Update app.py

app.py

@@ -1,23 +1,25 @@
-import PyPDF2
 from pprint import pprint
-from getpass import getpass
-from haystack import Pipeline
-from haystack.schema import Document
+from haystack import Document, Pipeline
 from haystack.nodes import BM25Retriever
 from haystack.document_stores import InMemoryDocumentStore
 from haystack.nodes import PromptTemplate, PromptNode
+from PyPDF2 import PdfReader
 import gradio as gr
 import os
 
-HF_TOKEN = getpass("Enter Token")
-from huggingface_hub import notebook_login
-notebook_login()
+# Function to read PDF file content directly
+def read_pdf(pdf_path):
+    content = ""
+    reader = PdfReader(pdf_path)
+    for page in reader.pages:
+        content += page.extract_text()
+    return content
 
 # Process and retrieve answers
 def process_invoice(file, hf_token, questions):
-    # Read file content
-    file_content = file.read()
-    document = Document(content=file_content)
+    # Read the PDF content directly
+    pdf_content = read_pdf(file.name)
+    document = Document(content=pdf_content)
     docs = [document]
 
     document_store = InMemoryDocumentStore(use_bm25=True)
@@ -60,13 +62,13 @@ def gradio_interface(file, hf_token, questions):
 interface = gr.Interface(
     fn=gradio_interface,
     inputs=[
-        gr.inputs.File(file_count="single", type="file", label="Upload Invoice (PDF or Image)"),
+        gr.inputs.File(file_count="single", type="file", label="Upload Invoice (PDF)"),
         gr.inputs.Textbox(type="password", label="Enter your Hugging Face Token"),
         gr.inputs.Textbox(lines=5, placeholder="Enter your questions separated by commas")
     ],
     outputs="json",
     title="Invoice Data Extraction",
-    description="Upload an invoice PDF or image, provide your Hugging Face token, and get the extracted data based on your questions."
+    description="Upload an invoice PDF, provide your Hugging Face token, and get the extracted data based on your questions."
 )
 
 if __name__ == "__main__":