Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -159,6 +159,59 @@ with gr.Blocks(title="PDF data extraction with PDF Extractor & Indexify") as pdf
|
|
| 159 |
outputs = [model_output_text_box]
|
| 160 |
)
|
| 161 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
demo = gr.TabbedInterface([marker_demo, pdf_demo, gemini_demo, openai_demo], ["Marker Extractor", "PDF Extractor", "Gemini Extractor", "OpenAI Extractor"], theme=gr.themes.Soft())
|
| 163 |
|
| 164 |
demo.queue()
|
|
|
|
| 159 |
outputs = [model_output_text_box]
|
| 160 |
)
|
| 161 |
|
| 162 |
+
with gr.Blocks(title="PDF data extraction with Gemini & Indexify") as gemini_demo:
|
| 163 |
+
gr.HTML("<h1 style='text-align: center'>PDF data extraction with Gemini & <a href='https://getindexify.ai/'>Indexify</a></h1>")
|
| 164 |
+
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>")
|
| 165 |
+
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>")
|
| 166 |
+
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/multimodal_gemini.ipynb' target='_blank'>extraction pipleine</a> with Indexify</h4>")
|
| 167 |
+
|
| 168 |
+
with gr.Row():
|
| 169 |
+
with gr.Column():
|
| 170 |
+
gr.HTML(
|
| 171 |
+
"<p><b>Step 1:</b> Upload a PDF file from local storage.</p>"
|
| 172 |
+
|
| 173 |
+
"<p style='color: #A0A0A0;'>Use this demo for single PDF file only. "
|
| 174 |
+
"You can extract from PDF files continuously and try various other extractors locally with "
|
| 175 |
+
"<a href='https://getindexify.ai/'>Indexify</a>.</p>"
|
| 176 |
+
)
|
| 177 |
+
|
| 178 |
+
pdf_file = gr.File(type="filepath")
|
| 179 |
+
|
| 180 |
+
gr.HTML("<p><b>Step 2:</b> Enter your API key.</p>")
|
| 181 |
+
|
| 182 |
+
key = gr.Textbox(
|
| 183 |
+
info="Please enter your GEMINI_API_KEY",
|
| 184 |
+
label="Key:"
|
| 185 |
+
)
|
| 186 |
+
|
| 187 |
+
with gr.Column():
|
| 188 |
+
gr.HTML("<p><b>Step 3:</b> Run the extractor.</p>")
|
| 189 |
+
|
| 190 |
+
go_button = gr.Button(
|
| 191 |
+
value="Run extractor",
|
| 192 |
+
variant="primary",
|
| 193 |
+
)
|
| 194 |
+
|
| 195 |
+
model_output_text_box = gr.Textbox(
|
| 196 |
+
label="Extractor Output",
|
| 197 |
+
elem_id="model_output_text_box",
|
| 198 |
+
)
|
| 199 |
+
|
| 200 |
+
with gr.Row():
|
| 201 |
+
|
| 202 |
+
gr.HTML(
|
| 203 |
+
"<p style='text-align: center'>"
|
| 204 |
+
"Developed with 🫶 by <a href='https://getindexify.ai/' target='_blank'>Indexify</a> | "
|
| 205 |
+
"a <a href='https://www.tensorlake.ai/' target='_blank'>Tensorlake</a> product"
|
| 206 |
+
"</p>"
|
| 207 |
+
)
|
| 208 |
+
|
| 209 |
+
go_button.click(
|
| 210 |
+
fn=use_gemini,
|
| 211 |
+
inputs = [pdf_file, key],
|
| 212 |
+
outputs = [model_output_text_box]
|
| 213 |
+
)
|
| 214 |
+
|
| 215 |
demo = gr.TabbedInterface([marker_demo, pdf_demo, gemini_demo, openai_demo], ["Marker Extractor", "PDF Extractor", "Gemini Extractor", "OpenAI Extractor"], theme=gr.themes.Soft())
|
| 216 |
|
| 217 |
demo.queue()
|