From d4fa69957e4dae70e6db02a098e45a1886bdbd23 Mon Sep 17 00:00:00 2001 From: DJP Date: Wed, 8 Apr 2026 15:11:59 -0400 Subject: [PATCH] Switch Ollama chat model to gemma4:latest Gemma 4 loads successfully, supports tool calling with proper structured output, and responds in ~100ms after initial load. Co-Authored-By: Claude Opus 4.6 --- docker-compose.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker-compose.yml b/docker-compose.yml index ca150ca..260e2ae 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -31,7 +31,7 @@ services: # Ollama — points to internal GPU server for embeddings + chat fallback OLLAMA_HOST: ${OLLAMA_HOST:-http://10.24.42.219:11434} OLLAMA_CHAT_HOST: ${OLLAMA_CHAT_HOST:-http://10.24.42.219:11434} - OLLAMA_CHAT_MODEL: ${OLLAMA_CHAT_MODEL:-mistral:latest} + OLLAMA_CHAT_MODEL: ${OLLAMA_CHAT_MODEL:-gemma4:latest} OLLAMA_EMBED_MODEL: ${OLLAMA_EMBED_MODEL:-nomic-embed-text} NODE_ENV: production AUTH_SECRET: ${AUTH_SECRET}