From e644a3e02f2966e84f585ae7b959e7cdea8456b9 Mon Sep 17 00:00:00 2001 From: yangdx Date: Wed, 17 Sep 2025 02:56:05 +0800 Subject: [PATCH] Adjust OpenAI temperature default and add mitigation guidance --- env.example | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/env.example b/env.example index 6eb61dcf..f7db6b05 100644 --- a/env.example +++ b/env.example @@ -175,7 +175,8 @@ LLM_BINDING_API_KEY=your_api_key # LLM_BINDING=openai ### OpenAI Compatible API Specific Parameters -OPENAI_LLM_TEMPERATURE=0.8 +### Increased temperature values may mitigate infinite inference loops in certain LLM, such as Qwen3-30B. +# OPENAI_LLM_TEMPERATURE=0.9 ### Set the max_tokens to mitigate endless output of some LLM (less than LLM_TIMEOUT * llm_output_tokens/second, i.e. 9000 = 180s * 50 tokens/s) ### Typically, max_tokens does not include prompt content, though some models, such as Gemini Models, are exceptions ### For vLLM/SGLang doployed models, or most of OpenAI compatible API provider