Update rag.py

rag.py

@@ -1,16 +1,9 @@
 import json
 from sentence_transformers import SentenceTransformer, util
 from groq import Groq
-import datetime
-import requests
-from io import BytesIO
-from PIL import Image, ImageDraw, ImageFont
-import numpy as np
-from dotenv import load_dotenv
 import os
-import pandas as pd
 import csv
-import os
+from dotenv import load_dotenv
 
 # Load environment variables
 load_dotenv()
@@ -18,11 +11,11 @@ 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')
 
 # Load dataset
-with open('dataset.json', 'r') as f:
+with open('dataset.json', 'r', encoding='utf-8') as f:
     dataset = json.load(f)
 
 # Precompute embeddings
@@ -30,6 +23,11 @@ dataset_questions = [item.get("input", "").lower().strip() for item in dataset]
 dataset_answers = [item.get("response", "") for item in dataset]
 dataset_embeddings = similarity_model.encode(dataset_questions, convert_to_tensor=True)
 
+# Use absolute path for unmatched_queries.csv
+base_dir = os.path.dirname(os.path.abspath(__file__))
+file_path = os.path.join(base_dir, "unmatched_queries.csv")
+print(f"[DEBUG] Writing to absolute path: {file_path}")
+
 def query_groq_llm(prompt, model_name="llama3-70b-8192"):
     try:
         chat_completion = groq_client.chat.completions.create(
@@ -63,12 +61,11 @@ def get_best_answer(user_input):
     best_match_idx = similarities.argmax().item()
     best_score = similarities[best_match_idx].item()
 
-    # ✏️ If not matched well, log to CSV
+    # ✏️ Log to CSV if similarity is low
     if best_score < 0.65:
-        file_path = "unmatched_queries.csv"
         print(f"[DEBUG] Similarity score too low: {best_score}. Logging query to: {file_path}")
 
-        # Check if file exists
+        # Create CSV with header if it doesn't exist
         if not os.path.exists(file_path):
             print(f"[DEBUG] File {file_path} does not exist. Creating file with header.")
             try:
@@ -79,6 +76,7 @@ def get_best_answer(user_input):
             except Exception as e:
                 print(f"[ERROR] Failed to create file: {e}")
 
+        # Append unmatched query
         try:
             with open(file_path, mode="a", newline="", encoding="utf-8") as file:
                 writer = csv.writer(file)
@@ -87,7 +85,7 @@ def get_best_answer(user_input):
         except Exception as e:
             print(f"[ERROR] Failed to write query to CSV: {e}")
 
-    # 🧠 Prompt construction
+    # 🧠 Construct prompt
     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: