Update rag.py

rag.py

@@ -3,6 +3,7 @@ import os
 import requests
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
+from openai import OpenAI
 
 
 from langchain_community.vectorstores import FAISS
@@ -103,7 +104,7 @@ class RAG:
     def predict_completion(self, instruction, context, model_parameters):
 
         client = OpenAI(
-                base_url=ENDPOINT_URL,
+                base_url=MODEL,
                 api_key=os.getenv("HF_TOKEN")
             )