app

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+from time import time
+from pathlib import Path
+from gradio_pdf import PDF
+from pdf2image import convert_from_path
+import shutil
+import tempfile
+from transformers import pipeline
+
+out_files = gr.State([])
+FILE_TIMEOUT = 10 ** 0
+MAX_FILES = 10
+
+p = pipeline(
+    "document-question-answering",
+    model="impira/layoutlm-document-qa",
+)
+
+def handle_files(cur_files):
+    cur_time = cur_files[-1][0]
+    deleted_indices = set()
+    for other_idx, (other_time, other_file) in enumerate(cur_files[:-1]):
+        if abs(cur_time - other_time) > FILE_TIMEOUT:
+            shutil.rmtree(other_file.parent)
+            deleted_indices.add(other_idx)
+    cur_files = [cur_files[idx] for idx in range(len(cur_files)) if idx not in deleted_indices]
+    
+    if len(cur_files) > MAX_FILES:
+        for _, other_file in cur_files[:-MAX_FILES]:
+            shutil.rmtree(other_file.parent)
+        cur_files = cur_files[-MAX_FILES:]
+    return cur_files
+
+# Function to process PDF and generate ZIP file
+def process_pdf(pdf_file, cur_files):
+    
+    zip_output = Path(tempfile.mkdtemp()) / f'{Path(pdf_file).stem}'
+    # zip_output.parent.mkdir()
+    
+    with tempfile.TemporaryDirectory() as path:
+        pdf_output = path
+        convert_from_path(pdf_file, output_folder=str(pdf_output))
+    
+        # Create a BytesIO object to store zip file in memory
+        shutil.make_archive(zip_output, 'zip', pdf_output)
+    
+    zip_output = zip_output.with_suffix('.zip')
+    
+    cur_time = time()
+    cur_files.append((cur_time, zip_output))
+    cur_files = handle_files(cur_files)
+    
+    return str(zip_output), cur_files
+
+# Function to process image and text query
+def process_image_and_text(doc, text_query):
+    images = convert_from_path(doc)
+    outputs = []
+    for img in images:
+        outputs += p(img, question)
+    return sorted(outputs, key=lambda x: x["score"], reverse=True)[0]['answer']
+
+# Interface for the Gradio app
+pdf_interface = gr.Interface(
+    fn=process_pdf,
+    inputs=[PDF(label="Upload PDF"), out_files],
+    outputs=[gr.File(label="Download ZIP"), out_files],
+    title="PDF to Image Converter",
+    description="Converts PDF pages to images and outputs a ZIP file."
+)
+
+image_interface = gr.Interface(
+    fn=process_image_and_text,
+    inputs=[
+        gr.Image(label="Upload Image"),
+        gr.Textbox(label="Text Query")
+    ],
+    outputs="text",
+    title="Image Text Search",
+    description="Searches for text in the uploaded image based on the provided query."
+)
+
+# Create a tabbed interface
+tabbed_interface = gr.TabbedInterface(
+    [pdf_interface, image_interface],
+    title="PDF interaction",
+    tab_names=["Converter", "Interaction"],
+    # description="Choose a tab to perform the desired task."
+)
+
+# Launch the app
+tabbed_interface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+gradio_pdf
+transformers