Upload 2 files
Browse files- UI.py +42 -65
- interface.py +87 -135
UI.py
CHANGED
@@ -1,21 +1,17 @@
|
|
1 |
# UI.py
|
2 |
import gradio as gr
|
3 |
-
import numpy as np # Necesario para np.inf
|
4 |
|
5 |
def create_interface(process_function_for_button):
|
6 |
"""
|
7 |
Crea la interfaz de usuario completa para el modelado de bioprocesos.
|
8 |
-
Conecta el botón de submit a la 'process_function_for_button' proporcionada.
|
9 |
"""
|
10 |
-
|
11 |
-
# Usar un tema estándar de Gradio para mayor compatibilidad.
|
12 |
-
# theme='gradio/soft' es una buena opción. Puedes cambiarlo si tienes un tema personalizado que funcione.
|
13 |
-
with gr.Blocks(theme='gradio/soft') as demo:
|
14 |
gr.Markdown("# Modelado de Bioprocesos con Ecuaciones Personalizadas y Análisis por IA")
|
15 |
gr.Markdown(
|
16 |
-
"Sube un archivo Excel
|
17 |
-
"Ingresa
|
18 |
-
"
|
19 |
)
|
20 |
|
21 |
with gr.Row():
|
@@ -28,113 +24,99 @@ def create_interface(process_function_for_button):
|
|
28 |
legend_position_ui = gr.Dropdown(
|
29 |
label="Posición de la leyenda",
|
30 |
choices=['best', 'upper right', 'upper left', 'lower right', 'lower left', 'center left', 'center right', 'lower center', 'upper center', 'center'],
|
31 |
-
value='best',
|
32 |
type="value"
|
33 |
)
|
34 |
with gr.Column(scale=1):
|
35 |
gr.Markdown("### 2. Conteo de Ecuaciones a Probar")
|
36 |
-
gr.Markdown("Define cuántas ecuaciones diferentes
|
37 |
-
# Usar floats para gr.Number, Gradio los maneja bien incluso con precision=0
|
38 |
biomass_eq_count_ui = gr.Number(label="Ecuaciones de Biomasa:", value=1.0, minimum=1.0, maximum=3.0, step=1.0, precision=0)
|
39 |
substrate_eq_count_ui = gr.Number(label="Ecuaciones de Sustrato:", value=1.0, minimum=1.0, maximum=3.0, step=1.0, precision=0)
|
40 |
product_eq_count_ui = gr.Number(label="Ecuaciones de Producto:", value=1.0, minimum=1.0, maximum=3.0, step=1.0, precision=0)
|
41 |
|
42 |
-
# ---
|
|
|
43 |
with gr.Accordion("3. Definición de Modelos de Biomasa", open=True):
|
44 |
-
gr.Markdown("
|
45 |
with gr.Row():
|
46 |
-
with gr.Column():
|
47 |
-
biomass_eq1_ui = gr.Textbox(label="Ecuación
|
48 |
biomass_param1_ui = gr.Textbox(label="Parámetros Biomasa 1", value="Xm, um, t_lag")
|
49 |
biomass_bound1_ui = gr.Textbox(label="Límites Biomasa 1", value="(0, np.inf), (0, np.inf), (0, np.inf)")
|
50 |
|
51 |
-
# Columna 2 para Biomasa
|
52 |
biomass_col2_container = gr.Column(visible=False)
|
53 |
with biomass_col2_container:
|
54 |
-
biomass_eq2_ui = gr.Textbox(label="Ecuación
|
55 |
-
biomass_param2_ui = gr.Textbox(label="Parámetros Biomasa 2", value="X0, um")
|
56 |
-
biomass_bound2_ui = gr.Textbox(label="Límites Biomasa 2", value="(0, np.inf), (0, np.inf)")
|
57 |
|
58 |
-
# Columna 3 para Biomasa
|
59 |
biomass_col3_container = gr.Column(visible=False)
|
60 |
with biomass_col3_container:
|
61 |
-
biomass_eq3_ui = gr.Textbox(label="Ecuación
|
62 |
-
biomass_param3_ui = gr.Textbox(label="Parámetros Biomasa 3", value="", placeholder="
|
63 |
-
biomass_bound3_ui = gr.Textbox(label="Límites Biomasa 3", value="", placeholder="
|
64 |
|
65 |
-
#
|
66 |
with gr.Accordion("4. Definición de Modelos de Sustrato", open=True):
|
67 |
-
gr.Markdown("
|
68 |
with gr.Row():
|
69 |
with gr.Column():
|
70 |
-
substrate_eq1_ui = gr.Textbox(label="Ecuación
|
71 |
substrate_param1_ui = gr.Textbox(label="Parámetros Sustrato 1", value="S0, YXS, mS")
|
72 |
-
substrate_bound1_ui = gr.Textbox(label="Límites Sustrato 1", value="(0, np.inf), (1e-9, np.inf), (0, np.inf)")
|
73 |
|
74 |
substrate_col2_container = gr.Column(visible=False)
|
75 |
with substrate_col2_container:
|
76 |
-
substrate_eq2_ui = gr.Textbox(label="Ecuación
|
77 |
-
substrate_param2_ui = gr.Textbox(label="Parámetros Sustrato 2", value="")
|
78 |
-
substrate_bound2_ui = gr.Textbox(label="Límites Sustrato 2", value="")
|
79 |
|
80 |
substrate_col3_container = gr.Column(visible=False)
|
81 |
with substrate_col3_container:
|
82 |
-
substrate_eq3_ui = gr.Textbox(label="Ecuación
|
83 |
-
substrate_param3_ui = gr.Textbox(label="Parámetros Sustrato 3", value="")
|
84 |
-
substrate_bound3_ui = gr.Textbox(label="Límites Sustrato 3", value="")
|
85 |
|
86 |
-
#
|
87 |
with gr.Accordion("5. Definición de Modelos de Producto", open=True):
|
88 |
-
gr.Markdown("
|
89 |
with gr.Row():
|
90 |
with gr.Column():
|
91 |
-
product_eq1_ui = gr.Textbox(label="Ecuación
|
92 |
product_param1_ui = gr.Textbox(label="Parámetros Producto 1", value="P0, YPX, mP")
|
93 |
product_bound1_ui = gr.Textbox(label="Límites Producto 1", value="(0, np.inf), (0, np.inf), (0, np.inf)")
|
94 |
|
95 |
product_col2_container = gr.Column(visible=False)
|
96 |
with product_col2_container:
|
97 |
-
product_eq2_ui = gr.Textbox(label="Ecuación
|
98 |
-
product_param2_ui = gr.Textbox(label="Parámetros Producto 2", value="")
|
99 |
-
product_bound2_ui = gr.Textbox(label="Límites Producto 2", value="")
|
100 |
|
101 |
product_col3_container = gr.Column(visible=False)
|
102 |
with product_col3_container:
|
103 |
-
product_eq3_ui = gr.Textbox(label="Ecuación
|
104 |
-
product_param3_ui = gr.Textbox(label="Parámetros Producto 3", value="")
|
105 |
-
product_bound3_ui = gr.Textbox(label="Límites Producto 3", value="")
|
106 |
|
107 |
-
# Lógica para mostrar/ocultar campos de ecuación dinámicamente
|
108 |
def update_eq_visibility(count_value):
|
109 |
try:
|
110 |
-
|
111 |
-
if count_value is None:
|
112 |
-
count = 0 # O 1, dependiendo de cómo quieras manejarlo. 0 ocultará todo.
