Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -18,31 +18,6 @@ def use_marker(pdf_filepath):
|
|
| 18 |
result = markdown_extractor.extract(content, config)
|
| 19 |
return result
|
| 20 |
|
| 21 |
-
with gr.Blocks(title="PDF data extraction with Marker & Indexify") as marker_demo:
|
| 22 |
-
gr.HTML("<h1 style='text-align: center'>PDF data extraction with Marker & <a href='https://getindexify.ai/'>Indexify</a></h1>")
|
| 23 |
-
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>")
|
| 24 |
-
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>")
|
| 25 |
-
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/efficient_rag.ipynb' target='_blank'>extraction pipeline</a> with Indexify</h4>")
|
| 26 |
-
|
| 27 |
-
with gr.Row():
|
| 28 |
-
with gr.Column():
|
| 29 |
-
gr.HTML(
|
| 30 |
-
"<p><b>Step 1:</b> Upload a PDF file from local storage.</p>"
|
| 31 |
-
"<p style='color: #A0A0A0;'>Use this demo for single PDF file only. "
|
| 32 |
-
"You can extract from PDF files continuously and try various other extractors locally with "
|
| 33 |
-
"<a href='https://getindexify.ai/'>Indexify</a>.</p>"
|
| 34 |
-
)
|
| 35 |
-
pdf_file_1 = gr.File(type="filepath")
|
| 36 |
-
with gr.Column():
|
| 37 |
-
gr.HTML("<p><b>Step 2:</b> Run the extractor.</p>")
|
| 38 |
-
go_button_1 = gr.Button(value="Run Marker extractor", variant="primary")
|
| 39 |
-
model_output_text_box_1 = gr.Textbox(label="Extractor Output", elem_id="model_output_text_box_1")
|
| 40 |
-
|
| 41 |
-
with gr.Row():
|
| 42 |
-
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>")
|
| 43 |
-
|
| 44 |
-
go_button_1.click(fn=use_marker, inputs=[pdf_file_1], outputs=[model_output_text_box_1])
|
| 45 |
-
|
| 46 |
@spaces.GPU
|
| 47 |
def use_pdf_extractor(pdf_filepath):
|
| 48 |
if pdf_filepath is None:
|
|
@@ -54,32 +29,56 @@ def use_pdf_extractor(pdf_filepath):
|
|
| 54 |
result = pdf_extractor.extract(content, config)
|
| 55 |
return result
|
| 56 |
|
| 57 |
-
with gr.Blocks(
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
|
|
|
| 81 |
|
| 82 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
|
| 84 |
demo.queue()
|
| 85 |
demo.launch()
|
|
|
|
| 18 |
result = markdown_extractor.extract(content, config)
|
| 19 |
return result
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
@spaces.GPU
|
| 22 |
def use_pdf_extractor(pdf_filepath):
|
| 23 |
if pdf_filepath is None:
|
|
|
|
| 29 |
result = pdf_extractor.extract(content, config)
|
| 30 |
return result
|
| 31 |
|
| 32 |
+
with gr.Blocks(theme=gr.themes.Soft()) as demo:
|
| 33 |
+
with gr.Tab("PDF data extraction with Marker & Indexify"):
|
| 34 |
+
gr.HTML("<h1 style='text-align: center'>PDF data extraction with Marker & <a href='https://getindexify.ai/'>Indexify</a></h1>")
|
| 35 |
+
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>")
|
| 36 |
+
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>")
|
| 37 |
+
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/efficient_rag.ipynb' target='_blank'>extraction pipeline</a> with Indexify</h4>")
|
| 38 |
+
|
| 39 |
+
with gr.Row():
|
| 40 |
+
with gr.Column():
|
| 41 |
+
gr.HTML(
|
| 42 |
+
"<p><b>Step 1:</b> Upload a PDF file from local storage.</p>"
|
| 43 |
+
"<p style='color: #A0A0A0;'>Use this demo for single PDF file only. "
|
| 44 |
+
"You can extract from PDF files continuously and try various other extractors locally with "
|
| 45 |
+
"<a href='https://getindexify.ai/'>Indexify</a>.</p>"
|
| 46 |
+
)
|
| 47 |
+
pdf_file_1 = gr.File(type="filepath")
|
| 48 |
+
with gr.Column():
|
| 49 |
+
gr.HTML("<p><b>Step 2:</b> Run the extractor.</p>")
|
| 50 |
+
go_button_1 = gr.Button(value="Run Marker extractor", variant="primary")
|
| 51 |
+
model_output_text_box_1 = gr.Textbox(label="Extractor Output", elem_id="model_output_text_box_1")
|
| 52 |
+
|
| 53 |
+
with gr.Row():
|
| 54 |
+
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>")
|
| 55 |
+
|
| 56 |
+
go_button_1.click(fn=use_marker, inputs=[pdf_file_1], outputs=[model_output_text_box_1])
|
| 57 |
|
| 58 |
+
with gr.Tab("PDF data extraction with PDF Extractor & Indexify"):
|
| 59 |
+
gr.HTML("<h1 style='text-align: center'>PDF data extraction with PDF Extractor & <a href='https://getindexify.ai/'>Indexify</a></h1>")
|
| 60 |
+
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>")
|
| 61 |
+
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>")
|
| 62 |
+
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/SEC_10_K_docs.ipynb' target='_blank'>extraction pipeline</a> with Indexify</h4>")
|
| 63 |
+
|
| 64 |
+
with gr.Row():
|
| 65 |
+
with gr.Column():
|
| 66 |
+
gr.HTML(
|
| 67 |
+
"<p><b>Step 1:</b> Upload a PDF file from local storage.</p>"
|
| 68 |
+
"<p style='color: #A0A0A0;'>Use this demo for single PDF file only. "
|
| 69 |
+
"You can extract from PDF files continuously and try various other extractors locally with "
|
| 70 |
+
"<a href='https://getindexify.ai/'>Indexify</a>.</p>"
|
| 71 |
+
)
|
| 72 |
+
pdf_file_2 = gr.File(type="filepath")
|
| 73 |
+
with gr.Column():
|
| 74 |
+
gr.HTML("<p><b>Step 2:</b> Run the extractor.</p>")
|
| 75 |
+
go_button_2 = gr.Button(value="Run PDF extractor", variant="primary")
|
| 76 |
+
model_output_text_box_2 = gr.Textbox(label="Extractor Output", elem_id="model_output_text_box_2")
|
| 77 |
+
|
| 78 |
+
with gr.Row():
|
| 79 |
+
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>")
|
| 80 |
+
|
| 81 |
+
go_button_2.click(fn=use_pdf_extractor, inputs=[pdf_file_2], outputs=[model_output_text_box_2])
|
| 82 |
|
| 83 |
demo.queue()
|
| 84 |
demo.launch()
|