Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+from langchain.llms import LlamaCpp
 from langchain import PromptTemplate, LLMChain
 from langchain.llms import GPT4All
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
@@ -33,7 +34,7 @@ def func(user):
     # callbacks = [StreamingStdOutCallbackHandler()]
     
     # Verbose is required to pass to the callback manager
-    llm = GPT4All(model="./nous-hermes-13b.ggmlv3.q4_0.bin", n_ctx=5000)
+    llm = LlamaCpp(model_path="./nous-hermes-13b.ggmlv3.q4_0.bin", n_ctx=2048)
     llm_chain = LLMChain(prompt=prompt, llm=llm)
     question = user
     llm_chain.run(question)