removed comments

app.py

@@ -3,12 +3,12 @@ import spaces
 import torch
 import os
 from huggingface_hub import snapshot_download
-from utils import read_file_pdf, fix_type, extract_content_in_pdf, doc_converter, EXTENSIONS_FILES, EXTENSIONS_IMG_FILES, MSG_NENHUM_ARQUIVO_ENVIADO, MSG_TEXTO_NAO_EXTRAIDO
+from utils import doc_converter, MSG_NENHUM_ARQUIVO_ENVIADO, MSG_TEXTO_NAO_EXTRAIDO
 from rag_utils import create_split_doc, store_docs, create_rag_chain
 import config
 
 zero = torch.Tensor([0]).cuda()
-print(zero.device) # <-- 'cpu' 🤔
+print(zero.device)
 
 MAX_FILE_SIZE = 10 * 1024 * 1024  # 10MB
 

rag_utils.py

@@ -5,11 +5,8 @@ from langchain.prompts import PromptTemplate
 
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 from langchain.llms import HuggingFacePipeline
-
-from langchain.chat_models import ChatOpenAI
 from langchain.chains import RetrievalQA
 
-import spaces
 import config
 import torch
 print(torch.cuda.is_available())
@@ -18,7 +15,6 @@ device = f'cuda:{torch.cuda.current_device()}' if torch.cuda.is_available() else
 
 import os
 os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "0"
-# cache_dir = "/home/user/.cache/huggingface" #"./model/qwen-awq" #"/home/felipe/.cache/huggingface/transformers" #"/home/user/.cache/huggingface"
 
 _embedding_instance = None
 _model_instance = None
@@ -32,9 +28,6 @@ def get_embedding_model():
         _embedding_instance = HuggingFaceEmbeddings(model_name=config.local_emb_path, model_kwargs={"device": "cpu"})
     return _embedding_instance
 
-# model_name = "Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8" #"Qwen/Qwen2.5-7B-Instruct-AWQ" #"Qwen/Qwen2.5-7B-Instruct"
-
-# @spaces.GPU
 def get_model():
     global _model_instance
     if _model_instance is None:
@@ -49,8 +42,6 @@ def get_model():
     
     return _model_instance
 
-# _model_instance.to(device)
-
 def get_tokenizer():
     global _tokenizer
     if _tokenizer is None:
@@ -66,7 +57,6 @@ def create_split_doc(raw_text):
 
     return docs
 
-# @spaces.GPU
 def store_docs(docs):
     embedding_model = get_embedding_model()
     vectorstore = FAISS.from_documents(docs, embedding_model)
@@ -90,7 +80,6 @@ Pergunta:
 )
     return prompt_template
 
-# @spaces.GPU
 def create_rag_chain(vectorstore):
     pipe = pipeline(
         "text-generation",