Update rag.py

rag.py

@@ -1,149 +1,286 @@
 import json
-import glob
-import os
-import pandas as pd
-from datetime import datetime
-from dotenv import load_dotenv
 
-# AI and Data Libraries
 from sentence_transformers import SentenceTransformer, util
+
 from groq import Groq
+
+from datetime import datetime
+
+import os
+
+import pandas as pd
+
 from datasets import load_dataset, Dataset
 
-# Image and Utility Libraries
-import requests
-from io import BytesIO
-from PIL import Image, ImageDraw, ImageFont
-import numpy as np
+from dotenv import load_dotenv
+
+import random
+
+import glob
+
+
 
 # Load environment variables
+
 load_dotenv()
 
+
+
 # Initialize Groq client
+
 groq_client = Groq(api_key=os.getenv("GROQ_API_KEY"))
 
-# Load models and dataset
+
+
+# Load similarity model
+
 similarity_model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
 
+
+
 # Config
+
 HF_DATASET_REPO = "midrees2806/unmatched_queries"
+
 HF_TOKEN = os.getenv("HF_TOKEN")
 
-# Load multiple JSON datasets from the 'datasets' folder
+
+
+# Greeting list
+
+GREETINGS = [
+
+    "hi", "hello", "hey", "good morning", "good afternoon", "good evening",
+
+    "assalam o alaikum", "salam", "aoa", "hi there",
+
+    "hey there", "greetings"
+
+]
+
+
+
+# Fixed rephrased unmatched query responses
+
+UNMATCHED_RESPONSES = [
+
+    "Thank you for your query. We’ve forwarded it to our support team and it will be added soon. In the meantime, you can visit the University of Education official website or reach out via the contact details below.\n\n📞 +92-42-99262231-33\n✉️ info@ue.edu.pk\n🌐 https://ue.edu.pk",
+
+    "We’ve noted your question and it’s in queue for inclusion. For now, please check the University of Education website or contact the administration directly.\n\n📞 +92-42-99262231-33\n✉️ info@ue.edu.pk\n🌐 https://ue.edu.pk",
+
+    "Your query has been recorded. We’ll update the system with relevant information shortly. Meanwhile, you can visit UE's official site or reach out using the details below:\n\n📞 +92-42-99262231-33\n✉️ info@ue.edu.pk\n🌐 https://ue.edu.pk",
+
+    "We appreciate your question. It has been forwarded for further processing. Until it’s available here, feel free to visit the official UE website or use the contact options:\n\n📞 +92-42-99262231-33\n✉️ info@ue.edu.pk\n🌐 https://ue.edu.pk"
+
+]
+
+
+
+# Load multiple JSON datasets
+
 dataset = []
+
 try:
-    # Using glob to find all json files in the folder
+
     json_files = glob.glob('datasets/*.json')
+
     for file_path in json_files:
+
         with open(file_path, 'r', encoding='utf-8') as f:
+
             data = json.load(f)
+
             if isinstance(data, list):
+
                 for item in data:
+
                     if isinstance(item, dict) and 'Question' in item and 'Answer' in item:
+
                         dataset.append(item)
+
+                    else:
+
+                        print(f"Invalid entry in {file_path}: {item}")
+
             else:
-                print(f"Skipping {file_path}: File does not contain a list.")
+
+                print(f"File {file_path} does not contain a list.")
+
 except Exception as e:
+
     print(f"Error loading datasets: {e}")
 
+
+
 # Precompute embeddings
+
 dataset_questions = [item.get("Question", "").lower().strip() for item in dataset]
+
 dataset_answers = [item.get("Answer", "") for item in dataset]
 
-if dataset_questions:
-    dataset_embeddings = similarity_model.encode(dataset_questions, convert_to_tensor=True)
-else:
-    dataset_embeddings = None
-    print("Warning: No data found in the datasets folder.")
+dataset_embeddings = similarity_model.encode(dataset_questions, convert_to_tensor=True)
+
+
 
 # Save unmatched queries to Hugging Face
+
 def manage_unmatched_queries(query: str):
+
     try:
+
         timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
         try:
+
             ds = load_dataset(HF_DATASET_REPO, token=HF_TOKEN)
+
             df = ds["train"].to_pandas()
+
         except:
+
             df = pd.DataFrame(columns=["Query", "Timestamp", "Processed"])
-            
+
         if query not in df["Query"].values:
+
             new_entry = {"Query": query, "Timestamp": timestamp, "Processed": False}
+
             df = pd.concat([df, pd.DataFrame([new_entry])], ignore_index=True)
+
             updated_ds = Dataset.from_pandas(df)
+
             updated_ds.push_to_hub(HF_DATASET_REPO, token=HF_TOKEN)
+
     except Exception as e:
+
         print(f"Failed to save query: {e}")
 
