import gradio as gr
import sentence_transformers
from sentence_transformers import SentenceTransformer
import torch
from sentence_transformers.util import semantic_search
import pandas as pd

model = SentenceTransformer('gart-labor/eng-distilBERT-se-eclass')


corpus = pd.read_json('corpus.jsonl', lines = True, encoding = 'utf-8')

def predict(name, description):
    text = 'Description: '+ description + '; Name: ' + name 
    query_embedding = model.encode(text, convert_to_tensor=True)

    corpus_embeddings = torch.Tensor(corpus["embeddings"])

    output = sentence_transformers.util.semantic_search(query_embedding, corpus_embeddings, top_k = 5)

    preferedName1 = corpus.iloc[output[0][0].get('corpus_id'),2]
    definition1 = corpus.iloc[output[0][0].get('corpus_id'),1]
    IRDI1 = corpus.iloc[output[0][0].get('corpus_id'),4]
    score1 = output[0][0].get('score')

    preferedName2 = corpus.iloc[output[0][1].get('corpus_id'),2]
    definition2 = corpus.iloc[output[0][1].get('corpus_id'),1]
    IRDI2 = corpus.iloc[output[0][1].get('corpus_id'),4]
    score2 = output[0][1].get('score')

    preferedName3 = corpus.iloc[output[0][2].get('corpus_id'),2]
    definition3 = corpus.iloc[output[0][2].get('corpus_id'),1]
    IRDI3 = corpus.iloc[output[0][2].get('corpus_id'),4]
    score3 = output[0][2].get('score')

    preferedName4 = corpus.iloc[output[0][3].get('corpus_id'),2]
    definition4 = corpus.iloc[output[0][3].get('corpus_id'),1]
    IRDI4 = corpus.iloc[output[0][3].get('corpus_id'),4]
    score4 = output[0][3].get('score')
        
    preferedName5 = corpus.iloc[output[0][4].get('corpus_id'),2]
    definition5 = corpus.iloc[output[0][4].get('corpus_id'),1]
    IRDI5 = corpus.iloc[output[0][4].get('corpus_id'),4]
    score5 = output[0][4].get('score')

    df = [[preferedName1, IRDI1, score1], [preferedName2, IRDI2, score2],[preferedName3, IRDI3, score3],[preferedName4, IRDI4, score4], [preferedName5, IRDI5, score5]]

    return pd.DataFrame(df)

interface = gr.Interface(fn = predict, 
            inputs = [gr.Textbox(label="Name:", placeholder="Name of the Pump Property", lines=1), gr.Textbox(label="Description:", placeholder="Description of the Pump Property", lines=1)], 
            #outputs = [gr.Textbox(label = 'preferedName'),gr.Textbox(label = 'definition'), gr.Textbox(label = 'IDRI'),gr.Textbox(label = 'score')],
            outputs = [gr.Dataframe(row_count = (5, "fixed"), col_count=(3, "fixed"), label="Predictions", headers=['ECLASS preferedName', 'ECLASS IRDI', 'simularity score'])],
            examples = [['Device type', 'describing a set of common specific characteristics in products or goods'], ['Item type','the type of product, an item can be assigned to'], 
                        ['Nominal power','power being consumed by or dissipated within an electric component as a variable'], ['Power consumption', 'power that is typically taken from the auxiliary power supply when the device is operating normally']],
                         #theme = 'huggingface',
            title = 'ECLASS-Property-Search', description = "This is a semantic search algorithm that mapps unknown pump properties to the ECLASS standard.")
    
interface.launch()