Update app.py

app.py

@@ -3,13 +3,11 @@ from pydantic import BaseModel
 from typing import List
 from transformers import AutoTokenizer, AutoModel
 import torch
-import os
 
 class EmbeddingModel:
     def __init__(self, model_name="intfloat/multilingual-e5-large"):
-        cache_dir = os.getenv("MODEL_CACHE_DIR", "./model_cache")
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name, cache_dir=cache_dir)
-        self.model = AutoModel.from_pretrained(model_name, cache_dir=cache_dir)
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModel.from_pretrained(model_name)
 
     def get_embedding(self, text):
         inputs = self.tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
@@ -52,4 +50,4 @@ async def create_embeddings(request: EmbeddingRequest):
             "total_tokens": sum(len(text.split()) for text in request.input)
         }
     )
-    return response
+    return response