12 Commits

Author	SHA1	Message	Date
Ryan Chen	32020a6c60	Replace Ollama with llama-server (OpenAI-compatible API) ... - Update llm.py to use OpenAI client with custom base_url for llama-server - Update agents.py to use ChatOpenAI instead of ChatOllama - Remove unused ollama imports from main.py, chunker.py, query.py - Add LLAMA_SERVER_URL and LLAMA_MODEL_NAME env vars - Remove ollama and langchain-ollama dependencies Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-31 21:39:23 -05:00
Ryan Chen	ad39904dda	reorganization	2026-01-31 17:13:27 -05:00
Ryan Chen	70799ffb7d	refactor	2025-11-10 15:51:13 -05:00
Ryan Chen	f16e13fccc	big uplift	2025-10-26 09:25:17 -04:00
Ryan Chen	68d73b62e8	Instituting LLM fallback to OpenAI if gaming PC is not on	2025-10-24 08:44:08 -04:00
Ryan Chen	2bbe33fedc	Starting attempt #2 at metadata filtering	2025-10-14 22:13:01 -04:00
Ryan Chen	c978b1a255	Reducing startup time/cost	2025-10-08 23:21:22 -04:00
Ryan Chen	51b9932389	fixing loal llm	2025-10-08 22:52:49 -04:00
Ryan Chen	ebf39480b6	urf	2025-10-08 22:46:16 -04:00
Ryan Chen	e4a04331cb	add some more debugging	2025-10-08 21:17:45 -04:00
Ryan Chen	166ffb4c09	i only ship bugs	2025-10-08 21:13:15 -04:00
Ryan Chen	c6c14729dd	interseting	2025-10-08 21:03:42 -04:00