20 commits

Author	SHA1	Message	Date
CREDO23	c30cc08771	Merge upstream/dev into feat/kb-export-and-folder-upload	2026-04-11 10:28:40 +02:00
Anish Sarkar	bb5b90e5bd	fix: update Azure Document Intelligence parser to use prebuilt-layout model	2026-04-10 20:40:54 +05:30
CREDO23	4ccdd80e26	Harden vision LLM fallback, folder upload validation, and export memory	2026-04-09 16:14:53 +02:00
CREDO23	e164fe0612	Fix misleading log when vision LLM fails vs not provided	2026-04-09 15:29:39 +02:00
CREDO23	55661bcde6	Replace mimetypes fallback with explicit extension-to-MIME mapping	2026-04-09 15:21:32 +02:00
CREDO23	71db53fc55	Add 5MB file size guard before base64 encoding for vision LLM	2026-04-09 15:17:08 +02:00
CREDO23	d6c4fb8938	Add try/except fallback in _extract_image for vision LLM failures	2026-04-09 15:11:24 +02:00
CREDO23	caaec2e0a7	Simplify vision LLM image description prompt	2026-04-09 14:56:18 +02:00
CREDO23	7e90a8ed3c	Route uploaded images to vision LLM with document-parser fallback	2026-04-09 14:33:33 +02:00
Anish Sarkar	8455451ce1	chore: ran linting	2026-04-08 05:20:03 +05:30
Anish Sarkar	20fa93f0ba	refactor: make Azure Document Intelligence an internal LLAMACLOUD accelerator instead of a standalone ETL service	2026-04-08 03:26:24 +05:30
Anish Sarkar	1fa8d1220b	feat: add support for Azure Document Intelligence in ETL pipeline	2026-04-08 00:59:12 +05:30
Anish Sarkar	0a26a6c5bb	chore: ran linting	2026-04-07 05:55:39 +05:30
Anish Sarkar	e7beeb2a36	refactor: unify file skipping logic across Dropbox, Google Drive, and OneDrive connectors by replacing classification checks with a centralized service-based approach, enhancing maintainability and consistency in file handling	2026-04-07 02:19:31 +05:30
Anish Sarkar	dc7047f64d	refactor: implement file type classification for supported extensions across Dropbox, Google Drive, and OneDrive connectors, enhancing file handling and error management	2026-04-06 22:03:47 +05:30
Anish Sarkar	f40de6b695	feat: add parsers for Docling, LlamaCloud, and Unstructured to ETL pipeline	2026-04-05 17:27:24 +05:30
Anish Sarkar	2824410be2	feat: add plaintext parser to ETL pipeline for reading text files	2026-04-05 17:26:42 +05:30
Anish Sarkar	35582c9389	feat: add direct_convert module to ETL pipeline for file conversion	2026-04-05 17:26:29 +05:30
Anish Sarkar	02fc6f1d16	feat: add audio transcription functionality to ETL pipeline	2026-04-05 17:26:03 +05:30
Anish Sarkar	5d22349dc1	feat: implement ETL pipeline with file classification and extraction services	2026-04-05 17:25:25 +05:30