Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import pandas as pd | |
| from geolocation_apis import addresses_to_coordinates, coordinates_to_route | |
| from pdf_parser import process_pdf_hebrew_rtl | |
| from llm_api import llm_parser | |
| from map_visualize import generate_route_map | |
| def summarize_items(items): | |
| """ | |
| Returns a preview list for the dataset component. | |
| """ | |
| return [ | |
| [ | |
| f"{i + 1}. [{item['source']}] " + ( | |
| os.path.basename(item['file'].name) if item['source'] == 'PDF' else item['content'][:40] | |
| ) + "..." | |
| ] | |
| for i, item in enumerate(items) | |
| ] | |
| def add_files(files, items): | |
| """ | |
| Adds uploaded PDF file objects to the state. | |
| """ | |
| new_items = [{"source": "PDF", "file": f} for f in files] | |
| items += new_items | |
| return items, gr.update(samples=summarize_items(items)) | |
| def add_text(text, items): | |
| """ | |
| Adds pasted text content to the state. | |
| """ | |
| if text.strip(): | |
| items.append({"source": "Paste", "content": text.strip()}) | |
| return items, gr.update(samples=summarize_items(items)) | |
| def delete_item(evt: gr.SelectData, items): | |
| """ | |
| Deletes an item when selected in the dataset component. | |
| """ | |
| del items[evt.index] | |
| return items, gr.update(samples=summarize_items(items)) | |
| def run_pipeline(items): | |
| """ | |
| Processes PDFs and pasted text through the LLM pipeline, | |
| geocodes addresses, computes an optimized route, | |
| and writes two HTML outputs (data table and map). | |
| """ | |
| # Separate file-based and pasted inputs | |
| pdf_paths = [item['file'].name for item in items if item['source'] == 'PDF'] | |
| # Parse PDFs to text | |
| text_docs = [process_pdf_hebrew_rtl(path) for path in pdf_paths] | |
| # Include any pasted text directly | |
| pasted_texts = [item['content'] for item in items if item['source'] == 'Paste'] | |
| # Combine for LLM parsing | |
| docs = text_docs + pasted_texts | |
| results, llm_parsed = llm_parser(docs=docs) | |
| # Geolocation and routing | |
| locations = addresses_to_coordinates([r.business_address for r in results]) | |
| points = [loc.coords for loc in locations] | |
| route = coordinates_to_route(points) | |
| # Build data table | |
| df = pd.DataFrame([loc.to_dict() for loc in locations]) | |
| llm_parsed = llm_parsed.rename(columns={'business_address': 'Address'}) | |
| df = df.join(llm_parsed.set_index('Address'), on='Address') | |
| # Write HTML outputs | |
| data_output_path = './data_output.html' | |
| with open(data_output_path, mode='w', encoding='utf-8') as html: | |
| html.write(df.to_html(index=False, escape=False)) | |
| map_output_path = './map_output.html' | |
| generate_route_map(route, map_output_path) | |
| return data_output_path, map_output_path | |
| # Build Gradio interface | |
| with gr.Blocks() as demo: | |
| state = gr.State([]) | |
| with gr.Row(): | |
| file_input = gr.Files(file_types=['.pdf'], label="Upload PDFs") | |
| file_btn = gr.Button("Add PDFs") | |
| with gr.Row(): | |
| paste_box = gr.Textbox(lines=3, placeholder="Paste text content...", label="Paste Text") | |
| paste_btn = gr.Button("Add Text") | |
| gr.Markdown("### 📝 Inputs:") | |
| item_list = gr.Dataset( | |
| components=[gr.Textbox(visible=False)], # hide the textbox | |
| samples=[], | |
| headers=["Items"] | |
| ) | |
| # Register callbacks for managing inputs | |
| file_btn.click(add_files, inputs=[file_input, state], outputs=[state, item_list]) | |
| paste_btn.click(add_text, inputs=[paste_box, state], outputs=[state, item_list]) | |
| item_list.select(delete_item, inputs=state, outputs=[state, item_list]) | |
| # Processing and output | |
| process_btn = gr.Button("Process & Download HTML") | |
| data_out = gr.File(label="📊 Business Data HTML") | |
| map_out = gr.File(label="🗺️ Route Map HTML") | |
| process_btn.click(run_pipeline, inputs=state, outputs=[data_out, map_out]) | |
| # Launch the app | |
| if __name__ == '__main__': | |
| demo.launch() | |