27 Commits

Author	SHA1	Message	Date
shamoon	fe205b31c2	indexing cleanup and tests	2025-07-02 11:04:00 -07:00
shamoon	559caf72c2	Unify prompts, cover	2025-07-02 11:03:59 -07:00
shamoon	2481a66544	Incremental llm index update, add scheduled llm index task	2025-07-02 11:03:59 -07:00
shamoon	f6a3882199	Some cleanup, typing	2025-07-02 11:03:59 -07:00
shamoon	8d48d398eb	Handle doc updates, refactor	2025-07-02 11:03:58 -07:00
shamoon	b3b9a8fb5b	Chat coverage	2025-07-02 11:03:58 -07:00
shamoon	6f0c6f39b1	Fix gzip breaks streaming and flush stream	2025-07-02 11:03:55 -07:00
shamoon	0690fd36c5	Fix openai api key, config settings saving	2025-07-02 11:03:55 -07:00
shamoon	bb3336f7bc	Just use the built-in ollama LLM class of course	2025-07-02 11:01:58 -07:00
shamoon	a9ed46de11	Fix naming	2025-07-02 11:01:58 -07:00
shamoon	1ccaf66869	Trim nodes	2025-07-02 11:01:57 -07:00
shamoon	e864a51497	Backend streaming chat	2025-07-02 11:01:57 -07:00
shamoon	4a28be233e	Fixup some tests	2025-07-02 11:01:56 -07:00
shamoon	5f26139a5f	Unify, respect perms ... [ci skip]	2025-07-02 11:01:56 -07:00
shamoon	ccfc7d98b1	Individual doc chat ... [ci skip]	2025-07-02 11:01:55 -07:00
shamoon	d1bd2af49c	Super basic doc chat ... [ci skip]	2025-07-02 11:01:55 -07:00
shamoon	e2eec6dc71	Better encapsulate backends, use llama_index OpenAI	2025-07-02 11:01:54 -07:00
shamoon	df8f07555f	Tweak ollama timeout, prompt ... [ci skip]	2025-07-02 11:01:54 -07:00
shamoon	3660336bcf	Fix ollama, fix RAG ... [ci skip]	2025-07-02 11:01:53 -07:00
shamoon	aeceaf60a2	RAG into suggestions	2025-07-02 11:01:53 -07:00
shamoon	959ebdbb85	llamaindex vector index, llmindex mangement command	2025-07-02 11:01:52 -07:00
shamoon	f5fc04cfe2	Use a frontend config	2025-07-02 11:01:51 -07:00
shamoon	767118fa8a	Fix	2025-07-02 11:01:48 -07:00
shamoon	339612f4ec	Backend tests	2025-07-02 11:01:48 -07:00
shamoon	e7592c6269	Correct object retrieval	2025-07-02 11:01:48 -07:00
shamoon	ffc0b936f3	Refactor	2025-07-02 11:01:47 -07:00
shamoon	1a6540e8ed	Move module	2025-07-02 11:01:47 -07:00