changes in the model with topic extraction

app.py

@@ -10,30 +10,30 @@ insert_data_if_empty()
 collection = get_mongo_client()
 
 #### **3. Streamlit App UI**
-st.title("📊 AI Sentiment Analysis Chatbot")
+# st.title("📊 MongoDB Data Viewer with AI Sentiment Chatbot")
 
-# Show first 5 rows from MongoDB
-#st.subheader("First 5 Rows from Database")
-#data = list(collection.find({}, {"_id": 0}).limit(5))
+# # Show first 5 rows from MongoDB
+# st.subheader("First 5 Rows from Database")
+# data = list(collection.find({}, {"_id": 0}).limit(5))
 
-#if data:
-#    st.write(pd.DataFrame(data))
-#else:
-#    st.warning("⚠️ No data found. Try refreshing the app.")
+# if data:
+#     st.write(pd.DataFrame(data))
+# else:
+#     st.warning("⚠️ No data found. Try refreshing the app.")
 
-# Button to show full MongoDB data
-#if st.button("Show Complete Data"):
-#    all_data = list(collection.find({}, {"_id": 0}))
-#    st.write(pd.DataFrame(all_data))
+# # Button to show full MongoDB data
+# if st.button("Show Complete Data"):
+#     all_data = list(collection.find({}, {"_id": 0}))
+#     st.write(pd.DataFrame(all_data))
 
-#### **4. AI Chatbot with Sentiment Analysis**
-st.subheader("🤖 AI Chatbot with Sentiment Analysis")
+#### **4. AI Chatbot with Sentiment Analysis & Topic Extraction**
+st.subheader("🤖 AI Chatbot with Sentiment Analysis & Topic Extraction")
 
 # User input for chatbot
 user_prompt = st.text_area("Ask AI something or paste text for sentiment analysis:")
 
 if st.button("Analyze Sentiment & Get AI Response"):
-    ai_response, sentiment_label, confidence = chatbot_response(user_prompt)
+    ai_response, sentiment_label, confidence, topics = chatbot_response(user_prompt)
 
     if ai_response:
         st.write("### AI Response:")
@@ -41,5 +41,9 @@ if st.button("Analyze Sentiment & Get AI Response"):
 
         st.write("### Sentiment Analysis:")
         st.write(f"**Sentiment:** {sentiment_label} ({confidence:.2f} confidence)")
+
+        st.write("### Extracted Topics:")
+        st.write(", ".join(topics) if topics else "No topics identified.")
+
     else:
-        st.warning("⚠️ Please enter a question or text for sentiment analysis.")
+        st.warning("⚠️ Please enter a question or text for analysis.")

backup.py

@@ -1,18 +1,7 @@
 import streamlit as st
 import pandas as pd
-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 Hugging Face transformers for sentiment analysis
-
-# 🔑 Fetch API key from Hugging Face Secrets
-GEMINI_API_KEY = os.getenv("gemini_api")
-
-if GEMINI_API_KEY:
-    genai.configure(api_key=GEMINI_API_KEY)
-else:
-    st.error("⚠️ Google API key is missing! Set it in Hugging Face Secrets.")
+from db import insert_data_if_empty, get_mongo_client
+from chatbot import chatbot_response  # Import chatbot functionality
 
 #### **1. Ensure Data is Inserted Before Display**
 insert_data_if_empty()
@@ -20,8 +9,8 @@ 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. Streamlit App UI**
+st.title("📊 AI Sentiment Analysis Chatbot")
 
 # Show first 5 rows from MongoDB
 #st.subheader("First 5 Rows from Database")
@@ -37,48 +26,78 @@ st.title("📊 MongoDB Data Viewer with AI Sentiment Chatbot")
 #    all_data = list(collection.find({}, {"_id": 0}))
 #    st.write(pd.DataFrame(all_data))
 
-#### **4. Load Sentiment Analysis Model (RoBERTa)**
-sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
-
-# Function to analyze sentiment
-def analyze_sentiment(text):
-    sentiment_result = sentiment_pipeline(text)[0]
-    label = sentiment_result['label']  # Extract sentiment label (POSITIVE, NEGATIVE, NEUTRAL)
-    score = sentiment_result['score']  # Extract confidence score
-
-    # Convert labels to a readable format
-    sentiment_mapping = {
-        "LABEL_0": "Negative",
-        "LABEL_1": "Neutral",
-        "LABEL_2": "Positive"
-    }
-    return sentiment_mapping.get(label, "Unknown"), score
-
-#### **5. AI Chatbot with Sentiment Analysis**
+#### **4. AI Chatbot with Sentiment Analysis**
 st.subheader("🤖 AI Chatbot with Sentiment Analysis")
 
 # User input for chatbot
 user_prompt = st.text_area("Ask AI something or paste text for sentiment analysis:")
 
 if st.button("Analyze Sentiment & Get AI Response"):
-    if user_prompt:
-        try:
-            # AI Response from Gemini
-            model = genai.GenerativeModel("gemini-1.5-pro")
-            ai_response = model.generate_content(user_prompt)
+    ai_response, sentiment_label, confidence = chatbot_response(user_prompt)
 
