XFE Git
XFE Studio Git
Git 首页 全局搜索
XFE 主站 文档 NuGet
公开
关注 0 Fork 0 Star 1
返回提交历史

XFEstudio/gpt4free

docs(docs/client.md): update G4F Client API guide

96e1efee
kqlio67 <kqlio67@users.noreply.github.com>
提交于

代码差异

1 个文件 +28 -2
Modified docs/client.md +28 -2
@@ -7,6 +7,7 @@
7 7 - [Getting Started](#getting-started)
8 8 - [Switching to G4F Client](#switching-to-g4f-client)
9 9 - [Initializing the Client](#initializing-the-client)
10 - [Creating Chat Completions](#creating-chat-completions)
10 11 - [Configuration](#configuration)
11 12 - [Usage Examples](#usage-examples)
12 13 - [Text Completions](#text-completions)
@@ -22,7 +23,7 @@
22 23
23 24
24 25 ## Introduction
25 Welcome to the G4F Client API, a cutting-edge tool for seamlessly integrating advanced AI capabilities into your Python applications. This guide is designed to facilitate your transition from using the OpenAI client to the G4F Client, offering enhanced features while maintaining compatibility with the existing OpenAI API.
26 Welcome to the G4F Client API, a cutting-edge tool for seamlessly integrating advanced AI capabilities into your Python applications. This guide is designed to facilitate your transition from using the OpenAI or Anthropic client to the G4F Client, offering enhanced features while maintaining compatibility with the existing OpenAI and Anthropic API.
26 27
27 28 ## Getting Started
28 29 ### Switching to G4F Client
@@ -42,7 +43,7 @@ from g4f.client import Client as OpenAI
42 43
43 44
44 45
45 The G4F Client preserves the same familiar API interface as OpenAI, ensuring a smooth transition process.
46 The G4F Client preserves the same familiar API interface as OpenAI or Anthropic, ensuring a smooth transition process.
46 47
47 48 ## Initializing the Client
48 49 To utilize the G4F Client, create a new instance. **Below is an example showcasing custom providers:**
@@ -56,6 +57,30 @@ client = Client(
56 57 # Add any other necessary parameters
57 58 )
58 59 ```
60
61 ## Creating Chat Completions
62 **Here’s an improved example of creating chat completions:**
63 ```python
64 response = client.chat.completions.create(
65 system="You are a helpful assistant.",
66 model="gpt-3.5-turbo",
67 messages=[
68 {
69 "role": "user",
70 "content": "Say this is a test"
71 }
72 ]
73 # Add any other necessary parameters
74 )
75 ```
76
77 **This example:**
78 - Sets a system message to define the assistant's role
79 - Asks a specific question `Say this is a test`
80 - Configures various parameters like temperature and max_tokens for more control over the output
81 - Disables streaming for a complete response
82
83 You can adjust these parameters based on your specific needs.
59 84
60 85
61 86 ## Configuration
@@ -271,6 +296,7 @@ while True:
271 296 try:
272 297 # Get GPT's response
273 298 response = client.chat.completions.create(
299 system="You are a helpful assistant.",
274 300 messages=messages,
275 301 model=g4f.models.default,
276 302 )