import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

def greet(name):

    tokenizer = AutoTokenizer.from_pretrained("zjunlp/MolGen")
    model = AutoModelForSeq2SeqLM.from_pretrained("zjunlp/MolGen")
    
    sf_input = tokenizer(name, return_tensors="pt")
    
    # beam search
    molecules = model.generate(input_ids=sf_input["input_ids"],
                              attention_mask=sf_input["attention_mask"],
                              max_length=15,
                              min_length=5,
                              num_return_sequences=5,
                              num_beams=5)

    sf_output = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True).replace(" ","") for g in molecules]
    return sf_output


examples = [
            
            '[C][=C][C][=C][C][=C][Ring1][=Branch1]',
'[C][=C][C][=C][C][=C][Ring1][=Branch1]'
'[C][=C][C][=C][C][=C][C][=C][Ring1][=Branch1]'
'[C][=C][C][=C][C][=C][Ring1][=Branch1][C][=C][C][=C]'
'[C][=C][C][=C][C][=C][Ring1][=Branch1][C@H1][C][=C][C]'
'[C][=C][C][=C][C][=C][Ring1][=Branch1][C@H1][=C][C][=C]'
]





iface = gr.Interface(fn=greet, inputs="text", outputs="text",examples=examples )
iface.launch()