import gradio as gr
from transformers import pipeline

ner = pipeline('ner')

def merge_tokens(tokens):
    merged_tokens = []
    for token in tokens:
        if merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:]):
            # If current token continues the entity of the last one, merge them
            last_token = merged_tokens[-1]
            last_token['word'] += token['word'].replace('##', '')
            last_token['end'] = token['end']
            last_token['score'] = (last_token['score'] + token['score']) / 2
        else:
            # Otherwise, add the token to the list
            merged_tokens.append(token)

    return merged_tokens

def named(input):
    output = ner(input)
    merged_word = merge_tokens(output)
    return {'text': input, 'entities': merged_word}

a = gr.Interface(fn=named, 
                 inputs=[gr.Textbox(label="Text input", lines= 2)],
                 outputs=[gr.HighlightedText(label='Text with entities')],
                 title='Named Entity Recognition', examples=["My name is Andrew, I'm building DeeplearningAI and I live in California", "My name is Poli, I live in Vienna and work at HuggingFace"])
a.launch()