23 Commits

Include renames

Author	SHA1	Message	Date
Thorsten Sommer	4e67504bca	Classify embedding failures at the provider level	2026-09-06 15:44:01 +02:00
Thorsten Sommer	8950acb654	Keep provider management working when tokenizer storage fails	2026-09-06 11:20:54 +02:00
Thorsten Sommer	fe35630eff	Merge branch 'main' into chunk-data ... Resolved 29 conflicting files. The notable decisions: Confidence: main's tool-calling gate (RequiredProviderConfidence) and this branch's local-RAG gate (DataConfidenceLevel) turned out to be the same rule on the same axis, so they are now one field. Both tool results and data sources raise it through RequireProviderConfidence(). The gate checks the level strictly and no longer exempts providers trusted by configuration: TrustedProviderIds is documented as applying to data-source security checks only, and organizations set confidence through DataConfidence .CustomConfidenceScheme instead. The security axis (DataSecurity, ERI, IsTrustedForDataSourceSecurityChecks) is unchanged. Provider creation: main's CreateProvider signature won (hfEndpointKind, capabilityOverrides, no model parameter); tokenizerPath was added to it and is set for every provider, including the new Hetzner, IONOS and LiteLLM. Provider and EmbeddingProvider combine the record parameters, Lua parsing and Lua serialization of both sides. File types: main's hierarchy (ODT leaf, WORD parent, PowerPoint without the legacy .ppt, TABULAR instead of DELIMITED_TABLE) plus this branch's SPREADSHEET parent with ODS and the xlsm/xlsb/xla/xlam extensions, which the runtime already reads. Both sides had added a conflicting HTML filter; the reading family keeps the name, and the export path uses a narrow HTML_DOCUMENT, following the existing LATEX/TEX split. Runtime: main's file_data.rs is the base, including the prompt-injection sanitizer and the extraction routes. Token counting and chunk segmentation moved into take_released, so they act on the text the filter has released rather than on text it is still holding. A failed count is logged and left out instead of ending the extraction, because the app counts such a segment itself. Data sources: the participating-provider checks of this branch are kept, and main's GetAllowedDataSources overload now builds on them. DirectChatService resolves the launched chat's data source options before the check, so filter and chat see the same options. .NET and Rust both build clean; I18N regenerated to 4060 keys.	2026-09-05 21:20:33 +02:00
Thorsten Sommer	f14c69b938	Reworked the Hugging Face provider (#944)	2026-08-30 16:45:14 +02:00
Peer HogeterpandThorsten Sommer	e78a0e61b9	Added provider icons (#934) ... Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>	2026-08-25 12:46:10 +02:00
Dominic NeuburgandThorsten Sommer	592c9c76e2	Added user-managed API keys for enterprise-configured providers (#919) ... Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>	2026-08-15 11:20:36 +02:00
Thorsten Sommer	98c86b94f5	Sort and group model lists by provider (#916)	2026-08-12 21:57:58 +02:00
PaulKoudelka	89f7156fdf	improved chunking pipeline and handling of expert settings	2026-07-29 18:47:59 +02:00
PaulKoudelka	1bf9328fb9	made the chunking process more robust	2026-07-28 16:37:07 +02:00
PaulKoudelka	ac677c5ac7	background embed	2026-05-08 17:37:34 +02:00
Paul Koudelka	aa554d4a53	added possibility to add tokenizer via plugin and refactored earlier changes	2026-04-23 16:29:30 +02:00
Paul Koudelka	4a8ab90173	cleanup to ensure uniform style of code	2026-04-15 10:17:14 +02:00
PaulKoudelka	e07ca378d4	added functionality to add tokenizer to LLM and embedding models	2026-04-10 18:34:10 +02:00
Paul KoudelkaandThorsten Sommer	a8951fe58a	Added embedding API (#654) ... Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>	2026-02-20 15:32:54 +01:00
Thorsten Sommer	1aa27d217a	Restrict export actions to admin settings visibility (#671)	2026-02-19 21:31:59 +01:00
Thorsten Sommer	4cf62672de	Added settings & features for administrators in organizations (#653)	2026-02-07 22:59:41 +01:00
Thorsten Sommer	3abc2bf0f1	Fixed several provider dialog issues (#629)	2026-01-18 17:15:18 +01:00
Thorsten Sommer	529986837e	Implemented the transcription API (#623)	2026-01-11 16:02:28 +01:00
Thorsten Sommer	30197cf507	Added transcription providers (#619)	2026-01-09 12:45:21 +01:00
Thorsten Sommer	f1c2a65450	Made dialog parameter usage explicit with generic types (#543)	2025-08-28 18:51:44 +02:00
Thorsten Sommer	9fa0f95611	Localized the embedding configuration (#455)	2025-05-11 16:57:52 +02:00
Thorsten Sommer	63be312bb4	Configure data sources (#259)	2025-01-13 19:51:26 +01:00
Thorsten Sommer	06f66fdab2	Refactored the settings page (#258)	2025-01-05 15:11:15 +01:00