|
113 |
-
else:
|
114 |
-
count = int(float(count_value)) # Convertir a float primero, luego a int
|
115 |
except ValueError:
|
116 |
-
count = 0
|
117 |
-
|
118 |
-
# gr.update es la forma canónica de actualizar propiedades
|
119 |
return gr.update(visible=count >= 2), gr.update(visible=count >= 3)
|
120 |
|
121 |
-
# Conectar eventos .change() de los contadores a la función de visibilidad
|
122 |
biomass_eq_count_ui.change(fn=update_eq_visibility, inputs=biomass_eq_count_ui, outputs=[biomass_col2_container, biomass_col3_container])
|
123 |
substrate_eq_count_ui.change(fn=update_eq_visibility, inputs=substrate_eq_count_ui, outputs=[substrate_col2_container, substrate_col3_container])
|
124 |
product_eq_count_ui.change(fn=update_eq_visibility, inputs=product_eq_count_ui, outputs=[product_col2_container, product_col3_container])
|
125 |
|
126 |
-
# Botón de envío
|
127 |
submit_button = gr.Button("Procesar y Analizar Modelos", variant="primary", scale=1, elem_id="submit_button_main")
|
128 |
|
129 |
-
# Salidas
|
130 |
gr.Markdown("## Resultados del Análisis y Modelado")
|
131 |
with gr.Row():
|
132 |
-
|
133 |
-
image_output = gr.Image(label="Gráfico Generado de Ajustes", type="pil", scale=2, show_download_button=True, height=750)
|
134 |
with gr.Column(scale=3):
|
135 |
analysis_output = gr.Markdown(label="Análisis del Modelo por IA")
|
136 |
|
137 |
-
# Lista de todos los inputs para el botón de submit
|
138 |
all_inputs_for_button = [
|
139 |
file_input,
|
140 |
biomass_eq1_ui, biomass_eq2_ui, biomass_eq3_ui,
|
@@ -155,18 +137,14 @@ def create_interface(process_function_for_button):
|
|
155 |
]
|
156 |
outputs_for_button = [image_output, analysis_output]
|
157 |
|
158 |
-
# Conexión del botón DENTRO del contexto de Blocks
|
159 |
submit_button.click(
|
160 |
-
fn=process_function_for_button,
|
161 |
inputs=all_inputs_for_button,
|
162 |
outputs=outputs_for_button,
|
163 |
-
# api_name="process_data" #
|
164 |
)
|
165 |
|
166 |
-
# Inicializar visibilidad usando demo.load para que se aplique al cargar la UI
|
167 |
def set_initial_visibility_on_load_wrapper(b_c_val, s_c_val, p_c_val):
|
168 |
-
# Obtener los valores iniciales de los gr.Number components y aplicar la lógica de visibilidad.
|
169 |
-
# Los valores de los Number inputs pueden ser float, convertirlos a int.
|
170 |
b_c_int = int(float(b_c_val)) if b_c_val is not None else 0
|
171 |
s_c_int = int(float(s_c_val)) if s_c_val is not None else 0
|
172 |
p_c_int = int(float(p_c_val)) if p_c_val is not None else 0
|
@@ -175,7 +153,6 @@ def create_interface(process_function_for_button):
|
|
175 |
s_vis2_upd, s_vis3_upd = update_eq_visibility(s_c_int)
|
176 |
p_vis2_upd, p_vis3_upd = update_eq_visibility(p_c_int)
|
177 |
|
178 |
-
# Devolver los resultados de gr.update para cada componente de salida del demo.load
|
179 |
return b_vis2_upd, b_vis3_upd, s_vis2_upd, s_vis3_upd, p_vis2_upd, p_vis3_upd
|
180 |
|
181 |
demo.load(
|
|
|
1 |
# UI.py
|
2 |
import gradio as gr
|
3 |
+
import numpy as np # Necesario para np.inf
|
4 |
|
5 |
def create_interface(process_function_for_button):
|
6 |
"""
|
7 |
Crea la interfaz de usuario completa para el modelado de bioprocesos.
|
|
|
8 |
"""
|
9 |
+
with gr.Blocks(theme='gradio/soft') as demo:
|
|
|
|
|
|
|
10 |
gr.Markdown("# Modelado de Bioprocesos con Ecuaciones Personalizadas y Análisis por IA")
|
11 |
gr.Markdown(
|
12 |
+
"Sube un archivo Excel (columnas: 'Tiempo', 'Biomasa', 'Sustrato', 'Producto'). "
|
13 |
+
"Ingresa ecuaciones (usa 't' para tiempo; 'X_val' para X(t) en S/P), "
|
14 |
+
"parámetros y límites. El sistema ajustará los modelos y un LLM analizará los resultados."
|
15 |
)
|
16 |
|
17 |
with gr.Row():
|
|
|
24 |
legend_position_ui = gr.Dropdown(
|
25 |
label="Posición de la leyenda",
|
26 |
choices=['best', 'upper right', 'upper left', 'lower right', 'lower left', 'center left', 'center right', 'lower center', 'upper center', 'center'],
|
27 |
+
value='best',
|
28 |
type="value"
|
29 |
)
|
30 |
with gr.Column(scale=1):
|
31 |
gr.Markdown("### 2. Conteo de Ecuaciones a Probar")
|
32 |
+
gr.Markdown("Define cuántas ecuaciones diferentes probar para cada componente (1-3).")
