ai_ml_operations/chat_backend
2
0
Fork 0
Code Issues 23 Pull Requests Actions Packages Projects Releases Wiki Activity

Always-on grounded retrieval + role-scoped Ollama models (#62 Phases 1–3) #65

Merged
westfarn merged 2 commits from feature/accuracy-grounded-retrieval-62 into master 2026-08-02 11:46:02 -07:00
Conversation 0 Commits 2 Files Changed 32
+1734 -187
2 Commits
Author SHA1 Message Date
westfarn 51464943a9 Point SEARXNG_BASE_URL at :8088 (dta_webapp owns :8080 on GPU host).
CI / test (pull_request) Successful in 11s
Details
Unit Tests / test (pull_request) Successful in 10s
Details 
Aligns with server-infra#10 / PR #11 — SearxNG binds 8088 on ai-server-4080.
 2026-08-02 13:23:40 -05:00
westfarn d51033809f Always-on grounded retrieval with SearxNG and role-scoped Ollama models (#62).
CI / test (pull_request) Successful in 11s
Details
Unit Tests / test (pull_request) Successful in 10s
Details 
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