optimize_query_mapper¶
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: cpu, vllm, hf
🔧 Parameter Configuration 参数配置¶
name 参数名 |
type 类型 |
default 默认值 |
desc 说明 |
---|---|---|---|
|
<class ‘str’> |
|
Hugging Face model ID. |
|
typing.Optional[str] |
|
System prompt for guiding the optimization task. |
|
typing.Optional[str] |
|
Template for building the input for the model. |
|
typing.Optional[str] |
|
Template for formatting the question and |
|
typing.Optional[str] |
|
Regular expression pattern to extract question |
|
<class ‘bool’> |
|
Whether to use VLLM for inference acceleration. |
|
typing.Optional[typing.Dict] |
|
Parameters for initializing the model. |
|
typing.Optional[typing.Dict] |
|
Sampling parameters for text generation (e.g., |
|
|
Extra keyword arguments. |
📊 Effect demonstration 效果演示¶
not available 暂无