Xunfei Spark Proxy LLM Configuration

Xunfei Spark proxy LLM configuration.

Details can be found in:
https://www.xfyun.cn/doc/spark/HTTP%E8%B0%83%E7%94%A8%E6%96%87%E6%A1%A3.html#_1-%E6%8E%A5%E5%8F%A3%E8%AF%B4%E6%98%8E

Parameters

Name	Type	Required	Description
name	string	✅	The name of the model.
backend	string	❌	The real model name to pass to the provider, default is None. If backend is None, use name as the real model name.
provider	string	❌	The provider of the model. If model is deployed in local, this is the inference type. If model is deployed in third-party service, this is platform name('proxy/<platform>') Defaults：proxy/spark
verbose	boolean	❌	Show verbose output. Defaults：False
concurrency	integer	❌	Model concurrency limit Defaults：100
prompt_template	string	❌	Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment.
context_length	integer	❌	The context length of the OpenAI API. If None, it is determined by the model.
api_base	string	❌	The base url of the Spark API. Defaults： ${env:XUNFEI_SPARK_API_BASE:-https://spark-api-open.xf-yun.com/v1}
api_key	string	❌	The API key of the Spark API. Defaults：${env:XUNFEI_SPARK_API_KEY}
api_type	string	❌	The type of the OpenAI API, if you use Azure, it can be: azure
api_version	string	❌	The version of the OpenAI API.
http_proxy	string	❌	The http or https proxy to use openai