请问本地ollama大模型的配置方式

我的本地运行的ollama :    http://127.0.0.1:11434/  

.env
# export LLM_API_KEY=""
export LLM_API_BASE="https://127.0.0.1:11434"
export PRIMARY_MODEL="Qwen/Qwen2.5"
export SECONDARY_MODEL="Qwen/Qwen2.5"

测试提示如下：
INFO:openai._base_client:Retrying request to /chat/completions in 0.488746 seconds
INFO:openai._base_client:Retrying request to /chat/completions in 0.836849 seconds

应该时配置问题吧，要怎么配置呢？