change in model

app.py

@@ -4,7 +4,7 @@ import google.generativeai as genai  # Import Generative AI library
 import os
 from pymongo import MongoClient
 from db import insert_data_if_empty, get_mongo_client  # Import functions from db.py
-from transformers import pipeline  # Import sentiment analysis model
+from transformers import pipeline  # Import sentiment analysis pipeline
 
 # 🔑 Fetch API key from Hugging Face Secrets
 GEMINI_API_KEY = os.getenv("gemini_api")
@@ -20,8 +20,16 @@ insert_data_if_empty()
 #### **2. MongoDB Connection**
 collection = get_mongo_client()
 
-#### **3. Streamlit App to Display Data**
-st.title("📊 MongoDB Data Viewer with AI Sentiment Chatbot")
+#### **3. Load Sentiment Analysis Model**
+sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
+
+def analyze_sentiment(text):
+    """Analyze sentiment using RoBERTa model."""
+    sentiment_result = sentiment_pipeline(text)[0]['label']
+    return sentiment_result  # Returns "LABEL_0", "LABEL_1", or "LABEL_2"
+
+#### **4. Streamlit App to Display Data**
+st.title("📊 MongoDB Data Viewer with AI & Sentiment Analysis")
 
 # Show first 5 rows from MongoDB
 st.subheader("First 5 Rows from Database")
@@ -37,38 +45,29 @@ if st.button("Show Complete Data"):
     all_data = list(collection.find({}, {"_id": 0}))
     st.write(pd.DataFrame(all_data))
 
-#### **4. Sentiment Analysis Chatbot**
-st.subheader("🤖 AI Sentiment Analysis Chatbot")
-
-# Load Hugging Face sentiment analysis model (RoBERTa)
-sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
+#### **5. AI Chatbot with Sentiment Analysis**
+st.subheader("🤖 AI Chatbot with Sentiment Analysis")
 
 # User input for chatbot
-user_prompt = st.text_input("Enter a text for sentiment analysis:")
+user_prompt = st.text_input("Paste text here for AI sentiment analysis:")
 
-if st.button("Analyze Sentiment"):
+if st.button("Get AI Response & Sentiment"):
     if user_prompt:
         try:
-            # Perform sentiment analysis
-            sentiment_result = sentiment_pipeline(user_prompt)[0]
-
-            # Display sentiment results
-            st.write("### Sentiment Analysis Result:")
-            st.write(f"**Sentiment:** {sentiment_result['label']}")
-            st.write(f"**Confidence Score:** {sentiment_result['score']:.4f}")
+            # Generate AI response
+            model = genai.GenerativeModel("gemini-1.5-pro")
+            response = model.generate_content(user_prompt)
+            ai_response = response.text
 
-            # Fetch similar sentiment examples from MongoDB
-            sentiment_label = sentiment_result["label"].lower()
-            matching_texts = list(collection.find({"sentiment": sentiment_label}, {"_id": 0, "text": 1}).limit(3))
+            # Analyze sentiment
+            sentiment = analyze_sentiment(ai_response)
 
-            if matching_texts:
-                st.write("### Similar Sentiment Examples from MongoDB:")
-                for item in matching_texts:
-                    st.write(f"- {item['text']}")
-            else:
-                st.write("No similar sentiment examples found in MongoDB.")
+            # Display results
+            st.write("### AI Response:")
+            st.write(ai_response)
+            st.write(f"**Sentiment Analysis:** {sentiment}")
 
         except Exception as e:
             st.error(f"❌ Error: {e}")
     else:
-        st.warning("⚠️ Please enter some text.")
+        st.warning("⚠️ Please enter a text input.")