Create app.py

app.py

@@ -0,0 +1,87 @@
+import spaces
+import gradio as gr
+from gemini.gemini_extractor import GeminiExtractorConfig, GeminiExtractor
+from oai.oai_extractor import OAIExtractorConfig, OAIExtractor
+from indexify_extractor_sdk import Content
+
+gemini_extractor = GeminiExtractor()
+oai_extractor = OAIExtractor()
+
+def use_gemini(pdf_filepath, key):
+	if pdf_filepath is None:
+		raise gr.Error("Please provide some input PDF: upload a PDF file")
+	with open(pdf_filepath, "rb") as f:
+		pdf_data = f.read()
+	content = Content(content_type="application/pdf", data=pdf_data)
+	config = GeminiExtractorConfig(prompt="Extract all text from the document.", model_name="gemini-1.5-flash", key=key)
+	result = gemini_extractor.extract(content, config)
+	return result
+
+with gr.Blocks(title="PDF data extraction with Gemini & Indexify") as gemini_demo:
+	gr.HTML("<h1 style='text-align: center'>PDF data extraction with Gemini & <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 continuous <a href='https://github.com/tensorlakeai/indexify/blob/main/docs/docs/examples/multimodal_gemini.ipynb' target='_blank'>extraction pipeline</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")
+			gr.HTML("<p><b>Step 2:</b> Enter your API key.</p>")
+			key = gr.Textbox(info="Please enter your GEMINI_API_KEY", label="Key:")
+		with gr.Column():
+			gr.HTML("<p><b>Step 3:</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_gemini, inputs=[pdf_file, key], outputs=[model_output_text_box])
+
+def use_openai(pdf_filepath, key):
+	if pdf_filepath is None:
+		raise gr.Error("Please provide some input PDF: upload a PDF file")
+	with open(pdf_filepath, "rb") as f:
+		pdf_data = f.read()
+	content = Content(content_type="application/pdf", data=pdf_data)
+	config = OAIExtractorConfig(prompt="Extract all text from the document.", model_name="gpt-4o", key=key)
+	result = oai_extractor.extract(content, config)
+	return result
+
+with gr.Blocks(title="PDF data extraction with OpenAI & Indexify") as openai_demo:
+	gr.HTML("<h1 style='text-align: center'>PDF data extraction with OpenAI & <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 continuous <a href='https://github.com/tensorlakeai/indexify/blob/main/docs/docs/examples/multimodal_openai.ipynb' target='_blank'>extraction pipeline</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")
+			gr.HTML("<p><b>Step 2:</b> Enter your API key.</p>")
+			key = gr.Textbox(info="Please enter your OPENAI_API_KEY", label="Key:")
+		with gr.Column():
+			gr.HTML("<p><b>Step 3:</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_openai, inputs=[pdf_file, key], outputs=[model_output_text_box])
+
+demo = gr.TabbedInterface([gemini_demo, openai_demo], ["Gemini Extractor", "OpenAI Extractor"], theme=gr.themes.Soft())
+
+demo.queue()
+demo.launch()