Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from sentence_transformers import SentenceTransformer
+from scipy.spatial.distance import cosine
+from sklearn.metrics.pairwise import cosine_similarity
+import nltk
+
+# Carica il modello
+model = SentenceTransformer('sentence-transformers/all-roberta-large-v1', device='cpu')
+nltk.download('punkt')
+
+# Preprocessamento manuale (potresti caricare il manuale da un file o base di dati)
+with open('manual.txt', 'r', encoding='utf-8') as file:
+    text = file.read()
+
+# Tokenizza il testo
+sentences = nltk.sent_tokenize(text)
+
+# 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()