changes made in all 3

app.py

@@ -1,20 +1,22 @@
 import streamlit as st
+import pandas as pd
 from db import insert_data_if_empty, get_mongo_client
 from chatbot import chatbot_response
 
-# Ensure MongoDB is populated.
+# Ensure that historical data is inserted if not already present.
 insert_data_if_empty()
-collection = get_mongo_client()
 
-st.subheader("💬 Chatbot for MongoDB Entry Analysis")
-st.write("Ask me something (e.g., 'Provide analysis for the data entry 1 in the dataset'):")
+# Connect to MongoDB (optional: can be used for additional visualizations).
+collection = get_mongo_client()
 
-user_prompt = st.text_area("Your query:")
+st.subheader("💬 Chatbot with Analysis for MongoDB Entries")
+# Updated hint: ask for analysis of a specific data entry.
+user_prompt = st.text_area("Ask me something (e.g., 'Provide analysis for the data entry 1 in the dataset'):")
 
 if st.button("Get AI Response"):
     ai_response, sentiment_label, sentiment_confidence, topic_label, topic_confidence = chatbot_response(user_prompt)
     if ai_response:
-        st.write("### AI Response:")
+        st.write("### Response:")
         st.write(ai_response)
         st.write("### Sentiment Analysis:")
         st.write(f"**Sentiment:** {sentiment_label} ({sentiment_confidence:.2f} confidence)")

chatbot.py

@@ -3,7 +3,7 @@ import re
 import streamlit as st
 import google.generativeai as genai
 from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
-from db import get_entry_by_index
+from db import get_entry_by_index  # For fetching a specific entry from MongoDB
 
 # Configure Gemini API key
 GEMINI_API_KEY = os.getenv("gemini_api")
@@ -56,16 +56,13 @@ def extract_topic(text):
     except Exception as e:
         return f"Error extracting topic: {e}", None
 
-# Helper function to parse a data entry index from the user's prompt.
-# It looks for a pattern like "data entry 1" or "entry 1" (case insensitive).
-def parse_entry_index(prompt):
-    match = re.search(r'(?:data\s+entry|entry)\s+(\d+)', prompt, re.IGNORECASE)
+# Helper: extract an entry index from a query string.
+# For example, "data entry 1" or "entry 2" will return index 0 or 1 respectively.
+def extract_entry_index(prompt):
+    match = re.search(r'(data entry|entry)\s+(\d+)', prompt, re.IGNORECASE)
     if match:
-        try:
-            # Convert to zero-based index.
-            return int(match.group(1)) - 1
-        except ValueError:
-            return None
+        index = int(match.group(2)) - 1  # Convert to 0-based index
+        return index
     return None
 
 def chatbot_response(user_prompt):
@@ -73,30 +70,41 @@ def chatbot_response(user_prompt):
         return None, None, None, None, None
 
     try:
-        # Check if the prompt contains a specific data entry request.
-        index = parse_entry_index(user_prompt)
-        if index is not None:
-            # Fetch the specified entry from MongoDB.
-            entry = get_entry_by_index(index)
+        # Check if the user query asks for a specific dataset entry.
+        entry_index = extract_entry_index(user_prompt)
+        if entry_index is not None:
+            # Fetch the requested entry from MongoDB.
+            entry = get_entry_by_index(entry_index)
             if entry is None:
-                return f"❌ No entry found for data entry {index+1}.", None, None, None, None
+                return "❌ No entry found for the requested index.", None, None, None, None
+            # Extract the required fields.
             entry_text = entry.get("text", "No text available.")
-            # Construct a simple generative prompt.
-            combined_prompt = f"Let's break down this tweet-like MongoDB entry:\n{entry_text}"
-            # Analyze sentiment and topic on the entry's text.
+            entry_user = entry.get("user", "Unknown")
+            entry_date = entry.get("date", "Unknown")
+            
+            # Build a static response message with only the desired parts.
+            ai_response = (
+                "Let's break down this tweet-like MongoDB entry:\n\n"
+                f"Text: {entry_text}\n"
+                f"User: {entry_user}\n"
+                f"Date: {entry_date}"
+            )
+            
+            # Perform sentiment and topic analysis on the entry's text.
             sentiment_label, sentiment_confidence = analyze_sentiment(entry_text)
             topic_label, topic_confidence = extract_topic(entry_text)
+            
+            return ai_response, sentiment_label, sentiment_confidence, topic_label, topic_confidence
         else:
-            # For any other prompt, use it as is.
-            combined_prompt = user_prompt
+            # For other queries, use the generative model flow.
+            model_gen = genai.GenerativeModel("gemini-1.5-pro")
+            ai_response_obj = model_gen.generate_content(user_prompt)
+            ai_response = ai_response_obj.text
+            
+            # Perform sentiment and topic analysis on the user prompt.
             sentiment_label, sentiment_confidence = analyze_sentiment(user_prompt)
             topic_label, topic_confidence = extract_topic(user_prompt)
-        
-        # Generate AI response using Gemini with the constructed prompt.
-        model_gen = genai.GenerativeModel("gemini-1.5-pro")
-        ai_response = model_gen.generate_content(combined_prompt)
-
-        # Return the generative response and the separately computed sentiment and category.
-        return ai_response.text, sentiment_label, sentiment_confidence, topic_label, topic_confidence
+            
+            return ai_response, sentiment_label, sentiment_confidence, topic_label, topic_confidence
     except Exception as e:
         return f"❌ Error: {e}", None, None, None, None

db.py

@@ -17,6 +17,11 @@ def insert_data_if_empty():
             response = requests.get(csv_url)
             response.raise_for_status()
             df = pd.read_csv(io.StringIO(response.text), encoding="ISO-8859-1")
+            # Add default fields if not present.
+            if "user" not in df.columns:
+                df["user"] = "Unknown"
+            if "date" not in df.columns:
+                df["date"] = "Unknown"
             collection.insert_many(df.to_dict("records"))
             print("✅ Data Inserted into MongoDB!")
         except Exception as e:
@@ -24,9 +29,9 @@ def insert_data_if_empty():
 
 def get_entry_by_index(index=0):
     collection = get_mongo_client()
-    # Skip the first "index" documents and return the next one.
-    cursor = collection.find({}, {"_id": 0}).skip(index).limit(1)
-    docs = list(cursor)
+    # Fetch the document by skipping "index" entries.
+    doc_cursor = collection.find({}, {"_id": 0}).skip(index).limit(1)
+    docs = list(doc_cursor)
     if docs:
         return docs[0]
     return None