---

"_Adoptamos el paquete **FastAPI** para crear un servidor **REST** que pueda ser consultado para obtener **predicciones**. [para Ludwig]_"

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

---

"_我們使用 **FastAPI** 來建立產生**預測**結果的 **REST** 伺服器。 [for Ludwig]_"

/// info | 说明

Python 3.4 及之后版本支持<a href="https://docs.python.org/zh-cn/3/library/enum.html" class="external-link" target="_blank">枚举（即 enums）</a>。

///

/// tip | 提示

**AlexNet**、**ResNet**、**LeNet** 是机器学习<abbr title="技术上来说是深度学习模型架构">模型</abbr>。

///

### 声明*路径参数*

使用 Enum 类（`ModelName`）创建使用类型注解的*路径参数*：

{* ../../docs_src/path_params/tutorial005.py hl[16] *}

### 查看文档

Em seguida, crie atributos de classe com valores fixos, que serão os valores válidos disponíveis:

{* ../../docs_src/path_params/tutorial005_py39.py hl[1,6:9] *}

/// tip | Dica
Se você está se perguntando, "AlexNet", "ResNet" e "LeNet" são apenas nomes de <abbr title="Tecnicamente, arquiteturas de modelos de Deep Learning">modelos</abbr> de Aprendizado de Máquina.
///

### Declare um parâmetro de path { #declare-a-path-parameter }

---

"_Мы начали использовать библиотеку **FastAPI**, чтобы поднять **REST**-сервер, к которому можно обращаться за **предсказаниями**. [для Ludwig]_"

Das müssen Sie selbst in Ihrem Code tun und sicherstellen, dass Sie diese JSON-Schlüssel verwenden.

Es ist fast das Einzige, woran Sie denken müssen, es selbst richtigzumachen und die Spezifikationen einzuhalten.

Den Rest erledigt **FastAPI** für Sie.

///

## Die Abhängigkeiten aktualisieren { #update-the-dependencies }

Jetzt werden wir unsere Abhängigkeiten aktualisieren.

This is something that you have to do yourself in your code, and make sure you use those JSON keys.

It's almost the only thing that you have to remember to do correctly yourself, to be compliant with the specifications.

For the rest, **FastAPI** handles it for you.

///

## Update the dependencies { #update-the-dependencies }

Now we are going to update our dependencies.

We want to get the `current_user` *only* if this user is active.

    state = STATE_READING_RESPONSE_BODY
    carrier.noNewExchanges()
    return UnknownLengthSource(url)
  }

  /**
   * Sets the delegate of `timeout` to [Timeout.NONE] and resets its underlying timeout
   * to the default configuration. Use this to avoid unexpected sharing of timeouts between pooled
   * connections.
   */
  private fun detachTimeout(timeout: ForwardingTimeout) {

/// info | 정보

<a href="https://docs.python.org/3/library/enum.html" class="external-link" target="_blank">열거형(또는 enums)</a>은 파이썬 버전 3.4 이후로 사용 가능합니다.

///

/// tip | 팁

혹시 궁금하다면, "AlexNet", "ResNet", 그리고 "LeNet"은 그저 기계 학습 <abbr title="기술적으로 정확히는 딥 러닝 모델 구조">모델</abbr>들의 이름입니다.

///

### *경로 매개변수* 선언

생성한 열거형 클래스(`ModelName`)를 사용하는 타입 어노테이션으로 *경로 매개변수*를 만듭니다:

pkg archive/zip, type Decompressor func(io.Reader) io.ReadCloser
pkg bufio, method (*Reader) Reset(io.Reader)
pkg bufio, method (*Writer) Reset(io.Writer)
pkg compress/flate, method (*Writer) Reset(io.Writer)
pkg compress/gzip, method (*Writer) Reset(io.Writer)
pkg compress/zlib, method (*Writer) Reset(io.Writer)
pkg container/heap, func Fix(Interface, int)
pkg container/list, method (*List) MoveAfter(*Element, *Element)