### Memory per Process { #memory-per-process }

Now, when the program loads things in memory, for example, a machine learning model in a variable, or the contents of a large file in a variable, all that **consumes a bit of the memory (RAM)** of the server.

在回傳給用戶端之前，它們會被轉成對應的值（此例為字串）：

{* ../../docs_src/path_params/tutorial005_py310.py hl[18,21,23] *}

你的用戶端會收到像這樣的 JSON 回應：

```JSON
{
  "model_name": "alexnet",
  "message": "Deep Learning FTW!"
}
```

## 包含路徑的路徑參數 { #path-parameters-containing-paths }

假設你有一個路徑為 `/files/{file_path}` 的「路徑操作」。

但你需要 `file_path` 本身就包含一個「路徑」，像是 `home/johndoe/myfile.txt`。

返回给客户端之前，会把枚举成员转换为对应的值（本例中为字符串）：

{* ../../docs_src/path_params/tutorial005_py310.py hl[18,21,23] *}

客户端中的 JSON 响应如下：

```JSON
{
  "model_name": "alexnet",
  "message": "Deep Learning FTW!"
}
```

## 包含路径的路径参数 { #path-parameters-containing-paths }

假设路径操作的路径为 `/files/{file_path}`。

但需要 `file_path` 中也包含路径，比如，`home/johndoe/myfile.txt`。

**FastAPI** is all based on these type hints, they give it many advantages and benefits.

But even if you never use **FastAPI**, you would benefit from learning a bit about them.

/// note

If you are a Python expert, and you already know everything about type hints, skip to the next chapter.

///

## Motivation { #motivation }

Let's start with a simple example:

# Tests

tf_cuda_library(
    name = "c_test_util",
    testonly = 1,
    srcs = ["c_test_util.cc"],
    hdrs = ["c_test_util.h"],
    visibility = [
        "//learning/brain:__subpackages__",
        "//tensorflow:__subpackages__",
    ],
    deps = [
        ":c_api",
        ":c_api_experimental",
        "//tensorflow/core:lib",
        "//tensorflow/core:protos_all_cc",

    ],
)

tf_cuda_library(
    name = "c_api_test_util",
    testonly = 1,
    srcs = ["c_api_test_util.cc"],
    hdrs = ["c_api_test_util.h"],
    visibility = [
        "//learning/brain:__subpackages__",
        "//tensorflow:__subpackages__",
    ],
    deps = [
        ":c_api",
        ":c_api_experimental",
        ":c_api_internal",
        "//tensorflow/c:c_test_util",

## Kullanım Senaryosu { #use-case }

Önce bir **kullanım senaryosu** örneğiyle başlayalım, sonra bunu bununla nasıl çözeceğimize bakalım.

Request’leri işlemek için kullanmak istediğiniz bazı **machine learning modelleriniz** olduğunu hayal edelim. 🤖

* <dfn title="Eine Methode des Machine Learning, die künstliche neuronale Netze mit zahlreichen versteckten Schichten zwischen Eingabe- und Ausgabeschicht verwendet und so eine umfassende interne Struktur entwickelt">Deep Learning</dfn>

## Überschriften { #headings }

//// tab | Test

* <dfn title="Un grupo de máquinas configuradas para estar conectadas y trabajar juntas de alguna manera.">clúster</dfn>
* <dfn title="Un método de Machine Learning que usa redes neuronales artificiales con numerosas capas ocultas entre las capas de entrada y salida, desarrollando así una estructura interna completa">Deep Learning</dfn>

## Encabezados { #headings }

//// tab | Prueba

### Desarrolla una webapp - un tutorial { #develop-a-webapp-a-tutorial }

## Caso de Uso { #use-case }

Empecemos con un ejemplo de **caso de uso** y luego veamos cómo resolverlo con esto.

Imaginemos que tienes algunos **modelos de machine learning** que quieres usar para manejar requests. 🤖