Update app.py

app.py

@@ -263,7 +263,7 @@ def simple_chat(message: dict, temperature: float = 0.8, max_length: int = 4096,
         print("  ")
         print("------")
         print("  ")
-        print(results_text)
+        print(generated_text)
         print("  ")
         print("------")
 
@@ -345,69 +345,6 @@ def simple_chat(message: dict, temperature: float = 0.8, max_length: int = 4096,
 #         return PlainTextResponse(f"Error: {str(e)}")
 
 
-        
-# def simple_chat(message: dict, temperature: float = 0.8, max_length: int = 4096, top_p: float = 1, top_k: int = 10, penalty: float = 1.0):
-#     try:
-#         model = AutoModelForCausalLM.from_pretrained(
-#             MODEL_ID,
-#             torch_dtype=torch.bfloat16,
-#             low_cpu_mem_usage=True,
-#             trust_remote_code=True
-#         )
-        
-#         tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
-
-#         conversation = []
-
-#         # Acceder al contenido del archivo y al nombre del archivo
-#         if "file_content" in message and message["file_content"]:
-#             file_content = message["file_content"]
-#             file_name = message["file_name"]
-            
-#             # Guardar el archivo en un archivo temporal
-#             with open(file_name, "wb") as f:
-#                 f.write(file_content.read())
-            
-#             # Llamar a `mode_load` con el nombre del archivo
-#             choice, contents = mode_load(file_name)
-            
-#             if choice == "image":
-#                 conversation.append({"role": "user", "image": contents, "content": message['text']})
-#             elif choice == "doc":
-#                 format_msg = contents + "\n\n\n" + "{} files uploaded.\n".format(1) + message['text']
-#                 conversation.append({"role": "user", "content": format_msg})
-#         else:
-#             # Manejar caso donde no se sube archivo
-#             conversation.append({"role": "user", "content": message['text']})
-
-#         print("--------------")
-#         print("  ")
-#         print(conversation)
-#         print("  ")
-#         print("--------------")
-
-#         input_ids = tokenizer.apply_chat_template(conversation, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
-
-#         generate_kwargs = dict(
-#             max_length=max_length,
-#             do_sample=True,
-#             top_p=top_p,
-#             top_k=top_k,
-#             temperature=temperature,
-#             repetition_penalty=penalty,
-#             eos_token_id=[151329, 151336, 151338],
-#         )
-
-#         with torch.no_grad():
-#             generated_ids = model.generate(input_ids['input_ids'], **generate_kwargs)
-#             generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
-
-
-#         return PlainTextResponse(generated_text)
-#     except Exception as e:
-#         return PlainTextResponse(f"Error: {str(e)}")
-
-
 
 @app.post("/chat/")
 async def test_endpoint(