Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,159 +1,46 @@
|
|
1 |
|
2 |
-
import os
|
3 |
-
import spacy
|
4 |
import gradio as gr
|
5 |
-
from
|
6 |
-
from
|
7 |
-
import numpy as np
|
8 |
-
import zipfile
|
9 |
-
import re
|
10 |
|
11 |
-
|
|
|
12 |
|
13 |
-
|
14 |
-
|
15 |
-
|
|
|
16 |
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
zip_ref.extractall(extraction_dir)
|
22 |
-
print(f"Modello estratto correttamente nella cartella {extraction_dir}")
|
23 |
|
24 |
-
#
|
25 |
-
|
26 |
-
|
27 |
|
28 |
-
#
|
29 |
-
|
30 |
-
os.makedirs(extract_to) # Crea la directory
|
31 |
-
|
32 |
-
# Estrai il file zip
|
33 |
-
if os.path.exists(zip_path): # Controlla che il file zip esista
|
34 |
-
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
|
35 |
-
zip_ref.extractall(extract_to)
|
36 |
-
print(f"Immagini estratte nella directory: {extract_to}")
|
37 |
-
print("Contenuto della directory images:", os.listdir(extract_to))
|
38 |
-
else:
|
39 |
-
print(f"File {zip_path} non trovato. Assicurati di caricarlo nello Space.")
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
# Percorso della cartella estratta
|
44 |
-
model_path = os.path.join(extraction_dir, "en_core_web_lg-3.8.0") # Assicurati che sia corretto
|
45 |
-
|
46 |
-
# Carica il modello
|
47 |
-
nlp = spacy.load(model_path)
|
48 |
-
|
49 |
-
|
50 |
-
# Carica il modello SentenceTransformer
|
51 |
-
|
52 |
-
model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-mpnet-base-v2', device='cpu')
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
# Preprocessamento manuale (carica il manuale da un file o base di dati)
|
58 |
-
with open('testo.txt', 'r', encoding='utf-8') as file:
|
59 |
-
text = file.read()
|
60 |
-
|
61 |
-
# Tokenizza il testo in frasi usando SpaCy
|
62 |
-
doc = nlp(text)
|
63 |
-
sentences = [sent.text for sent in doc.sents] # Estrarre frasi dal testo
|
64 |
-
|
65 |
-
# Crea gli embedding per il manuale
|
66 |
-
embeddings = model.encode(sentences, batch_size=8, show_progress_bar=True)
|
67 |
-
|
68 |
-
# Percorso della cartella delle immagini
|
69 |
-
image_folder = "images"
|
70 |
-
|
71 |
-
def extract_figure_numbers(text):
|
72 |
-
"""Estrae tutti i numeri delle figure da una frase."""
|
73 |
-
matches = re.findall(r"\(Figure (\d+)\)", text, re.IGNORECASE)
|
74 |
-
if matches:
|
75 |
-
return matches # Restituisce una lista di numeri di figure
|
76 |
-
return []
|
77 |
-
|
78 |
-
|
79 |
-
def generate_figure_mapping(folder):
|
80 |
-
"""Genera la mappatura delle figure dal nome dei file immagini."""
|
81 |
-
mapping = {}
|
82 |
-
for file_name in os.listdir(folder):
|
83 |
-
if file_name.lower().endswith((".jpg", ".png", ".jpeg")):
|
84 |
-
figure_reference = file_name.split(".")[0].replace("_", " ")
|
85 |
-
mapping[figure_reference] = file_name
|
86 |
-
return mapping
|
87 |
-
|
88 |
-
figure_mapping = generate_figure_mapping(image_folder)
|
89 |
-
#print("Generated figure mapping:", figure_mapping)
|
90 |
-
|
91 |
-
def format_sentences(sentences):
|
92 |
-
"""
|
93 |
-
Converte la lista in una stringa, sostituendo i delimitatori '|' con un a capo senza aggiungere spazi extra.
|
94 |
-
Interrompe il processo se trova '.end'.
|
95 |
-
"""
|
96 |
-
# Uniamo la lista in una singola stringa
|
97 |
-
sentences_str = " ".join(sentences)
|
98 |
-
|
99 |
-
# Interrompiamo al primo '.end'
|
100 |
-
if ".end" in sentences_str:
|
101 |
-
sentences_str = sentences_str.split(".end")[0]
|
102 |
|
103 |
-
# Sostituiamo il delimitatore '|' con un a capo
|
104 |
-
formatted_response = sentences_str.replace(" |", "\n").replace("|", "\n")
|
105 |
-
|
106 |
-
return formatted_response
|
107 |
-
|
108 |
-
def find_relevant_sentences(query, threshold=0.2, top_n=6):
|
109 |
-
"""Trova le frasi più rilevanti e le immagini collegate."""
