import gradio as gr

from transformers import pipeline
get_completion = pipeline("ner", model="dslim/bert-base-NER")

def merge_tokens(tokens):
    merged_tokens = []
    for token in tokens:
        if (merged_tokens and token['word'].startswith('##')) or (merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:])):
            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
            merged_tokens[-1] = last_token

        else:
            # Otherwise, add the token to the list
            merged_tokens.append(token)

    return merged_tokens

def ner_merged(input):
    output = get_completion(input)
    merged_tokens = merge_tokens(output)
    return {"text": input, "entities": merged_tokens}

demo = gr.Interface(fn=ner_merged,
                    # 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 `dslim/bert-base-NER` model under the hood!",
                    inputs=[gr.Textbox(label="Type or paste text to find Named Entities or even select and submit below examples", lines=2)],
                    outputs=[gr.HighlightedText(label="Text with Named Entities identified")],
                    title="Named Entity Recognition test and demo app by Srinivas.V ",
                    description="Find entities",
                    allow_flagging="never",
                    examples=["My name is Srinivas and I live in Dubai, United Arab Emirates. I love DeepLearningAI",
                    "I am a Data Scientist and I am a citizen of Bharat"])
demo.launch()