YG-Soft/YG_FT
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(data-process): 增加可配置思维链生成

Browse Source
This commit is contained in:
caoxiaozhu
2026-07-27 14:41:38 +08:00
parent 97cdb5cc68
commit f97245b814
12 changed files with 224 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
frontend/src/views/data-process/create/dataProcessCreateState.ts
View File

@@ -9,7 +9,25 @@ import type {
} from './types'
import { normalizeQaPairsGenerationCount } from './types'
export const DEFAULT_GENERATION_PROMPT = '你是一名专业的数据生成助手。请根据输入内容生成准确、完整、可直接用于模型训练的问答数据。仅输出符合所选输出类型和目标格式的内容，答案应事实清晰、语言自然，不要添加无关说明。'
const LEGACY_DEFAULT_GENERATION_PROMPT = '你是一名专业的数据生成助手。请根据输入内容生成准确、完整、可直接用于模型训练的问答数据。仅输出符合所选输出类型和目标格式的内容，答案应事实清晰、语言自然，不要添加无关说明。'
export const DEFAULT_STANDARD_GENERATION_PROMPT = '你是一名专业的数据生成助手。请严格依据输入内容生成准确、完整、可直接用于监督微调的问答数据。只生成问题和最终答案，不输出分析、推理过程或来源中不存在的信息；答案应事实清晰、语言自然。'
export const DEFAULT_REASONING_GENERATION_PROMPT = '你是一名专业的推理数据生成助手。请严格依据输入内容生成问题、可核验的推理过程和最终答案。推理需要说明关键依据与必要步骤，不得引入来源中不存在的事实；最终答案应准确、完整且语言自然。'
export function defaultGenerationPrompt(outputType: 'standard' | 'reasoning') {
return outputType === 'reasoning'
? DEFAULT_REASONING_GENERATION_PROMPT
: DEFAULT_STANDARD_GENERATION_PROMPT
}
export function isBuiltInGenerationPrompt(value: string) {
return [
LEGACY_DEFAULT_GENERATION_PROMPT,
DEFAULT_STANDARD_GENERATION_PROMPT,
DEFAULT_REASONING_GENERATION_PROMPT,
].includes(value)
}
export function createDefaultStructuredOptions(): StructuredProcessOptions {
return {
@@ -18,8 +36,9 @@ export function createDefaultStructuredOptions(): StructuredProcessOptions {
qaPairsPerRow: 1,
datasetSplit: { train: 80, validation: 10, test: 10 },
generationModelId: '',
generationPrompt: DEFAULT_GENERATION_PROMPT,
generationPrompt: DEFAULT_STANDARD_GENERATION_PROMPT,
outputType: 'standard',
reasoningDetail: 'normal',
temperature: 0.7,
maxTokens: 1024,
jsonMode: false,
@@ -52,8 +71,9 @@ export function createDefaultUnstructuredOptions(): UnstructuredProcessOptions {
qaPairsPerChunk: 1,
datasetSplit: { train: 80, validation: 10, test: 10 },
generationModelId: '',
generationPrompt: DEFAULT_GENERATION_PROMPT,
generationPrompt: DEFAULT_STANDARD_GENERATION_PROMPT,
outputType: 'standard',
reasoningDetail: 'normal',
temperature: 0.7,
maxTokens: 1024,
jsonMode: false,
@@ -92,12 +112,21 @@ function generationOptionsFromConfig(
config: DataProcessConfig,
defaults: GenerationControlOptions,
): GenerationControlOptions {
const outputType = configValue(config, 'output_type', defaults.outputType) === 'reasoning'
? 'reasoning'
: 'standard'
const configuredPrompt = String(
configValue(config, 'generation_prompt', defaults.generationPrompt),
)
return {
generationModelId: configValue(config, 'generation_model_id', defaults.generationModelId),
generationPrompt: String(configValue(config, 'generation_prompt', defaults.generationPrompt)),
outputType: configValue(config, 'output_type', defaults.outputType) === 'reasoning'
? 'reasoning'
: 'standard',
generationPrompt: isBuiltInGenerationPrompt(configuredPrompt)
? defaultGenerationPrompt(outputType)
: configuredPrompt,
outputType,
reasoningDetail: configValue(config, 'reasoning_detail', defaults.reasoningDetail) === 'detailed'
? 'detailed'
: 'normal',
temperature: numberValue(config, 'temperature', defaults.temperature),
maxTokens: numberValue(config, 'max_tokens', defaults.maxTokens),
jsonMode: Boolean(configValue(config, 'json_mode', defaults.jsonMode)),
@@ -224,6 +253,7 @@ export function generationAffectingOptionsFor(
generationModelId: options.generationModelId,
generationPrompt: options.generationPrompt,
outputType: options.outputType,
reasoningDetail: options.reasoningDetail,
temperature: options.temperature,
maxTokens: options.maxTokens,
jsonMode: options.jsonMode,