add app

app.py

@@ -0,0 +1,54 @@
+import streamlit as st
+from transformers import pipeline
+from PyPDF2 import PdfReader
+import docx
+
+# Initialize the NLP pipeline
+nlp = pipeline(
+    "document-question-answering",
+    model="impira/layoutlm-document-qa",
+)
+
+# Set the title of the app
+st.title("LayoutLM Example")
+
+# Create a file uploader that accepts various document formats
+uploaded_file = st.file_uploader("Drag and drop a document here", type=['txt', 'pdf', 'docx'])
+
+# Create a text box for user input
+question = st.text_area("What would you like to know?")
+
+def extract_text_from_file(uploaded_file):
+    if uploaded_file.type == "text/plain":
+        return uploaded_file.read().decode("utf-8")
+    elif uploaded_file.type == "application/pdf":
+        reader = PdfReader(uploaded_file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
+        return text
+    elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+        doc = docx.Document(uploaded_file)
+        text = "\n".join([paragraph.text for paragraph in doc.paragraphs])
+        return text
+    else:
+        return None
+
+if uploaded_file and question:
+    # Extract text from the uploaded document
+    document_text = extract_text_from_file(uploaded_file)
+
+    if document_text:
+        # Run the NLP model on the extracted text and the user's question
+        answer = nlp(
+            {
+                "context": document_text,
+                "question": question
+            }
+        )
+
+        # Display the answer
+        st.write("Answer:")
+        st.write(answer['answer'])
+    else:
+        st.write("Unsupported file type or failed to extract text from the document.")