Update app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 import torch
-from transformers import VisionEncoderDecoderModel, AutoTokenizer, pipeline
+from transformers import AutoTokenizer, pipeline
 from pdf2image import convert_from_path
 import pytesseract
 from PIL import Image
@@ -9,12 +9,9 @@ import io
 from typing import List, Tuple
 
 # Initialize models and tokenizer
-vision_model_name = "nlpconnect/vit-gpt2-image-captioning"
 text_model_name = "peteparker456/medical_diagnosis_llama2"
 
 # Load the vision and text models
-vision_model = VisionEncoderDecoderModel.from_pretrained(vision_model_name)
-vision_tokenizer = AutoTokenizer.from_pretrained(vision_model_name)
 text_model = pipeline("text-generation", model=text_model_name)
 
 pytesseract.pytesseract.tesseract_cmd = r'/usr/bin/tesseract'  # Path to Tesseract executable
@@ -43,7 +40,6 @@ def extract_text_from_pdf(pdf_path: str) -> str:
 def generate_insights(text: str) -> List[Tuple[str, str]]:
     """Get interpretations and recommendations from the text."""
     # Create a dummy input for the text model
-    inputs = vision_tokenizer.encode(text, return_tensors="pt", max_length=1000, truncation=True)
     output_text = text_model(text, max_length=1000)[0]["generated_text"]
 
     return [