Update app.py

app.py

@@ -14,6 +14,10 @@ from nltk.stem.lancaster import LancasterStemmer
 import os
 from functools import lru_cache
 import pandas as pd
+import tensorflow as tf  # Added to enable resource variables
+
+# Enable resource variables in TensorFlow to avoid deprecated warnings
+tf.compat.v1.enable_resource_variables()
 
 # Ensure necessary NLTK resources are downloaded
 nltk.download('punkt')
@@ -213,77 +217,22 @@ def generate_map(wellness_data):
 
     for place in wellness_data:
         name, address, lat, lon = place
-        folium.Marker(
-            location=[lat, lon],
-            popup=f"<b>{name}</b><br>{address}",
-            icon=folium.Icon(color='blue', icon='info-sign')
-        ).add_to(m)
+        folium.Marker([lat, lon], popup=f"{name}\n{address}").add_to(m)
 
-    # Save map as an HTML string
-    map_html = m._repr_html_()
-    
-    return map_html
+    return m
 
-# Gradio interface setup for user interaction
-def user_interface(message, location, history, api_key, words, labels, model):
-    history, history = chat(message, history, words, labels, model)
-    
-    # Sentiment analysis
-    inputs = tokenizer_sentiment(message, return_tensors="pt")
-    outputs = model_sentiment(**inputs)
-    sentiment = ["Negative", "Neutral", "Positive"][torch.argmax(outputs.logits, dim=1).item()]
-    
-    # Emotion detection
-    emotion, resources, video_link = detect_emotion(message)
-    
-    # Get wellness professionals
-    wellness_data = get_wellness_professionals(location, api_key)
-    
-    # Generate the map
-    map_html = generate_map(wellness_data)
-    
-    # Create a DataFrame for the suggestions
-    suggestions_df = pd.DataFrame(resources, columns=["Resource", "Link"])
-    
-    # Format the final output
-    output = f"**Chat Response:** {history[-1][1]}\n\n"
-    output += f"**Sentiment:** {sentiment}\n\n"
-    output += f"**Detected Emotion:** {emotion}\n\n"
-    output += "**Suggestions based on Emotion:**\n"
-    for resource in resources:
-        output += f"- [{resource[0]}]({resource[1]})\n"
-    output += f"\n**Video Suggestion:** {video_link}\n\n"
-    output += "**Wellness Professionals near you:**\n"
-    output += map_html
-    
-    return output, history
+# Initialize the necessary files
+data = load_intents("intents.json")
+words, labels, training, output = load_preprocessed_data("data.pickle")
 
-# Load intents and preprocessed data
-data = load_intents('intents.json')
-words, labels, training, output = load_preprocessed_data('data.pkl')
-
-# Build and load the model
-net = build_model(words, labels, training, output)
-model = load_model('model.tflearn', net)
+# Build the model
+model = build_model(words, labels, training, output)
+model = load_model("model.tflearn", model)
 
 # Gradio interface
-iface = gr.Interface(
-    fn=user_interface,
-    inputs=[
-        gr.inputs.Textbox(label="Message"),
-        gr.inputs.Textbox(label="Location"),
-        gr.State([]),  # History
-        gr.State(os.getenv("GOOGLE_API_KEY")),  # API Key
-        gr.State(words),
-        gr.State(labels),
-        gr.State(model)
-    ],
-    outputs=[
-        gr.outputs.Markdown(label="Response"),
-        gr.outputs.Chatbot(label="Chat History")
-    ],
-    title="Wellness Chatbot",
-    description="A chatbot to provide wellness support and locate professionals near you."
-)
+def chatbot_interface(message, history):
+    return chat(message, history, words, labels, model)
+
+# Example usage with Gradio UI
+gr.Interface(fn=chatbot_interface, inputs=["text", "state"], outputs=["chatbot", "state"]).launch()
 
-iface.launch(debug=True)