Update app.py

app.py

@@ -71,7 +71,7 @@ with gr.Blocks(title="PDF data extraction with Marker & Indexify") as marker_dem
 	gr.HTML("<h1 style='text-align: center'>PDF data extraction with Marker & <a href='https://getindexify.ai/'>Indexify</a></h1>")
 	gr.HTML("<p style='text-align: center'>Indexify is a scalable realtime and continuous indexing and structured extraction engine for unstructured data to build generative AI applications</p>")
 	gr.HTML("<h3 style='text-align: center'>If you like this demo, please ⭐ Star us on <a href='https://github.com/tensorlakeai/indexify' target='_blank'>GitHub</a>!</h3>")
-	gr.HTML("<h4 style='text-align: center'>Here's an example notebook that demonstrates how to build a continous <a href='https://github.com/tensorlakeai/indexify/blob/main/docs/docs/examples/SEC_10_K_docs.ipynb' target='_blank'>extraction pipleine</a> with Indexify</h4>")
+	gr.HTML("<h4 style='text-align: center'>Here's an example notebook that demonstrates how to build a continous <a href='https://github.com/tensorlakeai/indexify/blob/main/docs/docs/examples/efficient_rag.ipynb' target='_blank'>extraction pipleine</a> with Indexify</h4>")
 
 	with gr.Row():
 		with gr.Column():
@@ -113,6 +113,52 @@ with gr.Blocks(title="PDF data extraction with Marker & Indexify") as marker_dem
 		outputs = [model_output_text_box]
 	)
 
+with gr.Blocks(title="PDF data extraction with PDF Extractor & Indexify") as pdf_demo:
+	gr.HTML("<h1 style='text-align: center'>PDF data extraction with PDF Extractor & <a href='https://getindexify.ai/'>Indexify</a></h1>")
+	gr.HTML("<p style='text-align: center'>Indexify is a scalable realtime and continuous indexing and structured extraction engine for unstructured data to build generative AI applications</p>")
+	gr.HTML("<h3 style='text-align: center'>If you like this demo, please ⭐ Star us on <a href='https://github.com/tensorlakeai/indexify' target='_blank'>GitHub</a>!</h3>")
+	gr.HTML("<h4 style='text-align: center'>Here's an example notebook that demonstrates how to build a continous <a href='https://github.com/tensorlakeai/indexify/blob/main/docs/docs/examples/SEC_10_K_docs.ipynb' target='_blank'>extraction pipleine</a> with Indexify</h4>")
+
+	with gr.Row():
+		with gr.Column():
+			gr.HTML(
+				"<p><b>Step 1:</b> Upload a PDF file from local storage.</p>"
+
+				"<p style='color: #A0A0A0;'>Use this demo for single PDF file only. "
+				"You can extract from PDF files continuously and try various other extractors locally with "
+				"<a href='https://getindexify.ai/'>Indexify</a>.</p>"
+			)
+
+			pdf_file = gr.File(type="filepath")
+
+		with gr.Column():
+			gr.HTML("<p><b>Step 2:</b> Run the extractor.</p>")
+
+			go_button = gr.Button(
+				value="Run extractor",
+				variant="primary",
+			)
+
+			model_output_text_box = gr.Textbox(
+				label="Extractor Output",
+				elem_id="model_output_text_box",
+			)
+
+	with gr.Row():
+
+		gr.HTML(
+			"<p style='text-align: center'>"
+				"Developed with 🫶 by <a href='https://getindexify.ai/' target='_blank'>Indexify</a> | "
+				"a <a href='https://www.tensorlake.ai/' target='_blank'>Tensorlake</a> product"
+			"</p>"
+		)
+
+	go_button.click(
+		fn=use_pdf_extractor, 
+		inputs = [pdf_file],
+		outputs = [model_output_text_box]
+	)
+
 demo = gr.TabbedInterface([marker_demo, pdf_demo, gemini_demo, openai_demo], ["Marker Extractor", "PDF Extractor", "Gemini Extractor", "OpenAI Extractor"], theme=gr.themes.Soft())
 
 demo.queue()