|
|
|
33 |
biomass_eq_count_ui = gr.Number(label="Ecuaciones de Biomasa:", value=1.0, minimum=1.0, maximum=3.0, step=1.0, precision=0)
|
34 |
substrate_eq_count_ui = gr.Number(label="Ecuaciones de Sustrato:", value=1.0, minimum=1.0, maximum=3.0, step=1.0, precision=0)
|
35 |
product_eq_count_ui = gr.Number(label="Ecuaciones de Producto:", value=1.0, minimum=1.0, maximum=3.0, step=1.0, precision=0)
|
36 |
|
37 |
+
# --- Contenedores para campos dinámicos ---
|
38 |
+
# Biomasa
|
39 |
with gr.Accordion("3. Definición de Modelos de Biomasa", open=True):
|
40 |
+
gr.Markdown("Ecuación (ej: `Xm*(1 - exp(-um*(t - t_lag)))`), Parámetros (ej: `Xm, um, t_lag`), Límites (ej: `(0, np.inf), (0, 5), (0, 100)`).")
|
41 |
with gr.Row():
|
42 |
+
with gr.Column():
|
43 |
+
biomass_eq1_ui = gr.Textbox(label="Ecuación Biomasa 1", value="Xm * (1 - exp(-um * (t - t_lag)))", lines=2)
|
44 |
biomass_param1_ui = gr.Textbox(label="Parámetros Biomasa 1", value="Xm, um, t_lag")
|
45 |
biomass_bound1_ui = gr.Textbox(label="Límites Biomasa 1", value="(0, np.inf), (0, np.inf), (0, np.inf)")
|
46 |
|
|
|
47 |
biomass_col2_container = gr.Column(visible=False)
|
48 |
with biomass_col2_container:
|
49 |
+
biomass_eq2_ui = gr.Textbox(label="Ecuación Biomasa 2", value="", lines=2, placeholder="Opcional: X0 * exp(um * t)")
|
50 |
+
biomass_param2_ui = gr.Textbox(label="Parámetros Biomasa 2", value="", placeholder="Opcional: X0, um")
|
51 |
+
biomass_bound2_ui = gr.Textbox(label="Límites Biomasa 2", value="", placeholder="Opcional: (0, np.inf), (0, np.inf)")
|
52 |
|
|
|
53 |
biomass_col3_container = gr.Column(visible=False)
|
54 |
with biomass_col3_container:
|
55 |
+
biomass_eq3_ui = gr.Textbox(label="Ecuación Biomasa 3", lines=2, value="", placeholder="Opcional")
|
56 |
+
biomass_param3_ui = gr.Textbox(label="Parámetros Biomasa 3", value="", placeholder="Opcional")
|
57 |
+
biomass_bound3_ui = gr.Textbox(label="Límites Biomasa 3", value="", placeholder="Opcional")
|
58 |
|
59 |
+
# Sustrato
|
60 |
with gr.Accordion("4. Definición de Modelos de Sustrato", open=True):
|
61 |
+
gr.Markdown("Usa `X_val` para X(t) si es necesario. Ej: `S0 - (X_val / YXS)`.")
|
62 |
with gr.Row():
|
63 |
with gr.Column():
|
64 |
+
substrate_eq1_ui = gr.Textbox(label="Ecuación Sustrato 1", value="S0 - (X_val / YXS) - mS * t", lines=2)
|
65 |
substrate_param1_ui = gr.Textbox(label="Parámetros Sustrato 1", value="S0, YXS, mS")
|
66 |
+
substrate_bound1_ui = gr.Textbox(label="Límites Sustrato 1", value="(0, np.inf), (1e-9, np.inf), (0, np.inf)")
|
67 |
|
68 |
substrate_col2_container = gr.Column(visible=False)
|
69 |
with substrate_col2_container:
|
70 |
+
substrate_eq2_ui = gr.Textbox(label="Ecuación Sustrato 2", lines=2, value="", placeholder="Opcional")
|
71 |
+
substrate_param2_ui = gr.Textbox(label="Parámetros Sustrato 2", value="", placeholder="Opcional")
|
72 |
+
substrate_bound2_ui = gr.Textbox(label="Límites Sustrato 2", value="", placeholder="Opcional")
|
73 |
|
74 |
substrate_col3_container = gr.Column(visible=False)
|
75 |
with substrate_col3_container:
|
76 |
+
substrate_eq3_ui = gr.Textbox(label="Ecuación Sustrato 3", lines=2, value="", placeholder="Opcional")
|
77 |
+
substrate_param3_ui = gr.Textbox(label="Parámetros Sustrato 3", value="", placeholder="Opcional")
|
78 |
+
substrate_bound3_ui = gr.Textbox(label="Límites Sustrato 3", value="", placeholder="Opcional")
|
79 |
|
80 |
+
# Producto
|
81 |
with gr.Accordion("5. Definición de Modelos de Producto", open=True):
|
82 |
+
gr.Markdown("Usa `X_val` para X(t) si es necesario. Ej: `P0 + YPX * X_val`.")
