OpenAI ChatGPT是一种人工智能聊天机器人，基于大规模的深度学习模型，专门用于生成自然语言文本。它能够理解和生成人类语言，因此能够与用户进行对话、回答问题、提供信息和协助完成各种任务。ChatGPT能够用于多种应用场景，包括客户服务、教育辅导、内容创作等等。

ChatGPT的底层技术基于Transformer架构，经过大量文本数据的训练，使其在理解上下文和生成连贯的回应方面表现出色。用户可以通过输入文本与其互动，ChatGPT会根据上下文生成相关的答案或建议。

Python接口

申请第三方测试key

https://github.com/chatanywhere/GPT_API_free

安装OpenAI模块

pip install openai

from openai import OpenAI

def chat_openai(question, model="gpt-3.5-turbo"):
	text = ''
	stream = True
	openai_url = 'https://api.chatanywhere.tech/v1'
	openai_key = 'sk-xxx'

	client = OpenAI(base_url=openai_url, api_key=openai_key)
	
	response = client.chat.completions.create(model=model, stream=stream, messages=[
		{"role": "user", "content": question},
	])
	
	if stream:
		for chunk in response:
			content = chunk.choices[0].delta.content
			if not content:
				continue
			text += content
			print(content, end='', flush=True)
	else:
		content = response.choices[0].message.content
		text += content
		print(content)
	
	print('\n')
	return text

if __name__ == '__main__':
	chat_openai('你是谁')

Kimi的API兼容OpenAI，只需要修改url和key即可，API KEY需要到官方网站申请，模型支持

• moonshot-v1-128k
• moonshot-v1-32k
• moonshot-v1-8k

Kimi url

https://api.moonshot.cn/v1

Kimi API key申请

https://platform.moonshot.cn/console/api-keys

Gradio创建webUI

Grdio是一个开源Python库，可以快速创建大语言模型的交互webUI，无需了解HTTP、CSS、JavaScript等web语言。

安装gradio库

pip install gradio

在上一个例子基础上添加gradio创建的UI

from openai import OpenAI
import gradio as gr

def chat_openai(self, question, model="gpt-3.5-turbo"):
	text = ''
	stream = True
	openai_url = 'https://api.chatanywhere.tech/v1'
	openai_key = 'sk-xxx'

	client = OpenAI(base_url=openai_url, api_key=openai_key)
	
	response = client.chat.completions.create(model=model, stream=stream, messages=[
		{"role": "user", "content": question},
	])
	
	if stream:
		for chunk in response:
			content = chunk.choices[0].delta.content
			if not content:
				continue
			text += content
			print(content, end='', flush=True)
			yield text
	else:
		content = response.choices[0].message.content
		text += content
		print(content)
		yield text
	
	print('\n')
	return text
	
def chat_response(message, history):
	resp = chat_openai(message)
	for r in resp:
		yield r

def webui():
	demo = gr.ChatInterface(fn=chat_response, type='messages', examples=['你好', '你是谁'])
	demo.launch(server_name='0.0.0.0')

if __name__ == '__main__':
	webui()

运行效果如下图所示