```

</div>

Na saída, há uma linha com algo como:

```hl_lines="4"
INFO:     Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
```

Essa linha mostra a URL onde a sua aplicação está sendo servida, na sua máquina local.

### Confira { #check-it }

Abra o seu navegador em <a href="http://127.0.0.1:8000" class="external-link" target="_blank">http://127.0.0.1:8000</a>.

Você verá essa resposta em JSON:

     * - Run the test.
     * - Pull the relevant lines of output from the test into a testcases file.
     * - Test the output:
     * --- cat testcases | while read L; do
     *       X=($L)
     *       A=$( cd /b/c && sudo mkdir -p ${X[0]} && cd ${X[0]} && pwd |
     *           sed -e 's#^//*#/#' )
     *       B=$( cd /b/c && cd ${X[1]} && pwd )
     *       cmp -s <(echo $A) <(echo $B) || echo "$X[0] -> $A vs. $B"

fi

if [ ! -f ./kes ]; then
	wget --quiet -O kes https://github.com/minio/kes/releases/latest/download/kes-linux-amd64 &&
		chmod +x kes
fi

if ! openssl version &>/dev/null; then
	apt install openssl || sudo apt install opensssl
fi

# Start KES Server
(./kes server --dev 2>&1 >kes-server.log) &
kes_pid=$!
sleep 5s
API_KEY=$(grep "API Key" <kes-server.log | awk -F" " '{print $3}')

Eu adoro saber como o **FastAPI** está sendo usado, o que você tem curtido nele, em qual projeto/empresa você o utiliza, etc.

## Vote no FastAPI { #vote-for-fastapi }

dd if=/dev/urandom bs=1 count=7048531 of=/tmp/7048531.txt
dd if=/dev/urandom bs=1 count=2847391 of=/tmp/2847391.txt

sudo apt install jq -y

      - name: Install Graphviz (MacOS)
        if: runner.os == 'macOS'
        run: brew install graphviz

      - name: Install Graphviz (Ubuntu)
        if: runner.os == 'Linux'
        run: sudo apt-get install graphviz

      - name: Install Graphviz (Windows)
        if: runner.os == 'Windows'
        run: choco install graphviz

      - name: Checkout maven

*   Clean up `BatchNormalization` layer's `trainable` property to act like
    standard python state when it's used inside `tf.functions` (frozen at
    tracing time), instead of acting like a pseudo-variable whose updates *kind
    of sometimes* get reflected in already-traced `tf.function` traces.
*   Add the `Conv1DTranspose` layer.
*   Refine the semantics of `SensitivitySpecificityBase` derived metrics. See

## Opiniões { #opinions }

"*[...] Estou usando **FastAPI** muito esses dias. [...] Estou na verdade planejando utilizar ele em todos os times de **serviços _Machine Learning_ na Microsoft**. Alguns deles estão sendo integrados no _core_ do produto **Windows** e alguns produtos **Office**.*"

```

This tells Traefik to listen on port 9999 and to use another file `routes.toml`.

/// tip

We are using port 9999 instead of the standard HTTP port 80 so that you don't have to run it with admin (`sudo`) privileges.

///

Now create that other file `routes.toml`:

```TOML hl_lines="5  12  20"
[http]
  [http.middlewares]

    [http.middlewares.api-stripprefix.stripPrefix]

```

Это говорит Traefik слушать порт 9999 и использовать другой файл `routes.toml`.

/// tip | Совет

Мы используем порт 9999 вместо стандартного HTTP‑порта 80, чтобы не нужно было запускать с правами администратора (`sudo`).

///

Теперь создайте второй файл `routes.toml`:

```TOML hl_lines="5  12  20"
[http]
  [http.middlewares]

    [http.middlewares.api-stripprefix.stripPrefix]
      prefixes = ["/api/v1"]