|
83 |
with gr.Row():
|
84 |
with gr.Column():
|
85 |
+
product_eq1_ui = gr.Textbox(label="Ecuación Producto 1", value="P0 + YPX * X_val + mP * t", lines=2)
|
86 |
product_param1_ui = gr.Textbox(label="Parámetros Producto 1", value="P0, YPX, mP")
|
87 |
product_bound1_ui = gr.Textbox(label="Límites Producto 1", value="(0, np.inf), (0, np.inf), (0, np.inf)")
|
88 |
|
89 |
product_col2_container = gr.Column(visible=False)
|
90 |
with product_col2_container:
|
91 |
+
product_eq2_ui = gr.Textbox(label="Ecuación Producto 2", lines=2, value="", placeholder="Opcional")
|
92 |
+
product_param2_ui = gr.Textbox(label="Parámetros Producto 2", value="", placeholder="Opcional")
|
93 |
+
product_bound2_ui = gr.Textbox(label="Límites Producto 2", value="", placeholder="Opcional")
|
94 |
|
95 |
product_col3_container = gr.Column(visible=False)
|
96 |
with product_col3_container:
|
97 |
+
product_eq3_ui = gr.Textbox(label="Ecuación Producto 3", lines=2, value="", placeholder="Opcional")
|
98 |
+
product_param3_ui = gr.Textbox(label="Parámetros Producto 3", value="", placeholder="Opcional")
|
99 |
+
product_bound3_ui = gr.Textbox(label="Límites Producto 3", value="", placeholder="Opcional")
|
100 |
|
|
|
101 |
def update_eq_visibility(count_value):
|
102 |
try:
|
103 |
+
count = int(float(count_value)) if count_value is not None else 0
|
|
|
|
|
|
|
|
|
104 |
except ValueError:
|
105 |
+
count = 0
|
|
|
|
|
106 |
return gr.update(visible=count >= 2), gr.update(visible=count >= 3)
|
107 |
|
|
|
108 |
biomass_eq_count_ui.change(fn=update_eq_visibility, inputs=biomass_eq_count_ui, outputs=[biomass_col2_container, biomass_col3_container])
|
109 |
substrate_eq_count_ui.change(fn=update_eq_visibility, inputs=substrate_eq_count_ui, outputs=[substrate_col2_container, substrate_col3_container])
|
110 |
product_eq_count_ui.change(fn=update_eq_visibility, inputs=product_eq_count_ui, outputs=[product_col2_container, product_col3_container])
|
111 |
|
|
|
112 |
submit_button = gr.Button("Procesar y Analizar Modelos", variant="primary", scale=1, elem_id="submit_button_main")
|
113 |
|
|
|
114 |
gr.Markdown("## Resultados del Análisis y Modelado")
|
115 |
with gr.Row():
|
116 |
+
image_output = gr.Image(label="Gráfico Generado de Ajustes", type="pil", scale=2, show_download_button=True, height=750, interactive=False)
|
|
|
117 |
with gr.Column(scale=3):
|
118 |
analysis_output = gr.Markdown(label="Análisis del Modelo por IA")
|
119 |
|
|
|
120 |
all_inputs_for_button = [
|
121 |
file_input,
|
122 |
biomass_eq1_ui, biomass_eq2_ui, biomass_eq3_ui,
|
|
|
137 |
]
|
138 |
outputs_for_button = [image_output, analysis_output]
|
139 |
|
|
|
140 |
submit_button.click(
|
141 |
+
fn=process_function_for_button,
|
142 |
inputs=all_inputs_for_button,
|
143 |
outputs=outputs_for_button,
|
144 |
+
# api_name="process_data" # Descomentar si necesitas un nombre de API específico
|
145 |
)
|
146 |
|
|
|
147 |
def set_initial_visibility_on_load_wrapper(b_c_val, s_c_val, p_c_val):
|
|
|
|
|
148 |
b_c_int = int(float(b_c_val)) if b_c_val is not None else 0
|
149 |
s_c_int = int(float(s_c_val)) if s_c_val is not None else 0
|
150 |
p_c_int = int(float(p_c_val)) if p_c_val is not None else 0
|
|
|
153 |
s_vis2_upd, s_vis3_upd = update_eq_visibility(s_c_int)
|
154 |
p_vis2_upd, p_vis3_upd = update_eq_visibility(p_c_int)
|
155 |
|
|
|
156 |
return b_vis2_upd, b_vis3_upd, s_vis2_upd, s_vis3_upd, p_vis2_upd, p_vis3_upd
|
157 |
|
158 |
demo.load(
|
interface.py
CHANGED
@@ -2,72 +2,78 @@
|
|
2 |
import numpy as np
|
3 |
import pandas as pd
|
4 |
import matplotlib
|
5 |
-
matplotlib.use('Agg')
|
6 |
import matplotlib.pyplot as plt
|
7 |
from PIL import Image
|
8 |
import io
|
9 |
import json
|
10 |
-
import traceback
|
11 |
|
12 |
-
|
13 |
-
|
|
|
14 |
|
15 |
-
# Variables globales
|
16 |
USE_MODAL_FOR_LLM_ANALYSIS = False
|
17 |
generate_analysis_from_modal = None
|
18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
def parse_bounds_str(bounds_str_input, num_params):
|
20 |
bounds_str = str(bounds_str_input).strip()
|
21 |
if not bounds_str:
|
22 |
print(f"Cadena de límites vacía para {num_params} params. Usando (-inf, inf).")
|
23 |
return [-np.inf] * num_params, [np.inf] * num_params
|
24 |
-
|
25 |
try:
|
26 |
bounds_str = bounds_str.lower().replace('inf', 'np.inf').replace('none', 'None')
|
27 |
-
if not (bounds_str.startswith('[') and bounds_str.endswith(']')):
|
28 |
bounds_str = f"[{bounds_str}]"
|
29 |
-
|
30 |
-
parsed_bounds_list = eval(bounds_str, {'np': np, 'inf': np.inf, 'None': None}) # Evaluar con np
|
31 |
|
32 |
if not isinstance(parsed_bounds_list, list):
|
33 |
-
raise ValueError("
|
34 |
-
|
35 |
if len(parsed_bounds_list) != num_params:
|
36 |
-
raise ValueError(f"
|
37 |
|
38 |
-
lower_bounds = []
|
39 |
-
upper_bounds = []
|
40 |
for item in parsed_bounds_list:
|
41 |
if not (isinstance(item, (tuple, list)) and len(item) == 2):
|
42 |
-
raise ValueError(f"
|
43 |
-
|
44 |
-
# Convertir a float y manejar None/np.nan
|
45 |
low = -np.inf if (item[0] is None or (isinstance(item[0], float) and np.isnan(item[0]))) else float(item[0])
|
46 |
high = np.inf if (item[1] is None or (isinstance(item[1], float) and np.isnan(item[1]))) else float(item[1])
|
47 |
-
|
48 |
-
lower_bounds.append(low)
|
49 |
-
upper_bounds.append(high)
|
50 |
-
|
51 |
return lower_bounds, upper_bounds
|
52 |
except Exception as e:
|
53 |
-
print(f"Error al parsear
|
54 |
return [-np.inf] * num_params, [np.inf] * num_params
|
55 |
|
56 |
-
|
57 |
def call_llm_analysis_service(prompt: str) -> str:
|
|
|
|
|
58 |
if USE_MODAL_FOR_LLM_ANALYSIS and generate_analysis_from_modal:
|
59 |
print("interface.py: Usando la función de análisis LLM de Modal...")
