1529 Commits

Author	SHA1	Message	Date
perf3ct	ea4d3ac800	Do a better job with Ollama context, again	2025-03-28 22:29:33 +00:00
perf3ct	2899707e64	Better use of interfaces, reducing useage of "any"	2025-03-28 21:47:28 +00:00
Elian Doran	35fbc731a7	Merge branch 'develop' into ai-llm-integration	2025-03-26 22:46:36 +02:00
perf3ct	baef5f9ada	fix updateProvider parameter	2025-03-26 19:21:59 +00:00
perf3ct	15630fb432	add swaggerUI docstrings for LLM/AI API routes	2025-03-26 19:19:19 +00:00
perf3ct	713805394c	move providers.ts into providers folder	2025-03-26 19:10:16 +00:00
perf3ct	c49883fdfa	move constants to their own files and folder	2025-03-26 17:56:37 +00:00
perf3ct	44b6734034	anthropic works	2025-03-26 04:13:04 +00:00
Elian Doran	b923a23d95	feat(settings): make the formatting locale value adjustable	2025-03-25 19:56:07 +02:00
perf3ct	b00c20c357	Merge branch 'develop' into ai-llm-integration	2025-03-24 21:16:20 +00:00
Elian Doran	cf874b5ee8	feat(mermaid): add basic support for vertical layout	2025-03-22 10:27:42 +02:00
Elian Doran	28c51cb38a	refactor(client): use webpack for mermaid	2025-03-22 02:15:09 +02:00
perf3ct	34940b5258	Merge branch 'develop' into ai-llm-integration	2025-03-20 19:52:01 +00:00
Elian Doran	b44bb4053c	refactor(deps): use webpack for jsplumb & panzoom	2025-03-20 21:51:03 +02:00
perf3ct	1be70f1163	do a better job of building the context	2025-03-20 19:35:20 +00:00
perf3ct	eb1ef36ab3	move the llm_prompt_constants to its own folder	2025-03-20 18:49:30 +00:00
perf3ct	e566692361	centralize all prompts	2025-03-20 00:06:56 +00:00
perf3ct	db4dd6d2ef	refactor "context" services	2025-03-19 19:28:02 +00:00
Panagiotis Papadopoulos	feb9fa03c3	chore(deps): move mind-elixir related packages to devDependencies ... webpack takes care of bundling these, so we don't need the modules at runtime anymore	2025-03-19 20:03:24 +01:00
perf3ct	352204bf78	add agentic thinking to chat	2025-03-19 18:49:14 +00:00
perf3ct	08f7f1962b	do a better job with similarity searches	2025-03-18 00:50:55 +00:00
perf3ct	c37201183b	add Voyage AI as Embedding provider	2025-03-17 22:32:00 +00:00
perf3ct	84a8473beb	adapt or regenerate embeddings - allows users to decide	2025-03-17 21:47:11 +00:00
perf3ct	ebc5107b96	add missing options	2025-03-17 21:23:43 +00:00
perf3ct	37f1dcdaab	add ability to fetch available models from openai	2025-03-17 21:03:21 +00:00
perf3ct	c40c702761	add anthropic options as well	2025-03-17 20:17:28 +00:00
perf3ct	4a4eac6f25	Allow users to specify OpenAI embedding and chat models	2025-03-17 20:07:53 +00:00
perf3ct	d95fd0b049	allow specifying openai embedding models too	2025-03-17 19:54:11 +00:00
perf3ct	cc85b9a8f6	fix autoupdate name inconsistency	2025-03-16 20:55:55 +00:00
perf3ct	781a2506f0	fix embeddings w/ cls.init()	2025-03-16 18:55:53 +00:00
perf3ct	697d348286	set up more reasonable context window and dimension sizes	2025-03-16 18:08:50 +00:00
perf3ct	c556989f85	Merge branch 'develop' into ai-llm-integration	2025-03-15 19:38:27 +00:00
Elian Doran	0f28bbb1be	feat(server): use custom temporary directory within trilium-data	2025-03-15 10:11:54 +02:00
Jon Fuller	39d265a9fa	Merge branch 'develop' into ai-llm-integration	2025-03-12 11:58:30 -07:00
perf3ct	eaa947ef7c	"rebuild index" functionality for users	2025-03-12 00:08:39 +00:00
perf3ct	72b1426d94	break up large vector_store into smaller files	2025-03-12 00:02:02 +00:00
perf3ct	fc5599575c	allow users to manually request index to be rebuilt	2025-03-11 23:29:54 +00:00
perf3ct	730d123802	create llm index service	2025-03-11 23:26:47 +00:00
perf3ct	0d2858c7e9	upgrade chunking	2025-03-11 23:04:51 +00:00
perf3ct	6ce3f1c355	better note names to LLM?	2025-03-11 22:47:36 +00:00
Elian Doran	cf76358dd7	fix(canvas): font loading	2025-03-11 23:03:34 +02:00
perf3ct	f47b070f0f	I think this works to handle failed embeddings	2025-03-11 20:22:01 +00:00
perf3ct	56fc720ac7	undo accidental MAX_ALLOWED_FILE_SIZE_MB change	2025-03-11 17:31:26 +00:00
perf3ct	ff679b00b6	move providers to their own folder	2025-03-11 17:30:50 +00:00
perf3ct	d2dc401639	add these options as configurable	2025-03-11 03:58:39 +00:00
Jon Fuller	d713f3831a	Merge branch 'develop' into ai-llm-integration	2025-03-10 16:43:48 -07:00
perf3ct	c1585c73da	actually shows useful responses now	2025-03-10 05:06:33 +00:00
perf3ct	ef6ecdc42d	it errors, but works	2025-03-10 04:28:56 +00:00
perf3ct	cf0e9242a0	try a context approach	2025-03-10 03:34:48 +00:00
Elian Doran	e129e0369d	server(attachments): render empty SVGs properly (closes #1378)	2025-03-09 22:23:01 +02:00