Update app.py

app.py

@@ -21,10 +21,10 @@ from huggingface_hub import hf_hub_download
 model_name_or_path = "hlhr202/llama-7B-ggml-int4"
 model_basename = "ggml-model-q4_0.bin" # the model is in bin format
 
-model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
+#model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
 
 n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool.
-n_batch = 256 
+n_batch = 256
 
 
 embed_model = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl",
@@ -39,25 +39,24 @@ prompt_helper = PromptHelper(
 )
 """
 from langchain_g4f import G4FLLM
-
-async def main(question):
-    llm : LLM = G4FLLM(
+llm = LLM = G4FLLM(
         model=models.gpt_35_turbo,
-        provider=Provider.Acytoo,
-    )
+        provider=Provider.Acytoo,)
     
 
-    llm = LangChainLLM(llm=llm)
+llm = LangChainLLM(llm=llm)
     
-    service_context = ServiceContext.from_defaults(llm=llm,
+service_context = ServiceContext.from_defaults(llm=llm,
   embed_model=embed_model)
 
-    documents = SimpleDirectoryReader("data/").load_data()
-    index = VectorStoreIndex.from_documents(documents, service_context=service_context)
+documents = SimpleDirectoryReader("data").load_data()
+index = VectorStoreIndex.from_documents(documents, service_context=service_context)
+  
+async def main(question):
     query_engine = index.as_query_engine(service_context=service_context)
     response = query_engine.query(question)
     print(response)
     return response
 
 iface = Interface(fn=main, inputs="text", outputs="text")
-iface.launch()
+iface.launch()