Spaces:
Sleeping
Sleeping
| 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() |