<div style="text-align: right; margin-right: 10%;">Kabir Khan - <strong>Microsoft</strong> <a href="https://github.com/tiangolo/fastapi/pull/26" target="_blank"><small>(ref)</small></a></div>

---

"_We adopted the **FastAPI** library to spawn a **REST** server that can be queried to obtain **predictions**. [for Ludwig]_"

<div style="text-align: right; margin-right: 10%;">Kabir Khan - <strong>Microsoft</strong> <a href="https://github.com/tiangolo/fastapi/pull/26" target="_blank"><small>(ref)</small></a></div>

---

"_Мы использовали библиотеку **FastAPI** для создания сервера **REST**, к которому можно делать запросы для получения **прогнозов**. [для Ludwig]_"

<div style="text-align: right; margin-right: 10%;">Kabir Khan - <strong>Microsoft</strong> <a href="https://github.com/tiangolo/fastapi/pull/26" target="_blank"><small>(ref)</small></a></div>

---

"_We adopted the **FastAPI** library to spawn a **REST** server that can be queried to obtain **predictions**. [for Ludwig]_"

---

## Instale o FastAPI

O primeiro passo é instalar o FastAPI.

Para o tutorial, você deve querer instalá-lo com todas as dependências e recursos opicionais.

<div class="termy">

```console
$ pip install "fastapi[all]"

---> 100%
```

</div>

...isso também inclui o `uvicorn`, que você pode usar como o servidor que rodará seu código.

!!! note "Nota"
    Você também pode instalar parte por parte.

## Gunicorn und Uvicorn installieren

<div class="termy">

```console
$ pip install "uvicorn[standard]" gunicorn

---> 100%
```

</div>

Dadurch wird sowohl Uvicorn mit zusätzlichen `standard`-Packages (um eine hohe Leistung zu erzielen) als auch Gunicorn installiert.

## Gunicorn mit Uvicorn-Workern ausführen

Dann können Sie Gunicorn ausführen mit:

<div class="termy">

```console

<div style="text-align: right; margin-right: 10%;">Kabir Khan - <strong>微软</strong> <a href="https://github.com/tiangolo/fastapi/pull/26" target="_blank"><small>(ref)</small></a></div>

---

「_我们选择了 **FastAPI** 来创建用于获取**预测结果**的 **REST** 服务。[用于 Ludwig]_」

<div class="termy">

```console
$ python myapp.py
```

</div>

그러나 다음과 같이 다른 파일을 가져올 때는 호출되지 않습니다.

```Python
from myapp import app
```

#### 추가 세부사항

파일 이름이 `myapp.py`라고 가정해 보겠습니다.

다음과 같이 실행하면

<div class="termy">

```console
$ python myapp.py
```

</div>

然后与Gunicorn兼容的**Uvicorn worker**类将负责将Gunicorn发送的数据转换为ASGI标准以供FastAPI使用。

## 安装 Gunicorn 和 Uvicorn

<div class="termy">

```console
$ pip install "uvicorn[standard]" gunicorn

---> 100%
```

</div>

这将安装带有`standard`扩展包（以获得高性能）的 Uvicorn 和 Gunicorn。

## Run Gunicorn with Uvicorn Workers

接下来你可以通过以下命令运行Gunicorn:

<div class="termy">

```console

## Install Gunicorn and Uvicorn

<div class="termy">

```console
$ pip install "uvicorn[standard]" gunicorn

---> 100%
```

</div>

That will install both Uvicorn with the `standard` extra packages (to get high performance) and Gunicorn.

## Run Gunicorn with Uvicorn Workers

Then you can run Gunicorn with:

<div class="termy">

```console

然后，它把请求重定位到运行在 `http://127.0.0.1:8000` 上的 Uvicorn。

现在，启动 Traefik：

<div class="termy">

```console
$ ./traefik --configFile=traefik.toml

INFO[0000] Configuration loaded from file: /home/user/awesomeapi/traefik.toml
```

</div>

接下来，使用 Uvicorn 启动应用，并使用 `--root-path` 选项：

<div class="termy">

```console
$ uvicorn main:app --root-path /api/v1