-            # Sentiment Analysis
-            sentiment_label, confidence = analyze_sentiment(user_prompt)
+    if ai_response:
+        st.write("### AI Response:")
+        st.write(ai_response)
 
-            # Display AI Response & Sentiment Analysis
-            st.write("### AI Response:")
-            st.write(ai_response.text)
-
-            st.write("### Sentiment Analysis:")
-            st.write(f"**Sentiment:** {sentiment_label} ({confidence:.2f} confidence)")
-
-        except Exception as e:
-            st.error(f"❌ Error: {e}")
+        st.write("### Sentiment Analysis:")
+        st.write(f"**Sentiment:** {sentiment_label} ({confidence:.2f} confidence)")
     else:
         st.warning("⚠️ Please enter a question or text for sentiment analysis.")
 
+#chatbot.py
+import os
+import streamlit as st
+import google.generativeai as genai
+from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
+
+# 🔑 Fetch API key from Hugging Face Secrets
+GEMINI_API_KEY = os.getenv("gemini_api")
+
+if GEMINI_API_KEY:
+    genai.configure(api_key=GEMINI_API_KEY)
+else:
+    st.error("⚠️ Google API key is missing! Set it in Hugging Face Secrets.")
+
+# Correct Model Path
+MODEL_NAME = "cardiffnlp/twitter-roberta-base-sentiment"
+
+# Load Sentiment Analysis Model (Ensure the correct model is used)
+try:
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    sentiment_pipeline = pipeline("sentiment-analysis", model=MODEL_NAME, tokenizer=tokenizer)
+except Exception as e:
+    st.error(f"❌ Error loading sentiment model: {e}")
+
+# Function to analyze sentiment
+def analyze_sentiment(text):
+    try:
+        sentiment_result = sentiment_pipeline(text)[0]
+        label = sentiment_result['label']  # Extract sentiment label (POSITIVE, NEGATIVE, NEUTRAL)
+        score = sentiment_result['score']  # Extract confidence score
+
+        # Convert labels to readable format
+        sentiment_mapping = {
+            "LABEL_0": "Negative",
+            "LABEL_1": "Neutral",
+            "LABEL_2": "Positive"
+        }
+        return sentiment_mapping.get(label, "Unknown"), score
+    except Exception as e:
+        return f"Error analyzing sentiment: {e}", None
+
+# Function to generate AI response & analyze sentiment
+def chatbot_response(user_prompt):
+    if not user_prompt:
+        return None, None, None
+
+    try:
+        # AI Response from Gemini
+        model = genai.GenerativeModel("gemini-1.5-pro")
+        ai_response = model.generate_content(user_prompt)
+
+        # Sentiment Analysis
+        sentiment_label, confidence = analyze_sentiment(user_prompt)
+
+        return ai_response.text, sentiment_label, confidence
+    except Exception as e:
+        return f"❌ Error: {e}", None, None

chatbot.py

@@ -2,6 +2,7 @@ import os
 import streamlit as st
 import google.generativeai as genai
 from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
+from keybert import KeyBERT  # Topic Extraction
 
 # 🔑 Fetch API key from Hugging Face Secrets
 GEMINI_API_KEY = os.getenv("gemini_api")
@@ -14,13 +15,16 @@ else:
 # Correct Model Path
 MODEL_NAME = "cardiffnlp/twitter-roberta-base-sentiment"
 
-# Load Sentiment Analysis Model (Ensure the correct model is used)
+# Load Sentiment Analysis Model
 try:
     tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
     sentiment_pipeline = pipeline("sentiment-analysis", model=MODEL_NAME, tokenizer=tokenizer)
 except Exception as e:
     st.error(f"❌ Error loading sentiment model: {e}")
 
+# Load KeyBERT for topic extraction
+kw_model = KeyBERT()
+
 # Function to analyze sentiment
 def analyze_sentiment(text):
     try:
@@ -38,10 +42,18 @@ def analyze_sentiment(text):
     except Exception as e:
         return f"Error analyzing sentiment: {e}", None
 
-# Function to generate AI response & analyze sentiment
+# Function to extract key topics
+def extract_topics(text, num_keywords=3):
+    try:
+        keywords = kw_model.extract_keywords(text, keyphrase_ngram_range=(1, 2), top_n=num_keywords)
+        return [word[0] for word in keywords]  # Return only the keywords
+    except Exception as e:
+        return [f"Error extracting topics: {e}"]
+
+# Function to generate AI response, analyze sentiment, and extract topics
 def chatbot_response(user_prompt):
     if not user_prompt:
-        return None, None, None
+        return None, None, None, None
 
     try:
         # AI Response from Gemini
@@ -51,6 +63,9 @@ def chatbot_response(user_prompt):
         # Sentiment Analysis
         sentiment_label, confidence = analyze_sentiment(user_prompt)
 
-        return ai_response.text, sentiment_label, confidence
+        # Topic Extraction
+        topics = extract_topics(user_prompt)
+
+        return ai_response.text, sentiment_label, confidence, topics
     except Exception as e:
-        return f"❌ Error: {e}", None, None
+        return f"❌ Error: {e}", None, None, None