+
+
 # Query Groq LLM
+
 def query_groq_llm(prompt, model_name="llama3-70b-8192"):
+
     try:
+
         chat_completion = groq_client.chat.completions.create(
+
             messages=[{
+
                 "role": "user",
+
                 "content": prompt
+
             }],
+
             model=model_name,
+
             temperature=0.7,
+
             max_tokens=500
+
         )
+
         return chat_completion.choices[0].message.content.strip()
+
     except Exception as e:
+
         print(f"Error querying Groq API: {e}")
+
         return ""
 
-# Main logic function
+
+
+# Main logic function to be called from Gradio
+
 def get_best_answer(user_input):
+
     if not user_input.strip():
+
         return "Please enter a valid question."
-        
+
+
+
     user_input_lower = user_input.lower().strip()
 
-    # 👉 Check if question is about fee
-    if any(keyword in user_input_lower for keyword in ["fee", "fees", "charges", "semester fee"]):
+
+
+    if len(user_input_lower.split()) < 3 and not any(greet in user_input_lower for greet in GREETINGS):
+
+        return "Please ask your question properly with at least 3 words."
+
+
+
+    if any(keyword in user_input_lower for keyword in ["fee structure", "fees structure", "semester fees", "semester fee"]):
+
         return (
+
             "💰 For complete and up-to-date fee details for this program, we recommend visiting the official University of Education fee structure page.\n"
-            "You’ll find comprehensive information regarding tuition, admission charges, and other applicable fees there.\n"
+
+            "You'll find comprehensive information regarding tuition, admission charges, and other applicable fees there.\n"
+
             "🔗 https://ue.edu.pk/allfeestructure.php"
+
         )
 
-    # 🔁 Continue with normal similarity-based logic
-    if dataset_embeddings is None:
-        return "I am currently updating my database. Please try again in a moment."
+
 
     user_embedding = similarity_model.encode(user_input_lower, convert_to_tensor=True)
+
     similarities = util.pytorch_cos_sim(user_embedding, dataset_embeddings)[0]
+
     best_match_idx = similarities.argmax().item()
+
     best_score = similarities[best_match_idx].item()
 
+
+
     if best_score < 0.65:
+
         manage_unmatched_queries(user_input)
 
-    if best_score >= 0.65:
-        original_answer = dataset_answers[best_match_idx]
-        prompt = f"""As an official assistant for University of Education Lahore, provide a clear response:
-        Question: {user_input}
-        Original Answer: {original_answer}
-        Improved Answer:"""
-    else:
-        prompt = f"""As an official assistant for University of Education Lahore, provide a helpful response:
-        Include relevant details about university policies.
-        If unsure, direct to official channels.
-        Question: {user_input}
-        Official Answer:"""
+        return random.choice(UNMATCHED_RESPONSES)
+
+
+
+    original_answer = dataset_answers[best_match_idx]
+
+    prompt = f"""Name is UOE AI Assistant! You are an official assistant for the University of Education Lahore.
+
+Rephrase the following official answer clearly and professionally. 
+
+Use structured formatting (like headings, bullet points, or numbered lists) where appropriate.
+
+DO NOT add any new or extra information. ONLY rephrase and improve the clarity and formatting of the original answer.
+
+### Question:
+
+{user_input}
+
+### Original Answer:
+
+{original_answer}
+
+### Rephrased Answer:
+
+"""
+
+
 
     llm_response = query_groq_llm(prompt)
 
+
+
     if llm_response:
-        for marker in ["Improved Answer:", "Official Answer:"]:
+
+        for marker in ["Improved Answer:", "Official Answer:", "Rephrased Answer:"]:
+
             if marker in llm_response:
-                response = llm_response.split(marker)[-1].strip()
-                break
-        else:
-            response = llm_response
+
+                return llm_response.split(marker)[-1].strip()
+
+        return llm_response
+
     else:
-        response = dataset_answers[best_match_idx] if best_score >= 0.65 else """For official information:
-        📞 +92-42-99262231-33
-        ✉️ info@ue.edu.pk
-        🌐 ue.edu.pk"""
 
-    return response
+        return dataset_answers[best_match_idx]
+