optimizequerymapper

February 4, 2026 · View on GitHub

Optimize queries in question-answer pairs to make them more specific and detailed.

This mapper refines the questions in a QA pair, making them more specific and detailed while ensuring that the original answer can still address the optimized question. It uses a predefined system prompt for the optimization process. The optimized query is extracted from the raw output by stripping any leading or trailing whitespace. The mapper utilizes a CUDA accelerator for faster processing.

优化问答对中的查询，使其更具体和详细。

该映射器改进问答对中的问题，使其更具体和详细，同时确保原始答案仍能回答优化后的问题。它使用预定义的系统提示进行优化过程。优化后的查询通过去除任何前导或尾随空格从原始输出中提取。映射器利用CUDA加速器进行更快的处理。

Type 算子类型: mapper

Tags 标签: gpu, vllm, hf, api

🔧 Parameter Configuration 参数配置

name 参数名	type 类型	default 默认值	desc 说明
`api_or_hf_model`	<class 'str'>	`'Qwen/Qwen2.5-7B-Instruct'`	API or huggingface model name.
`is_hf_model`	<class 'bool'>	`True`	If true, use huggingface model. Otherwise, use API.
`api_endpoint`	typing.Optional[str]	`None`	URL endpoint for the API.
`response_path`	typing.Optional[str]	`None`	Path to extract content from the API response. Defaults to 'choices.0.message.content'.
`system_prompt`	typing.Optional[str]	`None`	System prompt for guiding the optimization task.
`input_template`	typing.Optional[str]	`None`	Template for building the input for the model. Please make sure the template contains one placeholder '{}', which corresponds to the question and answer pair generated by param `qa_pair_template`.
`qa_pair_template`	typing.Optional[str]	`None`	Template for formatting the question and answer pair. Please make sure the template contains two '{}' to format question and answer.
`output_pattern`	typing.Optional[str]	`None`	Regular expression pattern to extract question and answer from model response.
`try_num`	typing.Annotated[int, Gt(gt=0)]	`3`	The number of retry attempts when there is an API call error or output parsing error.
`enable_vllm`	<class 'bool'>	`False`	Whether to use VLLM for inference acceleration.
`model_params`	typing.Optional[typing.Dict]	`None`	Parameters for initializing the model.
`sampling_params`	typing.Optional[typing.Dict]	`None`	Sampling parameters for text generation (e.g., {'temperature': 0.9, 'top_p': 0.95}).
`kwargs`		`''`	Extra keyword arguments.