Fix imports

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 import pandas as pd
 from key_info import extract_entities
 from summarization_with_bart import summarize_email_conditional
-from llama2_response_mail_generator import generate_email_response
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
 import torch
 from huggingface_hub import hf_hub_download

llama2_response_mail_generator.py

@@ -2,20 +2,6 @@ from huggingface_hub import hf_hub_download
 
 from llama_cpp import Llama
 
-model_name_or_path = "TheBloke/Llama-2-13B-chat-GGML"
-model_basename = "llama-2-13b-chat.ggmlv3.q5_1.bin"  # The model is in bin format
-
-# Download the model file
-model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
-
-# Initialize the Llama model with appropriate settings for GPU
-lcpp_llm = Llama(
-    model_path=model_path,
-    n_threads=2,  # CPU cores to use
-    n_batch=512,  # Batch size for processing; adjust as per your VRAM capacity
-    n_gpu_layers=32  # Number of layers to run on GPU, dependent on your GPU's VRAM
-)
-
 def generate_email_response(email_prompt):
     # Check input received by the function
     print("Received prompt:", email_prompt)