12 Commits

Author	SHA1	Message	Date
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
Prodman Devokadev	5966f0f6a5	Added LiteLLM as a new LLM provider (#909) ... Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>	2026-08-30 12:55:18 +02:00
Paul Koudelka	2e06af13e0	Merge branch 'main' into chunk-data	2026-07-01 09:54:12 +02:00
Thorsten Sommer	c0e6a9a644	Enhanced llama.cpp support for loading available models (#808)	2026-06-11 15:46:17 +02:00
PaulKoudelka	0854debc00	added functionality to save/move tokenizer file	2026-04-10 18:31:20 +02:00
Thorsten Sommer	3abc2bf0f1	Fixed several provider dialog issues (#629)	2026-01-18 17:15:18 +01:00
Thorsten Sommer	30197cf507	Added transcription providers (#619)	2026-01-09 12:45:21 +01:00
Thorsten Sommer	7a08baf99b	Added more text content to the I18N system (#446)	2025-05-04 14:59:30 +02:00
Thorsten Sommer	2144cfe059	Updated documentation (#409)	2025-04-20 15:24:43 +02:00
Peer Schütt	1ff27fe21f	Added Hugging Face inference provider (#397)	2025-04-11 14:31:10 +02:00
Thorsten Sommer	799112eb9d	Added embedding configurations (#224)	2024-12-03 15:24:40 +01:00