Update requirements.txt

app.py

@@ -18,7 +18,7 @@ llm = LlamaCPP(
     generate_kwargs={},
     # set to at least 1 to use GPU
     # This is small model and there's no indication of layers offloaded to the GPU
-    model_kwargs={"n_gpu_layers": 0},
+    model_kwargs={"n_gpu_layers": 32},
     messages_to_prompt=messages_to_prompt,
     completion_to_prompt=completion_to_prompt,
     verbose=True

requirements.txt

@@ -3,4 +3,4 @@ llama-index
 langchain
 PyPDF2
 sentence_transformers
-llama_cpp
+llama-cpp-python