Spaces:
Running
Running
Commit ·
100a70e
1
Parent(s): 207b3fa
updated changes in phase0102
Browse files
phase0102_chunker_aggregator_2.py
CHANGED
|
@@ -227,8 +227,6 @@ async def run_chunking_process(pdf_path, queue=None, whole=WHOLE, start_p=START_
|
|
| 227 |
"original": lookahead[:len(res.get('break_text', '')) + 500] # Save a snippet of the original
|
| 228 |
}
|
| 229 |
|
| 230 |
-
|
| 231 |
-
|
| 232 |
# Throttling to stay under 6000 TPM limit
|
| 233 |
await asyncio.sleep(7)
|
| 234 |
|
|
@@ -336,7 +334,7 @@ Visual Clarity: Table Markdown is perfect for a quick bird's-eye view, such as t
|
|
| 336 |
# --- NESTED AND TABULAR MARKDOWN
|
| 337 |
def export_visual_formats(final_data, timestamp):
|
| 338 |
# --- NESTED MARKDOWN ---
|
| 339 |
-
md_nested = f"# 👑 VOLUME: {final_data['metadata']['pages']}\n"
|
| 340 |
md_nested += f"> {final_data['l3_volume']['content'] if final_data['l3_volume'] else 'N/A'}\n\n"
|
| 341 |
|
| 342 |
for l2 in final_data['l2_chapters']:
|
|
|
|
| 227 |
"original": lookahead[:len(res.get('break_text', '')) + 500] # Save a snippet of the original
|
| 228 |
}
|
| 229 |
|
|
|
|
|
|
|
| 230 |
# Throttling to stay under 6000 TPM limit
|
| 231 |
await asyncio.sleep(7)
|
| 232 |
|
|
|
|
| 334 |
# --- NESTED AND TABULAR MARKDOWN
|
| 335 |
def export_visual_formats(final_data, timestamp):
|
| 336 |
# --- NESTED MARKDOWN ---
|
| 337 |
+
#md_nested = f"# 👑 VOLUME: {final_data['metadata']['pages']}\n"
|
| 338 |
md_nested += f"> {final_data['l3_volume']['content'] if final_data['l3_volume'] else 'N/A'}\n\n"
|
| 339 |
|
| 340 |
for l2 in final_data['l2_chapters']:
|