) {
    std::vector<tensorflow::shape_inference::DimensionHandle> dim_vec;
    dim_vec.reserve(num_dims);
    for (int i = 0; i < num_dims; ++i) {
      dim_vec.push_back(ic->MakeDim(dims[i]));
    }
    return ic->MakeShape(dim_vec);
  } else {
    return ic->UnknownShape();
  }
}

* Restarts
* Replication (the number of processes running)
* Memory
* Previous steps before starting

We'll see how they would affect **deployments**.

In the end, the ultimate objective is to be able to **serve your API clients** in a way that is **secure**, to **avoid disruptions**, and to use the **compute resources** (for example remote servers/virtual machines) as efficiently as possible. 🚀

E esses modelos estão compartilhando muitos dos dados e duplicando nomes e tipos de atributos.

Nós poderíamos fazer melhor.

Podemos declarar um modelo `UserBase` que serve como base para nossos outros modelos. E então podemos fazer subclasses desse modelo que herdam seus atributos (declarações de tipo, validação, etc.).

Toda conversão de dados, validação, documentação, etc. ainda funcionará normalmente.