Update app.py

app.py

@@ -1,6 +1,5 @@
 import inspect
 from tqdm import tqdm
-from langchain_huggingface import HuggingFacePipeline,ChatHuggingFace
 path_hf=inspect.getfile(HuggingFacePipeline)
 from subprocess import Popen, PIPE as P
 from langchain_experimental.tools.python.tool import PythonREPLTool as PYT
@@ -87,8 +86,21 @@ else:
 #m=M.from_pretrained("peterpeter8585/syai4.3")
 #t=T.from_pretrained("peterpeter8585/syai4.3")
 #pipe=pipeline(model=m,tokenizer=t,task="text-generation")
-from langchain_community.llms import GPT4ALL
-llm=GPT4ALL(model="./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf")
+import multiprocessing
+
+from langchain_community.chat_models import ChatLlamaCpp
+
+llm = ChatLlamaCpp(
+    temperature=0,
+    model_path="./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf",
+    n_ctx=10000,
+    n_gpu_layers=8,
+    n_batch=300,  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
+    max_tokens=512,
+    n_threads=multiprocessing.cpu_count() - 1,
+    repeat_penalty=1.5,
+    top_p=0.5,
+)
 from langchain.retrievers import WikipediaRetriever as Wiki
 import gradio as gr
 chatbot = gr.Chatbot(