37 commits

Author	SHA1	Message	Date
BukeLy	85f17f9955	Fix list_index variable shadowing in fix_incorrect_toc ... The loop variable `list_index = page_index - start_index` was overwriting the outer `list_index = incorrect_item['list_index']`, causing results to be written back to wrong index positions. Rename the loop variable to `page_list_idx` to avoid shadowing. Closes #66	2026-03-16 14:19:51 +08:00
Bukely_	599d2ce497	Merge pull request #65 from luojiyin1987/fix/extract-toc-infinite-loop ... fix: prevent infinite loop in extract_toc_content	2026-03-16 13:34:05 +08:00
Bukely_	b487f9d7c7	Merge pull request #63 from luojiyin1987/fix/api-error-return ... fix: make ChatGPT_API_with_finish_reason return consistent tuple	2026-03-16 13:24:54 +08:00
Matias Insaurralde	cf52a678a3	fix: rename tob_extractor_prompt typo to toc_extractor_prompt (#109) ... Signed-off-by: Matías Insaurralde <matias@insaurral.de>	2026-02-27 15:16:19 +08:00
luojiyin	ac9ceaf2ee	fix: prevent infinite loop in extract_toc_content ... The while loop exit condition used len(chat_history), but chat_history was rebuilt every iteration with exactly 2 elements, making the check len(chat_history) > 5 never true. Replace with explicit attempt counter and max_attempts limit.	2026-01-19 12:34:39 +08:00
luojiyin	87962b4d42	fix: make ChatGPT_API_with_finish_reason return consistent tuple ... Signed-off-by: luojiyin <luojiyin@hotmail.com>	2026-01-19 12:27:35 +08:00
Ray	33ec9aca6e	by default add node summary	2025-09-01 14:06:57 +08:00
zmtomorrow	d799a0cf67	firx print_toc	2025-08-31 11:52:59 +01:00
zmtomorrow	d4c910ad5a	firx print_toc	2025-08-31 11:51:50 +01:00
Ray	987f91c3bf	fix params	2025-08-28 13:22:43 +08:00
Ray	4b4ae4d51d	fix model	2025-08-28 13:07:15 +08:00
Ray	6d1b505541	fix params	2025-08-28 12:45:39 +08:00
zmtomorrow	277bcb9512	filter code	2025-08-27 15:22:44 +01:00
zmtomorrow	fdcbed54f1	Merge branch 'feat/markdown-tree' of github.com:VectifyAI/PageIndex into feat/markdown-tree	2025-08-27 15:12:55 +01:00
zmtomorrow	edd1be353c	filter code	2025-08-27 15:12:45 +01:00
Ray	ad6a926fce	add markdown runner	2025-08-26 21:27:40 +08:00
zmtomorrow	82ad5e2651	add markdown_to_tree	2025-08-26 12:18:06 +01:00
zmtomorrow	fd70ef1acf	add markdown_to_tree	2025-08-26 12:17:21 +01:00
zmtomorrow	78cce56b33	add markdown_to_tree	2025-08-26 12:17:05 +01:00
Ray	c22778f85d	fix node summary	2025-08-26 16:30:12 +08:00
Ray	19faaad74f	fix format	2025-08-26 16:17:05 +08:00
Ray	34ed3fbc60	fix structure	2025-08-26 16:14:29 +08:00
Ray	802f149dd1	add summary	2025-08-26 15:49:03 +08:00
zmtomorrow	04bbdae647	add markdown_to_tree	2025-08-25 20:57:44 +01:00
Ray	d9568ff4ed	use async with for client calls	2025-06-26 01:37:20 +08:00
Ray	6d6e92d56e	consolidate async calls	2025-06-25 15:41:29 +08:00
Ray	991324efed	Merge pull request #21 from clarenceluo78/main ... Fix: handle TOC items exceeding document length	2025-06-01 14:56:10 +08:00
Ray	ad65e3f19c	fix option for adding node text	2025-05-30 14:02:38 +08:00
clarenceluo78	1679600c9a	fix: handle TOC items exceeding document length	2025-05-30 03:03:20 +01:00
Ray	57ea07da3d	fix arg parsing	2025-04-23 17:10:54 +08:00
Ray	7b890a16fa	fix index range	2025-04-20 07:59:20 +08:00
Ray	b588cd62a1	add async. various fixes.	2025-04-20 07:57:07 +08:00
zmtomorrow	5aef9b4a49	fix physical index	2025-04-18 17:01:02 +08:00
Ray	4ba12cf3ce	fix pdf name	2025-04-09 19:37:00 +08:00
Ray	8a7f8132cf	fix yaml	2025-04-09 17:30:36 +08:00
Ray	63024b1d7b	fix typo	2025-04-07 14:56:18 +08:00
Ray	403a7a4f54	Restructure and update CLI entry point to run_pageindex.py	2025-04-06 21:49:16 +08:00