From 7d6267bfcd0cb0b8e0a0252a713f2c924e3b92a0 Mon Sep 17 00:00:00 2001 From: Ian Date: Tue, 3 Jun 2025 23:16:13 -0700 Subject: [PATCH] Add ollama thinking docs (#39375) --- source/_integrations/ollama.markdown | 2 ++ 1 file changed, 2 insertions(+) diff --git a/source/_integrations/ollama.markdown b/source/_integrations/ollama.markdown index d2ad23caf3b..4db4e5914e9 100644 --- a/source/_integrations/ollama.markdown +++ b/source/_integrations/ollama.markdown @@ -48,6 +48,8 @@ Max history messages: description: Maximum number of messages to keep for each conversation (0 = no limit). Limiting this value will cause older messages in a conversation to be dropped. Keep alive: description: Duration in seconds for the Ollama host to keep the model in memory after receiving a message (-1 = no limit, 0 = no retention). Default value is -1. +Think before responding: + description: If the AI should think about its response before responding. This will cause the AI to take longer to respond, but may result in better responses. Default value is `false`. Thinking is not supported by all models and displaying thinking content is not supported by frontend clients yet. {% endconfiguration_basic %} ## Controlling Home Assistant