Spaces:
Sleeping
Sleeping
File size: 2,054 Bytes
38f8736 6c05acd 38f8736 351552e 38f8736 6c05acd a56c804 6748684 f77c0a8 7e17d32 6c05acd f77c0a8 be65985 6c05acd f77c0a8 6c05acd f77c0a8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
import os
import spacy
import gradio as gr
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np
import zipfile
# Estrai il file ZIP
zip_path = os.path.join(os.getcwd(), "en_core_web_sm.zip")
extract_dir = os.path.join(os.getcwd(), "en_core_web_sm")
if not os.path.exists(extract_dir):
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
zip_ref.extractall(extract_dir)
# Carica il modello
nlp = spacy.load(extract_dir)
# Carica il modello SentenceTransformer
model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2', device='cpu')
# Preprocessamento manuale (carica il manuale da un file o base di dati)
with open('testo.txt', 'r', encoding='utf-8') as file:
text = file.read()
# Tokenizza il testo in frasi usando SpaCy
doc = nlp(text)
sentences = [sent.text for sent in doc.sents] # Estrarre frasi dal testo
# Crea gli embedding per il manuale
embeddings = model.encode(sentences, batch_size=8, show_progress_bar=True)
# Funzione per ottenere le frasi più rilevanti
def find_relevant_sentences(query):
query_embedding = model.encode([query])
similarities = cosine_similarity(query_embedding, embeddings).flatten()
# Filtra i risultati in base alla similitudine
threshold = 0.5
filtered_results = [(idx, sim) for idx, sim in enumerate(similarities) if sim >= threshold]
# Ordina i risultati per similitudine
filtered_results.sort(key=lambda x: x[1], reverse=True)
# Ottieni le frasi più rilevanti
top_n = 4
relevant_sentences = [sentences[idx] for idx, _ in filtered_results[:top_n]]
return relevant_sentences
# Interfaccia Gradio
iface = gr.Interface(
fn=find_relevant_sentences,
inputs=gr.Textbox(label="Insert your query"),
outputs=gr.Textbox(label="Relevant sentences"),
title="Manual Querying System",
description="Enter a question about the machine, and this tool will find the most relevant sentences from the manual."
)
# Avvia l'app Gradio
iface.launch()
|