Update app.py

app.py

@@ -65,49 +65,92 @@ 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):
+# Percorso della cartella delle immagini
+image_folder = "./images"
+
+def extract_figure_numbers(text):
+    """Estrae tutti i numeri delle figure da una frase."""
+    matches = re.findall(r"\(Figure (\d+)\)", text, re.IGNORECASE)
+    if matches:
+        return matches  # Restituisce una lista di numeri di figure
+    return []
+
+
+def generate_figure_mapping(folder):
+    """Genera la mappatura delle figure dal nome dei file immagini."""
+    mapping = {}
+    for file_name in os.listdir(folder):
+        if file_name.lower().endswith((".jpg", ".png", ".jpeg")):
+            figure_reference = file_name.split(".")[0].replace("_", " ")
+            mapping[figure_reference] = file_name
+    return mapping
+
+figure_mapping = generate_figure_mapping(image_folder)
+#print("Generated figure mapping:", figure_mapping)
+
+def format_sentences(sentences):
+    """
+    Converte la lista in una stringa, sostituendo i delimitatori '|' con un a capo senza aggiungere spazi extra.
+    Interrompe il processo se trova '.end'.
+    """
+    # Uniamo la lista in una singola stringa
+    sentences_str = " ".join(sentences)
+    
+    # Interrompiamo al primo '.end'
+    if ".end" in sentences_str:
+        sentences_str = sentences_str.split(".end")[0]
+    
+    # Sostituiamo il delimitatore '|' con un a capo
+    formatted_response = sentences_str.replace(" |", "\n").replace("|", "\n")
+    
+    return formatted_response
+    
+def find_relevant_sentences(query, threshold=0.2, top_n=6):
+    """Trova le frasi più rilevanti e le immagini collegate."""
+    global sentences
     query_embedding = model.encode([query])
     similarities = cosine_similarity(query_embedding, embeddings).flatten()
 
-    # Filtra i risultati in base alla similitudine
-    threshold = 0.2
     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 = 5
+    if not filtered_results:
+        return "**RESPONSE:**\nNo relevant sentences found for your query.", None
+
     relevant_sentences = [sentences[idx] for idx, _ in filtered_results[:top_n]]
-        
-    doc = nlp(" ".join(relevant_sentences))
- 
-    grouped_results = [sent.text for sent in doc.sents]
-    # Pulizia
-    cleaned_results = [text.replace("\n", " ") for text in grouped_results]  # Rimuove gli a capo
-    final_output = " ".join(cleaned_results)  # Combina tutte le frasi in un unico testo
+    relevant_images = set()  # Usa un set per evitare duplicati
 
-    
-    return final_output
+    for sent in relevant_sentences:
+        figure_numbers = extract_figure_numbers(sent)  # Restituisce una lista di figure
+        for figure_number in figure_numbers:
+            if figure_number in figure_mapping:
+                image_path = os.path.join(image_folder, figure_mapping[figure_number])
+                if os.path.exists(image_path):
+                    relevant_images.add(image_path)  # Aggiunge al set
 
+    # Formatta le frasi senza categorizzazione
+    formatted_response = "****\n" + format_sentences(relevant_sentences)
+    return formatted_response, list(relevant_images)  # Converte il set in lista
+
+
+
+# Interfaccia Gradio
 examples = [
     ["irresponsible use of the machine?"],
-    ["If I have a problem how can I get help? "],
+    ["If I have a problem how can I get help?"],
     ["precautions when using the cutting machine"],
-    ["How do I change the knife of the cutting machine?"],
-    
+    ["How do I  DRILL BIT REPLACEMENT ?"],
+    ["instructions for changing the knife"],
+    ["lubrication for the knife holder cylinder"]
 ]
 
-# Interfaccia Gradio
 iface = gr.Interface(
-    fn=find_relevant_sentences, 
-    inputs=gr.Textbox(label="Insert your query"), 
-    outputs=gr.Textbox(label="Relevant sentences"),
-    examples=examples, 
+    fn=find_relevant_sentences,
+    inputs=gr.Textbox(label="Insert your query"),
+    outputs=[gr.Textbox(label="Relevant sentences"), gr.Gallery(label="Relevant figures")],
+    examples=examples,
     title="Manual Querying System",
-    description="Enter a question about the machine, and this tool will find the most relevant sentences from the manual."
+    description="Enter a question about the machine, and this tool will find the most relevant sentences and associated figures from the manual.",
 )
 
-# Avvia l'app Gradio
 iface.launch()