|
60 |
try:
|
61 |
return generate_analysis_from_modal(prompt)
|
62 |
except Exception as e_modal_call:
|
63 |
print(f"Error llamando a la función Modal LLM: {e_modal_call}")
|
64 |
-
traceback.print_exc()
|
65 |
return f"Error al contactar el servicio de análisis IA (Modal): {e_modal_call}"
|
66 |
else:
|
67 |
print("interface.py: Usando la función de análisis LLM local (fallback)...")
|
|
|
68 |
try:
|
69 |
-
from config import MODEL_PATH, MAX_LENGTH, DEVICE
|
70 |
-
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
71 |
|
72 |
print(f"Fallback: Cargando modelo {MODEL_PATH} localmente en {DEVICE}...")
|
73 |
tokenizer_local = AutoTokenizer.from_pretrained(MODEL_PATH)
|
@@ -80,8 +86,7 @@ def call_llm_analysis_service(prompt: str) -> str:
|
|
80 |
inputs = tokenizer_local(prompt, return_tensors="pt", truncation=True, max_length=max_prompt_len).to(DEVICE)
|
81 |
with torch.no_grad():
|
82 |
outputs = model_local.generate(
|
83 |
-
**inputs,
|
84 |
-
max_new_tokens=MAX_LENGTH,
|
85 |
eos_token_id=tokenizer_local.eos_token_id,
|
86 |
pad_token_id=tokenizer_local.pad_token_id if tokenizer_local.pad_token_id else tokenizer_local.eos_token_id,
|
87 |
do_sample=True, temperature=0.6, top_p=0.9
|
@@ -113,31 +118,37 @@ def process_and_plot(
|
|
113 |
substrate_eq_count_ui,
|
114 |
product_eq_count_ui
|
115 |
):
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
|
|
120 |
if file_obj is None:
|
121 |
-
return
|
122 |
|
123 |
try:
|
124 |
df = pd.read_excel(file_obj.name)
|
125 |
except Exception as e:
|
126 |
-
return
|
127 |
|
128 |
expected_cols = ['Tiempo', 'Biomasa', 'Sustrato', 'Producto']
|
129 |
for col in expected_cols:
|
130 |
if col not in df.columns:
|
131 |
-
return
|
132 |
|
133 |
time_data = df['Tiempo'].values
|
134 |
biomass_data_exp = df['Biomasa'].values
|
135 |
substrate_data_exp = df['Sustrato'].values
|
136 |
product_data_exp = df['Producto'].values
|
137 |
|
138 |
-
|
139 |
-
|
140 |
-
|
|
|
|
|
|
|
|
|
|
|
141 |
|
142 |
all_eq_inputs = {
|
143 |
'biomass': (
|
@@ -167,135 +178,76 @@ def process_and_plot(
|
|
167 |
biomass_params_for_s_p = None
|
168 |
|
169 |
for model_type, (eq_list, param_str_list, bound_str_list, exp_data) in all_eq_inputs.items():
|
170 |
-
if not np.
|
171 |
-
print(f"Datos experimentales para {model_type}
|
172 |
continue
|
173 |
|
174 |
for i in range(len(eq_list)):
|
175 |
-
eq_str = eq_list[i]
|
176 |
-
param_s
|
177 |
-
bound_s = bound_str_list[i]
|
178 |
-
|
179 |
-
if not eq_str or not param_s:
|
180 |
-
print(f"Ecuación o parámetros vacíos para {model_type} #{i+1}, saltando.")
|
181 |
-
continue
|
182 |
|
183 |
-
print(f"Procesando {model_type} #{i+1}: Eq='{eq_str}', Params='{param_s}'")
|
184 |
-
|
185 |
try:
|
186 |
model_handler.set_model(model_type, eq_str, param_s)
|
187 |
num_p = len(model_handler.models[model_type]['params'])
|
188 |
l_b, u_b = parse_bounds_str(bound_s, num_p)
|
|
|
189 |
|
190 |
-
|
191 |
-
|
192 |
-
y_pred, popt = model_handler.fit_model(model_type, time_data, exp_data, bounds=(l_b, u_b), biomass_params_fitted=current_biomass_params)
|
193 |
|
194 |
-
current_params = model_handler.params
|
195 |
r2_val = model_handler.r2.get(model_type, float('nan'))
|
196 |
rmse_val = model_handler.rmse.get(model_type, float('nan'))
|
197 |
|
198 |
-
fitted_results_for_plot[model_type].append({
|
199 |
-
|
200 |
-
'y_pred': y_pred,
|
201 |
-
'params': current_params,
|
202 |
-
'R2': r2_val
|
203 |
-
})
|
204 |
-
results_for_llm_prompt[model_type].append({
|
205 |
-
'equation': eq_str,
|
206 |
-
'params_fitted': current_params,
|
207 |
-
'R2': r2_val,
|
208 |
-
'RMSE': rmse_val
|
209 |
-
})
|
210 |
|
211 |
-
if model_type == 'biomass' and biomass_params_for_s_p is None:
|
212 |
biomass_params_for_s_p = current_params
|
213 |
-
|
214 |
-
|
215 |
-
|
216 |
-
error_msg = f"Error ajustando {model_type} #{i+1} ('{eq_str}'): {e}\n{traceback.format_exc()}"
|
217 |
-
print(error_msg)
|
218 |
-
return default_image, error_msg
|
219 |
|
220 |
# Generar gráfico
|
221 |
fig, axs = plt.subplots(3, 1, figsize=(10, 18), sharex=True)
|
222 |
-
|
223 |
-
axs[0]: (biomass_data_exp, 'Biomasa', fitted_results_for_plot['
|
224 |
axs[1]: (substrate_data_exp, 'Sustrato', fitted_results_for_plot['sustrato']),
|
225 |
axs[2]: (product_data_exp, 'Producto', fitted_results_for_plot['producto'])
|
226 |
}
|
227 |
|
228 |
-
for ax, data_actual, ylabel,
|
229 |
-
if np.
