Update app.py

app.py

@@ -1,11 +1,6 @@
 
 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)
-
 n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool.
 n_batch = 256 
 
@@ -24,12 +19,19 @@ from langchain_g4f import G4FLLM
 # Make sure the model path is correct for your system!
 llm = LLM = G4FLLM(
         model=models.gpt_35_turbo,
-        provider=Provider.DeepAi,
+        provider=Provider.Aichat,
     )
     
-
-embeddings = LlamaCppEmbeddings(model_path=model_path )
-
+from langchain.embeddings import HuggingFaceEmbeddings
+
+model_name = "sentence-transformers/all-mpnet-base-v2"
+model_kwargs = {'device': 'cpu'}
+encode_kwargs = {'normalize_embeddings': False}
+embeddings = HuggingFaceEmbeddings(
+    model_name=model_name,
+    model_kwargs=model_kwargs,
+    encode_kwargs=encode_kwargs
+)
 docs = Docs(llm=llm, embeddings=embeddings)
 
 keyword_search = 'bispecific antibody manufacture'