|
110 |
-
global sentences
|
111 |
-
query_embedding = model.encode([query])
|
112 |
-
similarities = cosine_similarity(query_embedding, embeddings).flatten()
|
113 |
-
|
114 |
-
filtered_results = [(idx, sim) for idx, sim in enumerate(similarities) if sim >= threshold]
|
115 |
-
filtered_results.sort(key=lambda x: x[1], reverse=True)
|
116 |
-
|
117 |
-
if not filtered_results:
|
118 |
-
return "**RESPONSE:**\nNo relevant sentences found for your query.", None
|
119 |
-
|
120 |
-
relevant_sentences = [sentences[idx] for idx, _ in filtered_results[:top_n]]
|
121 |
-
relevant_images = set() # Usa un set per evitare duplicati
|
122 |
-
|
123 |
-
for sent in relevant_sentences:
|
124 |
-
figure_numbers = extract_figure_numbers(sent) # Restituisce una lista di figure
|
125 |
-
for figure_number in figure_numbers:
|
126 |
-
if figure_number in figure_mapping:
|
127 |
-
image_path = os.path.join(image_folder, figure_mapping[figure_number])
|
128 |
-
if os.path.exists(image_path):
|
129 |
-
relevant_images.add(image_path) # Aggiunge al set
|
130 |
-
|
131 |
-
# Formatta le frasi senza categorizzazione
|
132 |
-
formatted_response = "****\n" + format_sentences(relevant_sentences)
|
133 |
-
return formatted_response, list(relevant_images) # Converte il set in lista
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
# Interfaccia Gradio
|
138 |
examples = [
|
139 |
-
["
|
140 |
-
["
|
141 |
-
["
|
142 |
-
["How do I DRILL BIT REPLACEMENT ?"],
|
143 |
-
["instructions for changing the knife"],
|
144 |
-
["lubrication for the knife holder cylinder"]
|
145 |
]
|
146 |
|
|
|
147 |
iface = gr.Interface(
|
148 |
-
fn=
|
149 |
-
|
150 |
outputs=[
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
examples=examples,
|
155 |
-
|
156 |
-
description="Enter a question
|
157 |
)
|
158 |
|
|
|
159 |
iface.launch()
|
|
|
1 |
|
|
|
|
|
2 |
import gradio as gr
|
3 |
+
from langchain.vectorstores import FAISS
|
4 |
+
from langchain.embeddings import HuggingFaceEmbeddings
|
|
|
|
|
|
|
5 |
|
6 |
+
# Carica il modello di embedding
|
7 |
+
embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/LaBSE")
|
8 |
|
9 |
+
# Carica i vectorstore FAISS salvati
|
10 |
+
vectorstore = FAISS.load_local("faiss_index", embedding_model, allow_dangerous_deserialization=True)
|
11 |
+
manual_vectorstore = FAISS.load_local("faiss_manual_index", embedding_model, allow_dangerous_deserialization=True)
|
12 |
+
problems_vectorstore = FAISS.load_local("faiss_problems_index", embedding_model, allow_dangerous_deserialization=True)
|
13 |
|
14 |
+
def search_query(query):
|
15 |
+
# Cerca nei manuali
|
16 |
+
manual_results = manual_vectorstore.similarity_search(query, k=2)
|
17 |
+
manual_output = "\n\n".join([doc.page_content for doc in manual_results])
|
|
|
|
|
18 |
|
19 |
+
# Cerca nei problemi
|
20 |
+
problems_results = problems_vectorstore.similarity_search(query, k=2)
|
21 |
+
problems_output = "\n\n".join([doc.page_content for doc in problems_results])
|
22 |
|
23 |
+
# Restituisce i risultati come output diviso
|
24 |
+
return manual_output, problems_output
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
examples = [
|
27 |
+
["How to change the knife?"],
|
28 |
+
["What are the safety precautions for using the machine?"],
|
29 |
+
["How can I get help with the machine?"]
|
|
|
|
|
|
|
30 |
]
|
31 |
|
32 |
+
# Interfaccia Gradio
|
33 |
iface = gr.Interface(
|
34 |
+
fn=search_query,
|
35 |
+
inputs=gr.Textbox(lines=2, placeholder="Enter your question here..."),
|
36 |
outputs=[
|
37 |
+
gr.Textbox(label="Manual Results"),
|
38 |
+
gr.Textbox(label="Issues Results")
|
39 |
+
],
|
40 |
+
examples=examples,
|
41 |
+
title="Manual Querying System",
|
42 |
+
description="Enter a question to get relevant information extracted from the manual and the most common related issues."
|
43 |
)
|
44 |
|
45 |
+
# Avvia l'app
|
46 |
iface.launch()
|