|
230 |
ax.plot(time_data, data_actual, 'o', label=f'Datos {ylabel}', markersize=5, alpha=0.7)
|
231 |
else:
|
232 |
-
ax.text(0.5, 0.5, f"No hay datos para {ylabel}", transform=ax.transAxes, ha='center', va='center'
|
233 |
|
234 |
-
for idx, res_detail in enumerate(
|
235 |
-
label = f'Modelo {idx+1} (R²:{res_detail
|
236 |
ax.plot(time_data, res_detail['y_pred'], '-', label=label, linewidth=2)
|
237 |
-
ax.set_xlabel('Tiempo')
|
238 |
-
ax.
|
239 |
-
ax.grid(True, linestyle=':', alpha=0.7)
|
240 |
-
if show_legend_ui:
|
241 |
-
ax.legend(loc=legend_position_ui, fontsize='small')
|
242 |
|
243 |
-
if show_params_ui and
|
244 |
-
param_display_texts = []
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
-
|
254 |
-
|
255 |
-
v_align = 'bottom'
|
256 |
-
|
257 |
-
ax.text(text_x_pos, text_y_pos, full_param_text, transform=ax.transAxes, fontsize=7,
|
258 |
-
verticalalignment=v_align, bbox=dict(boxstyle='round,pad=0.3', fc='lightyellow', alpha=0.8))
|
259 |
-
|
260 |
-
plt.tight_layout(rect=[0, 0, 1, 0.96])
|
261 |
-
fig.suptitle("Resultados del Ajuste de Modelos Cinéticos", fontsize=16)
|
262 |
-
|
263 |
-
buf = io.BytesIO()
|
264 |
-
plt.savefig(buf, format='png', dpi=150)
|
265 |
-
buf.seek(0)
|
266 |
-
image = Image.open(buf)
|
267 |
-
plt.close(fig)
|
268 |
-
|
269 |
-
# Construir prompt para LLM y llamar al servicio
|
270 |
-
prompt_intro = "Eres un experto en modelado cinético de bioprocesos. Analiza los siguientes resultados del ajuste de modelos a datos experimentales:\n\n"
|
271 |
prompt_details = json.dumps(results_for_llm_prompt, indent=2, ensure_ascii=False)
|
272 |
-
prompt_instructions = "
|
273 |
-
1. **Resumen General:** Una breve descripción del experimento y qué se intentó modelar.
|
274 |
-
2. **Análisis por Componente (Biomasa, Sustrato, Producto):**
|
275 |
-
a. Para cada ecuación probada:
|
276 |
-
i. Calidad del Ajuste: Evalúa el R² (cercano a 1 es ideal) y el RMSE (más bajo es mejor). Comenta si el ajuste es bueno, regular o pobre.
|
277 |
-
ii. Interpretación de Parámetros: Explica brevemente qué representan los parámetros ajustados y si sus valores parecen razonables en un contexto de bioproceso (ej. tasas positivas, concentraciones no negativas).
|
278 |
-
iii. Ecuación Específica: Menciona la ecuación usada.
|
279 |
-
b. Comparación (si se probó más de una ecuación para un componente): ¿Cuál ecuación proporcionó el mejor ajuste y por qué?
|
280 |
-
3. **Problemas y Limitaciones:**
|
281 |
-
a. ¿Hay problemas evidentes (ej. R² muy bajo, parámetros físicamente no realistas, sobreajuste si se puede inferir, etc.)?
|
282 |
-
b. ¿Qué limitaciones podrían tener los modelos o el proceso de ajuste?
|
283 |
-
4. **Sugerencias y Próximos Pasos:**
|
284 |
-
a. ¿Cómo se podría mejorar el modelado (ej. probar otras ecuaciones, transformar datos, revisar calidad de datos experimentales)?
|
285 |
-
b. ¿Qué experimentos adicionales podrían realizarse para validar o refinar los modelos?
|
286 |
-
5. **Conclusión Final:** Un veredicto general conciso sobre el éxito del modelado y la utilidad de los resultados obtenidos.
|
287 |
-
|
288 |
-
Utiliza un lenguaje claro y accesible, pero manteniendo el rigor técnico. El análisis debe ser útil para alguien que busca entender la cinética de su bioproceso."""
|
289 |
-
|
290 |
full_prompt = prompt_intro + prompt_details + prompt_instructions
|
291 |
-
|
292 |
-
analysis_text = call_llm_analysis_service(full_prompt)
|
293 |
|
294 |
-
return
|
295 |
|
296 |
except Exception as general_e:
|
297 |
-
# Captura cualquier excepción no manejada y la muestra en la UI
|
298 |
error_trace = traceback.format_exc()
|
299 |
error_message_full = f"Error inesperado en process_and_plot: {general_e}\n{error_trace}"
|
300 |
print(error_message_full)
|
301 |
-
return
|
|
|
2 |
import numpy as np
|
3 |
import pandas as pd
|
4 |
import matplotlib
|
5 |
+
matplotlib.use('Agg') # Backend no interactivo
|
6 |
import matplotlib.pyplot as plt
|
7 |
from PIL import Image
|
8 |
import io
|
9 |
import json
|
10 |
+
import traceback # Para traceback detallado
|
11 |
|
12 |
+
# Importar BioprocessModel de TU models.py (el que usa sympy)
|
13 |
+
from models import BioprocessModel
|
14 |
+
# from decorators import gpu_decorator # No es necesario con Modal
|
15 |
|
16 |
+
# Variables globales que serán "inyectadas"
|
17 |
USE_MODAL_FOR_LLM_ANALYSIS = False
|
18 |
generate_analysis_from_modal = None
|
19 |
|
20 |
+
def create_error_image(message="Error", width=600, height=400):
|
21 |
+
"""Crea una imagen PIL simple para mostrar mensajes de error."""
|
22 |
+
img = Image.new('RGB', (width, height), color = (255, 200, 200)) # Fondo rojo claro
|
23 |
+
# No podemos dibujar texto fácilmente sin Pillow-SIMD o dependencias de dibujo complejas.
|
24 |
+
# Una imagen simple es suficiente para indicar un error.
|
25 |
+
# from PIL import ImageDraw
|
26 |
+
# d = ImageDraw.Draw(img)
|
27 |
+
# d.text((10,10), message, fill=(0,0,0)) # Esto requeriría una fuente
|
28 |
+
print(f"Generando imagen de error: {message}")
|
29 |
+
return img
|
30 |
+
|
31 |
def parse_bounds_str(bounds_str_input, num_params):
|
32 |
bounds_str = str(bounds_str_input).strip()
|
33 |
if not bounds_str:
|
34 |
print(f"Cadena de límites vacía para {num_params} params. Usando (-inf, inf).")
|
35 |
return [-np.inf] * num_params, [np.inf] * num_params
|
|
|
36 |
try:
|
37 |
bounds_str = bounds_str.lower().replace('inf', 'np.inf').replace('none', 'None')
|
38 |
+
if not (bounds_str.startswith('[') and bounds_str.endswith(']')):
|
39 |
bounds_str = f"[{bounds_str}]"
|
40 |
+
parsed_bounds_list = eval(bounds_str, {'np': np, 'inf': np.inf, 'None': None})
|
|
|
41 |
|
42 |
if not isinstance(parsed_bounds_list, list):
|
43 |
+
raise ValueError("Cadena de límites no evaluó a una lista.")
|
|
|
44 |
if len(parsed_bounds_list) != num_params:
|
45 |
+
raise ValueError(f"Num límites ({len(parsed_bounds_list)}) != num params ({num_params}).")
|
46 |
|
47 |
+
lower_bounds, upper_bounds = [], []
|
|
|
48 |
for item in parsed_bounds_list:
|
49 |
if not (isinstance(item, (tuple, list)) and len(item) == 2):
|
50 |
+
raise ValueError(f"Límite debe ser (low, high). Se encontró: {item}")
|
|
|
|
|
51 |
low = -np.inf if (item[0] is None or (isinstance(item[0], float) and np.isnan(item[0]))) else float(item[0])
|
52 |
high = np.inf if (item[1] is None or (isinstance(item[1], float) and np.isnan(item[1]))) else float(item[1])
|
53 |
+
lower_bounds.append(low); upper_bounds.append(high)
|
|
|
|
|
|
|
54 |
return lower_bounds, upper_bounds
|
55 |
except Exception as e:
|
56 |
+
print(f"Error al parsear límites '{bounds_str_input}': {e}. Usando por defecto (-inf, inf).")
|
57 |
return [-np.inf] * num_params, [np.inf] * num_params
|
58 |
|
|
|
59 |
def call_llm_analysis_service(prompt: str) -> str:
|
60 |
+
"""Llama al servicio LLM (ya sea localmente o a través de Modal)."""
|
61 |
+
# ... (sin cambios respecto a la versión anterior completa)
|
62 |
if USE_MODAL_FOR_LLM_ANALYSIS and generate_analysis_from_modal:
|
63 |
print("interface.py: Usando la función de análisis LLM de Modal...")
|
64 |
try:
|
65 |
return generate_analysis_from_modal(prompt)
|
66 |
except Exception as e_modal_call:
|
67 |
print(f"Error llamando a la función Modal LLM: {e_modal_call}")
|
68 |
+
traceback.print_exc()
|
69 |
return f"Error al contactar el servicio de análisis IA (Modal): {e_modal_call}"
|
70 |
else:
|
71 |
print("interface.py: Usando la función de análisis LLM local (fallback)...")
|
72 |
+
# Implementación de fallback local (como en la respuesta anterior)
|
73 |
try:
|
74 |
+
from config import MODEL_PATH, MAX_LENGTH, DEVICE
|
75 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
76 |
+
import torch # Asegurar importación de torch para fallback
|
77 |
|
78 |
print(f"Fallback: Cargando modelo {MODEL_PATH} localmente en {DEVICE}...")
|
79 |
tokenizer_local = AutoTokenizer.from_pretrained(MODEL_PATH)
|
|
|
86 |
inputs = tokenizer_local(prompt, return_tensors="pt", truncation=True, max_length=max_prompt_len).to(DEVICE)
|
87 |
with torch.no_grad():
|
88 |
outputs = model_local.generate(
|
89 |
+
**inputs, max_new_tokens=MAX_LENGTH,
|
|
|
90 |
eos_token_id=tokenizer_local.eos_token_id,
|
91 |
pad_token_id=tokenizer_local.pad_token_id if tokenizer_local.pad_token_id else tokenizer_local.eos_token_id,
|
92 |
do_sample=True, temperature=0.6, top_p=0.9
|
|
|
118 |
substrate_eq_count_ui,
|
119 |
product_eq_count_ui
|
120 |
):
|
121 |
+
# Imagen y texto de error por defecto
|
122 |
+
error_img = create_error_image("Error en procesamiento")
|
123 |
+
error_analysis_text = "No se pudo generar el análisis debido a un error."
|
124 |
+
|
125 |
+
try:
|
126 |
if file_obj is None:
|
127 |
+
return error_img, "Error: Por favor, sube un archivo Excel."
|
128 |
|
129 |
try:
|
130 |
df = pd.read_excel(file_obj.name)
|
131 |
except Exception as e:
|
132 |
+
return error_img, f"Error al leer el archivo Excel: {e}\n{traceback.format_exc()}"
|
133 |
|
134 |
expected_cols = ['Tiempo', 'Biomasa', 'Sustrato', 'Producto']
|
135 |
for col in expected_cols:
|
136 |
if col not in df.columns:
|
137 |
+
return error_img, f"Error: La columna '{col}' no se encuentra en el archivo Excel."
|
138 |
|
139 |
time_data = df['Tiempo'].values
|
140 |
biomass_data_exp = df['Biomasa'].values
|
141 |
substrate_data_exp = df['Sustrato'].values
|
142 |
product_data_exp = df['Producto'].values
|
143 |
|
144 |
+
# Asegurar que los contadores sean enteros válidos
|
145 |
+
try:
|
146 |
+
active_biomass_eqs = int(float(biomass_eq_count_ui))
|
147 |
+
active_substrate_eqs = int(float(substrate_eq_count_ui))
|
148 |
+
active_product_eqs = int(float(product_eq_count_ui))
|
149 |
+
except (TypeError, ValueError):
|
150 |
+
return error_img, "Error: Número de ecuaciones inválido."
