Update rag.py

rag.py

@@ -8,8 +8,6 @@ from PIL import Image, ImageDraw, ImageFont
 import numpy as np
 from dotenv import load_dotenv
 import os
-import pandas as pd
-from datasets import load_dataset, Dataset
 
 # Load environment variables
 load_dotenv()
@@ -29,34 +27,6 @@ dataset_questions = [item.get("Question", "").lower().strip() for item in datase
 dataset_answers = [item.get("Answer", "") for item in dataset]
 dataset_embeddings = similarity_model.encode(dataset_questions, convert_to_tensor=True)
 
-# Greeting list
-GREETINGS = [
-    "hi", "hello", "hey", "good morning", "good afternoon", "good evening",
-    "assalam o alaikum", "salam", "aoa", "hi there",
-    "hey there", "greetings"
-]
-
-# Hugging Face config
-HF_DATASET_REPO = "midrees2806/unmatched_queries"
-HF_TOKEN = os.getenv("HF_TOKEN")
-
-# Save unmatched queries to Hugging Face
-def manage_unmatched_queries(query: str):
-    try:
-        timestamp = datetime.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}")
-
 def query_groq_llm(prompt, model_name="llama3-70b-8192"):
     try:
         chat_completion = groq_client.chat.completions.create(
@@ -76,16 +46,8 @@ def query_groq_llm(prompt, model_name="llama3-70b-8192"):
 def get_best_answer(user_input):
     user_input_lower = user_input.lower().strip()
 
-    # 👉 Greeting functionality
-    if any(greet in user_input_lower for greet in GREETINGS):
-        greeting_response = query_groq_llm(
-            f"You are an official assistant for University of Education Lahore. "
-            f"Respond to this greeting in a friendly and professional manner: {user_input}"
-        )
-        return greeting_response if greeting_response else "Hello! How can I assist you today?"
-
     # 👉 Check if question is about fee
-    if any(keyword in user_input_lower for keyword in ["semester fee", "semester fees"]):
+    if any(keyword in user_input_lower for keyword in ["fee", "fees", "charges", "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"
@@ -98,10 +60,6 @@ def get_best_answer(user_input):
     best_match_idx = similarities.argmax().item()
     best_score = similarities[best_match_idx].item()
 
-    # 👉 Save unmatched query if no close match
-    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: