Update app.py

app.py

@@ -6,6 +6,7 @@ from transformers import AutoTokenizer, AutoModel
 import torch
 from pdf2image import convert_from_path
 import io
+from io import BytesIO
 
 # CSS styles
 css = """
@@ -64,14 +65,12 @@ def get_text_embeddings(text, model_name='bert-base-uncased'):
 # Function to process PDF and generate a response
 def process_pdf_and_generate_response(pdf_file):
  try:
- # Save the uploaded PDF to a temporary file
- tmp_pdf_path = "/tmp/uploaded_file.pdf"
- with open(tmp_pdf_path, 'wb') as tmp_pdf:
- tmp_pdf.write(pdf_file.read())
+ # Convert the binary stream to a file-like object
+ pdf_file_stream = BytesIO(pdf_file)
 
  # Convert PDF to images
  img_dir = "pdf_images"
- pdf_to_images(tmp_pdf_path, img_dir)
+ pdf_to_images(pdf_file_stream, img_dir)
 
  # Generate embeddings for each image
  image_embeddings = []
@@ -93,7 +92,7 @@ def process_pdf_and_generate_response(pdf_file):
 
 iface = gr.Interface(
  fn=process_pdf_and_generate_response,
- inputs=gr.File(label="Upload PDF", type="file"),
+ inputs=gr.File(label="Upload PDF", type="binary"), # Changed 'file' to 'binary'
  outputs=gr.Textbox("Placeholder for PDF insights", label="Insights", type="text"),
  title="pdf-chatbot",
  description="Upload a PDF and receive insights based on its content.",