westfarn d51033809f Always-on grounded retrieval with SearxNG and role-scoped Ollama models (#62). ...

Phases 1–3: split THINKING/FAST/UTILITY/EMBED models, structured search with
SearxNG primary + DDGS failover, fail-open grounding, citations on Prompt + WS
frames, single history window with prompt budgeting, and reindex_embeddings.

2026-08-02 09:05:45 -05:00

..

.idea

temp checkin

2025-03-07 12:23:00 -06:00

chat_backend

Always-on grounded retrieval with SearxNG and role-scoped Ollama models (#62).

2026-08-02 09:05:45 -05:00

finance

Tier-gated RAG + Drive document sources (#42) (#54)

2026-08-01 14:02:36 -07:00

llm_be

Always-on grounded retrieval with SearxNG and role-scoped Ollama models (#62).

2026-08-02 09:05:45 -05:00

templates/admin

Closes #4

2025-12-08 13:52:30 -06:00

manage.py

RAG implementation, content moderation, prompt classification, new LLM chain, document storage

2025-05-14 03:27:38 -05:00

scp_command.txt

temp checkin

2025-03-07 12:23:00 -06:00