from transformers import pipeline
import gradio as gr

get_completion = pipeline("ner", model="dslim/bert-base-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 the two tokens
            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 ner(input):
    output = get_completion(input)
    merged_tokens = merge_tokens(output)
    return {"text": input, "entities": merged_tokens}

gr.close_all()
demo = gr.Interface(fn=ner,
                    inputs=[gr.Textbox(label="Text to find entities", lines=2)],
                    outputs=[gr.HighlightedText(label="Text with entities")],
                    title="NER with dslim/bert-base-NER",
                    description="Find entities using the `BERT-base` model under the hood!",
                    allow_flagging="never",
                    examples=["My name is Raul and I live in Niterói, Rio de Janeiro, Brazil",
                             "Lionel Messi is the greatest footballer of the new century",
                             "Toronto is hockey capital of the world",
                             "S&P 500 has gained 400 points in last trailing 7 days",
                             "Paris is one of most visited cities in the world every year."])
demo.launch()