Update app.py

app.py

@@ -1,30 +1,3 @@
-import gradio as gr
-from PyPDF2 import PdfReader
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-
-# Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("himmeow/vi-gemma-2b-RAG")
-model = AutoModelForCausalLM.from_pretrained(
-    "himmeow/vi-gemma-2b-RAG",
-    device_map="auto",
-    torch_dtype=torch.bfloat16
-)
-
-if torch.cuda.is_available():
-    model.to("cuda")
-
-# Define the prompt format for the model
-prompt = """
-### Instruction and Input:
-Based on the following context/document:
-{}
-Please answer the question: {}
-
-### Response:
-{}
-"""
-
 def extract_text_from_pdf(pdf):
     pdf_Text = ""
     reader = PdfReader(pdf)
@@ -32,30 +5,5 @@ def extract_text_from_pdf(pdf):
         page = reader.pages[page_num]
         text = page.extract_text()
         pdf_Text += text + "\n"
+    print("Extracted Text:\n", pdf_Text)  # Add this line to debug
     return pdf_Text
-
-def generate_response(pdf, query):
-    pdf_Text = extract_text_from_pdf(pdf)
-    input_text = prompt.format(pdf_Text, query, " ")
-    input_ids = tokenizer(input_text, return_tensors="pt")
-
-    if torch.cuda.is_available():
-        input_ids = input_ids.to("cuda")
-
-    outputs = model.generate(
-        **input_ids,
-        max_new_tokens=500,  # Limit the number of tokens generated
-        no_repeat_ngram_size=5,  # Prevent repetition of 5-gram phrases
-    )
-    return tokenizer.decode(outputs[0])
-
-# Gradio interface
-iface = gr.Interface(
-    fn=generate_response,
-    inputs=[gr.File(label="Upload PDF"), gr.Textbox(label="Ask a question")],
-    outputs="text",
-    title="PDF Question Answering with vi-gemma-2b-RAG",
-    description="Upload a PDF and ask a question based on its content. The model will generate a response."
-)
-
-iface.launch()