23 Commits

Author	SHA1	Message	Date
perf3ct	2311c3c049	centralize LLM constants more	2025-03-28 23:25:06 +00:00
perf3ct	224cb22fe9	centralize prompts	2025-03-28 23:07:02 +00:00
perf3ct	72c380b6f4	do a wayyy better job at building the messages with context	2025-03-28 22:50:15 +00:00
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
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	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
perf3ct	352204bf78	add agentic thinking to chat	2025-03-19 18:49:14 +00:00
perf3ct	c37201183b	add Voyage AI as Embedding provider	2025-03-17 22:32:00 +00:00
perf3ct	697d348286	set up more reasonable context window and dimension sizes	2025-03-16 18:08:50 +00:00
perf3ct	72b1426d94	break up large vector_store into smaller files	2025-03-12 00:02:02 +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
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
perf3ct	adaac46fbf	I'm 100% going to have to destroy this commit later	2025-03-09 02:19:26 +00:00