【DeepLearning.AI】吴恩达系列课程——使用Gradio构建AI应用

pip install python
pip install gradio

# update
pip install --upgrade gradio -i https://mirror.baidu.com/pypi/simple

import gradio as gr

def greet(name):
    return "Hello " + name + "!"

demo = gr.Interface(fn=greet, inputs="text", outputs="text")

    
if \_\_name\_\_ == "\_\_main\_\_":
    demo.launch()   **输出**：

from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import gradio as gr

# 使用我们下载到本地的模型
model = AutoModelForSeq2SeqLM.from\_pretrained('./model/distilbart-cnn-12-6')
tokenizer = AutoTokenizer.from\_pretrained('./model/distilbart-cnn-12-6')
get\_completion = pipeline("summarization", model=model, tokenizer=tokenizer)

# 输入文本，调用模型来返回输出
def summarize(input):
    output = get\_completion(input)
    return output[0]['summary\_text']


gr.close\_all()
demo = gr.Interface(fn=summarize, inputs="text", outputs="text")
demo.launch(share=True)

from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForTokenClassification
import gradio as gr

model = AutoModelForTokenClassification.from_pretrained('./model/bert-base-NER')
tokenizer = AutoTokenizer.from_pretrained('./model/bert-base-NER')
get_completion = pipeline("token-classification", model=model, tokenizer=tokenizer)


def ner(input):
    output = get_completion(input)
    return {"text": input, "entities": output}


gr.close_all()
demo = gr.Interface(fn=ner,
                    inputs=[gr.Textbox(label="Text to find entities", lines=2)],
                    # gr.HighlightedText是Gradio库中的一个组件，它创建了一个可以高亮显示文本的区域。你可以在gr.HighlightedText中使用label参数来设置文本区域的标签
                    outputs=[gr.HighlightedText(label="Text with entities")],
                    title="NER with dslim/bert-base-NER",
                    description="Find entities using the `dslim/bert-base-NER` model under the hood!",
                    allow_flagging="never",
                    #Here we introduce a new tag, examples, easy to use examples for your application
                    examples=["My name is Andrew and I live in California", "My name is Poli and work at HuggingFace"])
demo.launch(share=True)

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.models.nlp import T5ForConditionalGeneration
from modelscope.preprocessors import TextGenerationT5Preprocessor
model = T5ForConditionalGeneration.from_pretrained('ClueAI/ChatYuan-large', revision='v1.0.0')
preprocessor = TextGenerationT5Preprocessor(model.model_dir)
pipeline_t2t = pipeline(task=Tasks.text2text_generation, model=model, preprocessor=preprocessor)

def preprocess(text):
  text = text.replace("\n", "\\n").replace("\t", "\\t")
  return text

def postprocess(text):
  return text.replace("\\n", "\n").replace("\\t", "\t")

def answer(text, sample=True, top_p=1, temperature=0.7):
  '''sample：是否抽样。生成任务，可以设置为True;
  top_p：0-1之间，生成的内容越多样'''
  text = preprocess(text)
  
  if not sample:
    out_text = pipeline_t2t(text, return_dict_in_generate=True, output_scores=False, max_new_tokens=2048, num_beams=1, length_penalty=0.6)
  else:
    out_text = pipeline_t2t(text, return_dict_in_generate=True, output_scores=False, max_new_tokens=2048, do_sample=True, top_p=top_p, temperature=temperature, no_repeat_ngram_size=3)
  
  return postprocess(out_text["text"])

input_text = '为什么地球是圆的？'
input = "用户：" + input_text + "\n小元："
output_text = answer(input)
print(f"{input}{output_text}")

#Back to Lesson 2, time flies!
import gradio as gr
def generate(input, slider):
    output = answer("用户：" + input + "\n小元：")
    print(output)
    return output

demo = gr.Interface(fn=generate, 
                    inputs=gr.Textbox(label="Prompt"), 
                    outputs=[gr.Textbox(label="Completion")])

gr.close_all()
demo.launch(share=True)

import random
import gradio as gr


def respond(message, chat_history):
        #No LLM here, just respond with a random pre-made message
        bot_message = random.choice(["Tell me more about it",
                                     "Cool, but I'm not interested",
                                     "Hmmmm, ok then"])
        chat_history.append((message, bot_message))
        return "", chat_history


with gr.Blocks() as demo:
	# 聊天框
    chatbot = gr.Chatbot(height=240) #just to fit the notebook
    # 输入框
    msg = gr.Textbox(label="Prompt")
    # 提交按钮
    btn = gr.Button("Submit")
    # 清空内容按钮
    clear = gr.ClearButton(components=[msg, chatbot], value="Clear console")
	
	# 提交按钮的功能函数
    btn.click(respond, inputs=[msg, chatbot], outputs=[msg, chatbot])
    msg.submit(respond, inputs=[msg, chatbot], outputs=[msg, chatbot]) #Press enter to submit

gr.close_all()
demo.launch(share=True)