Update rag.py

rag.py

@@ -1,3 +1,48 @@
+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
+
+# Load environment variables
+load_dotenv()
+
+# Initialize Groq client
+groq_client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+
+# Load models and dataset
+similarity_model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+
+# Load dataset (automatically using the path)
+with open('dataset.json', 'r') as f:
+    dataset = json.load(f)
+
+# Precompute embeddings
+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)
+
+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 ""
+
 def get_best_answer(user_input):
     user_input_lower = user_input.lower().strip()