|
151 |
+
|
152 |
|
153 |
all_eq_inputs = {
|
154 |
'biomass': (
|
|
|
178 |
biomass_params_for_s_p = None
|
179 |
|
180 |
for model_type, (eq_list, param_str_list, bound_str_list, exp_data) in all_eq_inputs.items():
|
181 |
+
if not (isinstance(exp_data, np.ndarray) and exp_data.size > 0 and np.any(np.isfinite(exp_data))):
|
182 |
+
print(f"Datos experimentales para {model_type} no válidos o vacíos, saltando ajuste.")
|
183 |
continue
|
184 |
|
185 |
for i in range(len(eq_list)):
|
186 |
+
eq_str, param_s, bound_s = eq_list[i], param_str_list[i], bound_str_list[i]
|
187 |
+
if not eq_str or not param_s: continue
|
|
|
|
|
|
|
|
|
|
|
188 |
|
|
|
|
|
189 |
try:
|
190 |
model_handler.set_model(model_type, eq_str, param_s)
|
191 |
num_p = len(model_handler.models[model_type]['params'])
|
192 |
l_b, u_b = parse_bounds_str(bound_s, num_p)
|
193 |
+
current_biomass_p = biomass_params_for_s_p if model_type in ['substrate', 'product'] else None
|
194 |
|
195 |
+
y_pred, popt = model_handler.fit_model(model_type, time_data, exp_data, bounds=(l_b, u_b), biomass_params_fitted=current_biomass_p)
|
|
|
|
|
196 |
|
197 |
+
current_params = model_handler.params.get(model_type, {}) # Obtener params del handler
|
198 |
r2_val = model_handler.r2.get(model_type, float('nan'))
|
199 |
rmse_val = model_handler.rmse.get(model_type, float('nan'))
|
200 |
|
201 |
+
fitted_results_for_plot[model_type].append({'equation': eq_str, 'y_pred': y_pred, 'params': current_params, 'R2': r2_val})
|
202 |
+
results_for_llm_prompt[model_type].append({'equation': eq_str, 'params_fitted': current_params, 'R2': r2_val, 'RMSE': rmse_val})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
203 |
|
204 |
+
if model_type == 'biomass' and biomass_params_for_s_p is None and current_params:
|
205 |
biomass_params_for_s_p = current_params
|
206 |
+
except Exception as e_fit:
|
207 |
+
error_msg = f"Error ajustando {model_type} #{i+1} ('{eq_str}'): {e_fit}\n{traceback.format_exc()}"
|
208 |
+
print(error_msg); return error_img, error_msg
|
|
|
|
|
|
|
209 |
|
210 |
# Generar gráfico
|
211 |
fig, axs = plt.subplots(3, 1, figsize=(10, 18), sharex=True)
|
212 |
+
plot_config_map = {
|
213 |
+
axs[0]: (biomass_data_exp, 'Biomasa', fitted_results_for_plot['biomass']),
|
214 |
axs[1]: (substrate_data_exp, 'Sustrato', fitted_results_for_plot['sustrato']),
|
215 |
axs[2]: (product_data_exp, 'Producto', fitted_results_for_plot['producto'])
|
216 |
}
|
217 |
|
218 |
+
for ax, data_actual, ylabel, plot_results in plot_config_map.items():
|
219 |
+
if isinstance(data_actual, np.ndarray) and data_actual.size > 0 and np.any(np.isfinite(data_actual)):
|
220 |
ax.plot(time_data, data_actual, 'o', label=f'Datos {ylabel}', markersize=5, alpha=0.7)
|
221 |
else:
|
222 |
+
ax.text(0.5, 0.5, f"No hay datos para {ylabel}", transform=ax.transAxes, ha='center', va='center')
|
223 |
|
224 |
+
for idx, res_detail in enumerate(plot_results):
|
225 |
+
label = f'Modelo {idx+1} (R²:{res_detail.get("R2", float("nan")):.3f})'
|
226 |
ax.plot(time_data, res_detail['y_pred'], '-', label=label, linewidth=2)
|
227 |
+
ax.set_xlabel('Tiempo'); ax.set_ylabel(ylabel); ax.grid(True, linestyle=':', alpha=0.7)
|
228 |
+
if show_legend_ui: ax.legend(loc=legend_position_ui, fontsize='small')
|
|
|
|
|
|
|
229 |
|
230 |
+
if show_params_ui and plot_results:
|
231 |
+
param_display_texts = [f"Modelo {idx+1}:\n" + "\n".join([f" {k}: {v:.4g}" for k,v in res_detail.get('params',{}).items()]) for idx, res_detail in enumerate(plot_results)]
|
232 |
+
ax.text(0.02, 0.98 if not ('upper' in legend_position_ui) else 0.02, "\n---\n".join(param_display_texts),
|
233 |
+
transform=ax.transAxes, fontsize=7, verticalalignment='top' if not ('upper' in legend_position_ui) else 'bottom',
|
234 |
+
bbox=dict(boxstyle='round,pad=0.3', fc='lightyellow', alpha=0.8))
|
235 |
+
|
236 |
+
plt.tight_layout(rect=[0, 0, 1, 0.96]); fig.suptitle("Resultados del Ajuste de Modelos Cinéticos", fontsize=16)
|
237 |
+
buf = io.BytesIO(); plt.savefig(buf, format='png', dpi=150); buf.seek(0)
|
238 |
+
image_pil = Image.open(buf); plt.close(fig)
|
239 |
+
|
240 |
+
# Construir prompt y llamar a LLM
|
241 |
+
prompt_intro = "Eres un experto en modelado cinético de bioprocesos...\n\n" # (como antes)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
242 |
prompt_details = json.dumps(results_for_llm_prompt, indent=2, ensure_ascii=False)
|
243 |
+
prompt_instructions = "\n\nPor favor, proporciona un análisis detallado...\n" # (como antes)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
244 |
full_prompt = prompt_intro + prompt_details + prompt_instructions
|
245 |
+
analysis_text_llm = call_llm_analysis_service(full_prompt)
|
|
|
246 |
|
247 |
+
return image_pil, analysis_text_llm
|
248 |
|
249 |
except Exception as general_e:
|
|
|
250 |
error_trace = traceback.format_exc()
|
251 |
error_message_full = f"Error inesperado en process_and_plot: {general_e}\n{error_trace}"
|
252 |
print(error_message_full)
|
253 |
+
return create_error_image(f"Error: {general_e}"), error_message_full
|