8 Commits

Author	SHA1	Message	Date
Dmitry Ng	aa2dd71269	Merge branch 'main' into release/v0.1.14-update.1	2026-01-24 02:07:00 +03:00
zhu733756	1bbaab130f	documentloaders: add RecursiveDirectoryLoader that loads documents with allowed extensions from a directory (#1386) ... * documentloaders: add RecursiveDirectoryLoader Signed-off-by: zhu733756 <qq107933812@gmail.com> * fix golangci-lint --------- Signed-off-by: zhu733756 <qq107933812@gmail.com>	2025-09-15 04:18:12 +02:00
Dmitry Ng	74fa9c6460	chrore: update audio file path in transcription test and add sample audio file in documentloaders	2025-06-23 15:21:36 +03:00
Dmitry Ng	ab24b67297	Merge branch 'pr/1068’ into main-pull-requests ... documentloaders: ms office docs Squashed commit of the following: Author: Simun Strukan <simun.strukan@gmail.com> Date: Tue May 6 16:46:40 2025 +0200 Reduced the size of docx and pptx files Author: Simun Strukan <simun.strukan@gmail.com> Date: Tue Apr 22 01:03:19 2025 +0200 Added custom regex based parsers for XML based documents, added constant for asci text extraction, separated EOF check from errors while reading doc and ppt document buffers Author: Simun Strukan <simun.strukan@gmail.com> Date: Mon Nov 18 14:57:36 2024 +0100 Added loader for all the common office doc types, doc, docx, ppt, pptx, xls, xlsx Author: Simun Strukan <simun.strukan@gmail.com> Date: Tue Nov 5 00:01:54 2024 +0100 Added core office docs documentloader	2025-06-22 02:03:39 +03:00
Matthew Plachter	9547d68c00	add pdf documentloader ... Update pdf_test.go fix assert order on test	2023-07-12 10:18:28 -04:00
Murilo Santana	9911f24bb9	document loaders: add html loader	2023-06-28 17:05:28 -03:00
Murilo Santana	d3e1424911	document loaders: add csv loader	2023-06-14 15:41:16 -03:00
FluffyKebab	b7d34a2865	documentloaders: add context to interface	2023-04-29 22:00:14 +02:00