import gradio as gr


with open('materials/introduction.html', 'r', encoding='utf-8') as file:
    html_description = file.read()

with gr.Blocks() as landing_interface:
    gr.HTML(html_description)
    
    with gr.Accordion("How to run this model locally", open=False):
        gr.Markdown(
            """
            ## Installation
            To use this model, you must install the GLiClass Python library:
            ```
            !pip install gliclass
            ```
         
            ## Usage
            Once you've downloaded the GLiClass library, you can import the GLiClassModel and ZeroShotClassificationPipeline classes.
            """
        )
        gr.Code(
            '''
from gliclass import GLiClassModel, ZeroShotClassificationPipeline
from transformers import AutoTokenizer

model = GLiClassModel.from_pretrained("knowledgator/gliclass-small-v1")
tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-small-v1")

pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')

text = "One day I will see the world!"
labels = ["travel", "dreams", "sport", "science", "politics"]
results = pipeline(text, labels, threshold=0.5)[0] #because we have one text

for result in results:
    print(result["label"], "=>", result["score"])
            ''',
            language="python",
        )