John Cortright ff9695fda5 fix(rag): add proper .docx text extraction via mammoth ... .docx files were classified as plain text and routed through raw-text extraction (extractTXTText). Since .docx is a ZIP archive containing XML, this produced garbage content in the Knowledge Base — XML tags and binary noise instead of the actual document text. Adds a dedicated 'docx' file type (split out of the generic 'text' bucket in determineFileType) and a mammoth-based extractor that parses the document XML properly.		2026-07-13 18:22:34 -07:00
..
controllers	feat(RAG): adds the ability to cancel all embedding jobs (#1034)	2026-06-23 04:47:11 +00:00
exceptions	fix(Docs): documentation renderer fixes	2025-12-23 16:00:33 -08:00
jobs	feat(RAG): adds the ability to cancel all embedding jobs (#1034)	2026-06-23 04:47:11 +00:00
middleware	fix(API): skip compression for Server-Sent Events (#798)	2026-05-20 10:16:00 -07:00
models	feat: replace legacy Kolibri image default with latest v19 image (#1019)	2026-06-23 04:47:07 +00:00
services	fix(rag): add proper .docx text extraction via mammoth	2026-07-13 18:22:34 -07:00
utils	fix(rag): add proper .docx text extraction via mammoth	2026-07-13 18:22:34 -07:00
validators	feat: configurable internet test url override in new Advanced Settings page	2026-06-23 04:47:10 +00:00