From e0460bd881005bc3c36953840d97fc9378046a4d Mon Sep 17 00:00:00 2001 From: Andrew Stoltz Date: Sun, 14 Jun 2026 00:54:36 -0500 Subject: [PATCH] infra(ai): consolidate fleet Ollama consumers onto GX10 VIP 10.0.57.201 Repoints fc-chat, fc-ttsreader, knowledge, fc-llm-bridge (off the slow edge1 Pi5 10.0.57.17) and intranet (off the reimaged BLUEJAY-AI test laptop 10.0.56.132) to the GX10 (DGX Spark / GB10) Ollama over the PROD MetalLB VIP 10.0.57.201. GX10 serves gemma3:12b/gemma3:4b/qwen2.5:1.5b/nomic-embed-text/ llama3.2:1b on local NVMe, warm-pinned (keep_alive=-1). fc-chat default model qwen2.5-coder:7b -> gemma3:12b (the coder model won't pull reliably on the GX10; gemma3:12b is the warm fleet default + a better general-chat model). Other consumers keep their exact models. Inline comments referencing edge1/BLUEJAY-AI are now historical; the values are the GX10 VIP. Co-Authored-By: Claude Opus 4.8 (1M context) --- apps/fc-chat/fc-chat.yaml | 8 ++++---- apps/fc-llm-bridge/fc-llm-bridge.yaml | 2 +- apps/fc-ttsreader/fc-ttsreader.yaml | 2 +- apps/intranet/intranet.yaml | 2 +- apps/knowledge/knowledge.yaml | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/apps/fc-chat/fc-chat.yaml b/apps/fc-chat/fc-chat.yaml index 96674e7..e52188a 100644 --- a/apps/fc-chat/fc-chat.yaml +++ b/apps/fc-chat/fc-chat.yaml @@ -34,10 +34,10 @@ data: # proved Chat pods time out reaching 10.0.56.20:11434. Keep generation and # behavior-rule checks on the cluster-routable edge1 endpoint until that route # is fixed; choose models that edge1 actually hosts. - FlowerCore__AI__OllamaBaseUrl: "http://10.0.57.17:11434" - FlowerCore__AI__DefaultModelName: "qwen2.5-coder:7b" - ChatOptions__BehaviorRuleEngine__OllamaBaseUrl: "http://10.0.57.17:11434" - ChatOptions__BehaviorRuleEngine__FallbackOllamaBaseUrl: "http://10.0.57.17:11434" + FlowerCore__AI__OllamaBaseUrl: "http://10.0.57.201:11434" + FlowerCore__AI__DefaultModelName: "gemma3:12b" + ChatOptions__BehaviorRuleEngine__OllamaBaseUrl: "http://10.0.57.201:11434" + ChatOptions__BehaviorRuleEngine__FallbackOllamaBaseUrl: "http://10.0.57.201:11434" ChatOptions__BehaviorRuleEngine__ModelName: "gemma3:4b" FlowerCore__AI__Memory__UseSharedIndexingAdapter: "true" FlowerCore__AI__Memory__UseOllamaEmbeddings: "true" diff --git a/apps/fc-llm-bridge/fc-llm-bridge.yaml b/apps/fc-llm-bridge/fc-llm-bridge.yaml index 171c1d4..ca20f1c 100644 --- a/apps/fc-llm-bridge/fc-llm-bridge.yaml +++ b/apps/fc-llm-bridge/fc-llm-bridge.yaml @@ -166,7 +166,7 @@ spec: optional: true # Shared.Chat — Ollama (edge1 Pi 5 + AI HAT+, matches bridge default) - name: FlowerCore__Chat__OllamaBaseUrl - value: "http://10.0.57.17:11434" + value: "http://10.0.57.201:11434" - name: FlowerCore__Chat__HttpTimeout value: "00:05:00" # Shared.Chat — Anthropic diff --git a/apps/fc-ttsreader/fc-ttsreader.yaml b/apps/fc-ttsreader/fc-ttsreader.yaml index 164ba80..6fb204b 100644 --- a/apps/fc-ttsreader/fc-ttsreader.yaml +++ b/apps/fc-ttsreader/fc-ttsreader.yaml @@ -605,7 +605,7 @@ spec: - name: TtsReader__Transcription__TimeoutSeconds value: "300" - name: TtsReader__Ollama__BaseUrl - value: "http://10.0.57.17:11434" + value: "http://10.0.57.201:11434" - name: TtsReader__Ollama__DefaultModel value: "gemma3:4b" - name: TtsReader__Ollama__TimeoutSeconds diff --git a/apps/intranet/intranet.yaml b/apps/intranet/intranet.yaml index f332155..6af90f6 100644 --- a/apps/intranet/intranet.yaml +++ b/apps/intranet/intranet.yaml @@ -92,7 +92,7 @@ spec: # down. Bulk embed runs in the background; /health does not depend on it. # Memory: feedback_pi5_nomic_embed_slow. - name: IntranetSearch__OllamaBaseUrl - value: "http://10.0.56.132:11434" + value: "http://10.0.57.201:11434" # Notes docs corpus IS now mounted at /srv/flowercore-notes (see the # notes-corpus-clone initContainer + notes-corpus-sync sidecar), so the # IntranetSearch indexer is ENABLED. First-boot bulk embed of the corpus diff --git a/apps/knowledge/knowledge.yaml b/apps/knowledge/knowledge.yaml index 2c4a734..b287b87 100644 --- a/apps/knowledge/knowledge.yaml +++ b/apps/knowledge/knowledge.yaml @@ -168,7 +168,7 @@ spec: # need a separate ingestion lane that can opt into the # workstation GPU when present. - name: FlowerCore__Ollama__BaseUrl - value: "http://10.0.57.17:11434" + value: "http://10.0.57.201:11434" - name: FlowerCore__Mcp__ApiKey__Key valueFrom: secretKeyRef: