Update chatbot.py

chatbot.py

@@ -15,10 +15,10 @@ AI_MODELS = [
         "name": "google/gemma-2b",
         "endpoint": "https://api-inference.huggingface.co/models/google/gemma-2b",
         "parameters": {
-            "max_length": 60,      # Slightly increased for more expressive responses
-            "temperature": 0.9,    # Higher for creativity
-            "top_p": 0.9,          # Encourage diversity in responses
-            "top_k": 50            # Consider top 50 tokens for sampling
+            "max_length": 60,
+            "temperature": 0.9,
+            "top_p": 0.9,
+            "top_k": 50
         }
     },
     {
@@ -26,7 +26,7 @@ AI_MODELS = [
         "endpoint": "https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1",
         "parameters": {
             "max_length": 60,
-            "temperature": 0.8,    # Slightly lower for coherence
+            "temperature": 0.8,
             "top_p": 0.95,
             "top_k": 40
         }
@@ -36,7 +36,7 @@ AI_MODELS = [
         "endpoint": "https://api-inference.huggingface.co/models/facebook/blenderbot-400M-distill",
         "parameters": {
             "max_length": 50,
-            "temperature": 0.85,   # Balanced for conversational tone
+            "temperature": 0.85,
             "top_p": 0.9,
             "top_k": 50
         }
@@ -46,7 +46,7 @@ AI_MODELS = [
         "endpoint": "https://api-inference.huggingface.co/models/EleutherAI/gpt-neo-1.3B",
         "parameters": {
             "max_length": 50,
-            "temperature": 0.9,    # Higher for creativity
+            "temperature": 0.9,
             "top_p": 0.9,
             "top_k": 50
         }
@@ -56,7 +56,7 @@ AI_MODELS = [
         "endpoint": "https://api-inference.huggingface.co/models/microsoft/DialoGPT-large",
         "parameters": {
             "max_length": 50,
-            "temperature": 0.85,   # Balanced for conversational tone
+            "temperature": 0.85,
             "top_p": 0.9,
             "top_k": 40
         }
@@ -66,14 +66,14 @@ AI_MODELS = [
         "endpoint": "https://api-inference.huggingface.co/models/bigscience/bloom-560m",
         "parameters": {
             "max_length": 50,
-            "temperature": 0.9,    # Higher for creativity
+            "temperature": 0.9,
             "top_p": 0.95,
             "top_k": 50
         }
     },
     {
         "name": "Grok by xAI",
-        "endpoint": None,  # Special case: Grok will be simulated directly
+        "endpoint": None,
         "parameters": {
             "max_length": 50,
             "temperature": 0.8,
@@ -116,16 +116,45 @@ conversation_context = {
     "message_count": 0   # Track the number of messages to trigger Ayush-teasing every 5th message
 }
 
+def analyze_sentiment(user_input):
+    """Analyze the sentiment of the user's input using a sentiment analysis model."""
+    headers = {
+        "Authorization": f"Bearer {HUGGINGFACE_API_TOKEN}",
+        "Content-Type": "application/json"
+    }
+    payload = {
+        "inputs": user_input
+    }
+    try:
+        response = requests.post(
+            "https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english",
+            headers=headers,
+            json=payload
+        )
+        if response.status_code == 200:
+            result = response.json()
+            if isinstance(result, list) and len(result) > 0:
+                sentiment = result[0]
+                label = sentiment[0]["label"]  # "POSITIVE" or "NEGATIVE"
+                return label.lower()
+        return "neutral"
+    except Exception as e:
+        print(f"Error analyzing sentiment: {str(e)}")
+        return "neutral"
+
 def get_krishna_response(user_input):
     """
     Generate a response from Little Krishna based on user input.
     - Match user input to predefined messages in krishna_blessings or ayush_surprises using keywords.
-    - Use context to provide more coherent responses.
+    - Use sentiment analysis to tailor responses based on Manavi's mood.
     - Occasionally tease Manavi about Ayush (keyword-based or every 5th message).
     - Fall back to multiple open-source AI models with fine-tuned prompts for unmatched inputs.
     """
     user_input_lower = user_input.lower().strip()
 
+    # Analyze the sentiment of the user's input
+    sentiment = analyze_sentiment(user_input)
+
     # Increment message count
     conversation_context["message_count"] += 1
 
@@ -161,6 +190,12 @@ def get_krishna_response(user_input):
         conversation_context["last_topic"] = "ayush"
         return random.choice(ayush_teasing["ayush"])
 
+    # Sentiment-based responses
+    if sentiment == "negative" and "sad" not in user_input_lower:  # Avoid overlap with keyword "sad"
+        return "Hare Manavi! I see a little cloud over your heart—let’s dance by the Yamuna to bring back your smile!"
+    if sentiment == "positive":
+        return "Hare Manavi! Your joy lights up Vrindavan—shall we celebrate with a flute melody?"
+
     # Trigger for "chat with you"
     if "chat with you" in user_input_lower or "want to chat" in user_input_lower:
         conversation_context["last_topic"] = "chat_with_you"