# import gradio as gr
# from transformers import AutoTokenizer

# # 第一个功能：基于输入文本和对应的损失值对文本进行着色展示
# def color_text(text_list=["hi", "FreshEval"], loss_list=[0.1,0.7]):
#     """
#     根据损失值为文本着色。
#     """
#     highlighted_text = []
#     for text, loss in zip(text_list, loss_list):
#         # color = "#FF0000" if float(loss) > 0.5 else "#00FF00"
#         color=loss
#         highlighted_text.append({"text": text, "bg_color": color})
#     return gr.HighlightedText(highlighted_text).get_html()

# # 第二个功能：根据 ID 列表和 tokenizer 将 ID 转换为文本，并展示
# def get_text(ids_list=[0.1,0.7], tokenizer=None):
#     """
#     给定一个 ID 列表和 tokenizer 名称，将这些 ID 转换成文本。
#     """
#     return ['Hi', 'Adam']
#     # tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
#     # text = tokenizer.decode(eval(ids_list), skip_special_tokens=True)
#     # 这里只是简单地返回文本，但是可以根据实际需求添加颜色或其他样式
#     # return text


# def get_ids_loss(text, tokenizer, model):
#     """
#     给定一个文本，返回其对应的 IDs 和损失值。
#     """
#     # tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
#     # model = AutoModelForCausalLM.from_pretrained(model_name)
#     # 这里只是简单地返回 IDs 和损失值，但是可以根据实际需求添加颜色或其他样式
#     return [1, 2], [0.1, 0.7]


# def color_pipeline(text=["hi", "FreshEval"],  model=None):
#     """
#     给定一个文本，返回其对应的着色文本。
#     """
#     tokenizer=None
#     ids, loss = get_ids_loss(text, tokenizer, model)
#     text = get_text(ids, tokenizer)
#     return color_text(text, loss)

# # 创建 Gradio 界面
# with gr.Blocks() as demo:
#     with gr.Tab("color your text"):
#         with gr.Row():
#             text_input = gr.Textbox(label="input text", placeholder="input your text here...")
#             # loss_input = gr.Number(label="loss")
#             model_input = gr.Textbox(label="model name", placeholder="input your model name here...")
#             color_text_output = gr.HTML(label="colored text")
#             gr.Markdown("## Text Examples")
#             # gr.Examples(
#             #     [["hi", "Adam"], [0.1,0.7]],
#             #     [text_input, loss_input],
#             #     cache_examples=True,
#             #     fn=color_text,
#             #     outputs=color_text_output
#             # )
#         color_text_button = gr.Button("color the text").click(color_pipeline, inputs=[text_input, model_input], outputs=color_text_output)


#         date_time_input = gr.Textbox(label="the date when the text is generated")#TODO add date time input
#         description_input = gr.Textbox(label="description of the text")
#         submit_button = gr.Button("submit a post or record")
#         #TODO add model and its score

    
#     # with gr.Tab("ID 转文本展示"):
#     #     with gr.Row():
#     #         ids_input = gr.Textbox(label="输入 IDs (如 [101, 102, ...])")
#     #         tokenizer_input = gr.Textbox(label="Tokenizer 名称", value="bert-base-uncased")
#     #         show_text_output = gr.Textbox(label="转换后的文本")
#     #     show_text_button = gr.Button("转换并展示").click(show_text, inputs=[ids_input, tokenizer_input], outputs=show_text_output)
    
#     with gr.Tab("model ppl with time"):
#         '''
#         see the matplotlib example, to see ppl with time, select the models
#         '''

    
#     with gr.Tab("model ppl with time"):
#         '''
#         see the matplotlib example, to see ppl with time, select the models
#         ''' 

        

# demo.launch()



# import gradio as gr
# from transformers import pipeline


# pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")

# def predict(input_img):
#     predictions = pipeline(input_img)
#     return input_img, {p["label"]: p["score"] for p in predictions} 

# gradio_app = gr.Interface(
#     predict,
#     inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
#     outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
#     title="Hot Dog? Or Not?",
# )

# if __name__ == "__main__":
#     gradio_app.launch()



import gradio as gr

def greet(name, intensity):
    return "Hello, " + name + "!" * int(intensity)

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

demo.launch(debug=True)

# lm-eval 
# lm-evaluation-harness