|
|
fde60f3341
|
updated chuck_size and overlap as they were too small
|
2025-06-02 18:41:08 -05:00 |
|
|
|
f0503e7aac
|
Fix for not applying company field to documents
|
2025-05-30 17:31:09 -05:00 |
|
|
|
25867c0f31
|
crawler now supports directories for loading multiple pdfs
|
2025-05-30 16:28:35 -05:00 |
|
|
|
f07afccdb3
|
clearing_index now uses filter
|
2025-05-30 16:28:07 -05:00 |
|
|
|
2552d867da
|
Added logger
|
2025-05-30 16:27:48 -05:00 |
|
|
|
696669aae4
|
Adding scrape_options
|
2025-05-27 17:54:11 -05:00 |
|
|
|
c381b0434a
|
Refactored and moved all keys and configuration into .env files and provided samples
|
2025-05-24 12:33:40 -05:00 |
|
|
|
b3da128396
|
refactored project to use poetry
|
2025-05-20 22:19:30 -05:00 |
|