Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 import nltk
 import numpy as np
@@ -41,20 +41,21 @@ try:
 except FileNotFoundError:
     raise FileNotFoundError("Error: 'data.pickle' file not found. Ensure it exists and matches the model.")
 
-# Build the model structure using Keras
-from tensorflow.keras.models import Sequential
-from tensorflow.keras.layers import Dense
-from tensorflow.keras.optimizers import Adam
-from tensorflow.keras.losses import CategoricalCrossentropy
+# Build the model structure
+net = tflearn.input_data(shape=[None, len(training[0])])
+net = tflearn.fully_connected(net, 8)
+net = tflearn.fully_connected(net, 8)
+net = tflearn.fully_connected(net, len(output[0]), activation="softmax")
+net = tflearn.regression(net)
 
-model = Sequential()
-model.add(Dense(8, input_shape=(len(training[0]),), activation='relu'))
-model.add(Dense(8, activation='relu'))
-model.add(Dense(len(output[0]), activation='softmax'))
-model.compile(optimizer=Adam(), loss=CategoricalCrossentropy(), metrics=['accuracy'])
+# Create a new model instance
+model = tflearn.DNN(net)
 
-# Load the trained model weights
-model.load_weights("MentalHealthChatBotmodel.tflearn")
+# Create a checkpoint object
+checkpoint = tf.train.Checkpoint(model=model)
+
+# Load the model weights
+checkpoint.restore("path/to/save/MentalHealthChatBotmodel")
 
 # Function to process user input into a bag-of-words format
 def bag_of_words(s, words):
@@ -74,7 +75,7 @@ def chat(message, history):
 
     try:
         # Predict the tag
-        results = model.predict(np.array([bag_of_words(message, words)]))
+        results = model.predict([bag_of_words(message, words)])
         results_index = np.argmax(results)
         tag = labels[results_index]
 
@@ -162,7 +163,7 @@ def scrape_website_for_contact_info(website):
         response = requests.get(website, timeout=5)
         soup = BeautifulSoup(response.content, 'html.parser')
 
-        phone_match = re.search(r'$$?\+?[0-9]*$$?[0-9_\- $$$$]*', soup.get_text())
+        phone_match = re.search(r'\(?\+?[0-9]*\)?[0-9_\- \(\)]*', soup.get_text())
         if phone_match:
             phone_number = phone_match.group()
 
@@ -243,7 +244,7 @@ def main():
 # Gradio UI setup
 with gr.Blocks() as demo:
     # Load pre-trained model and tokenizer
-    @gr.cache
+    @gr.cache_resource
     def load_model():
         tokenizer = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
         model = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
@@ -278,7 +279,7 @@ with gr.Blocks() as demo:
 
         try:
             # Predict the tag
-            results = model.predict(np.array([bag_of_words(message, words)]))
+            results = model.predict([bag_of_words(message, words)])
             results_index = np.argmax(results)
             tag = labels[results_index]