first-update
This commit is contained in:
@@ -0,0 +1,77 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { db } from '@/lib/db';
|
||||
|
||||
export async function POST(req, { params }) {
|
||||
try {
|
||||
const { projectId, datasetId } = params;
|
||||
|
||||
// 1. 获取数据集详情
|
||||
const dataset = await db.datasets.findUnique({
|
||||
where: { id: datasetId, projectId }
|
||||
});
|
||||
|
||||
if (!dataset) {
|
||||
return NextResponse.json({ error: 'Dataset not found' }, { status: 404 });
|
||||
}
|
||||
|
||||
// 2. 尝试通过 questionId 查找关联的 chunkId
|
||||
let chunkId = null;
|
||||
if (dataset.questionId) {
|
||||
const question = await db.questions.findUnique({
|
||||
where: { id: dataset.questionId }
|
||||
});
|
||||
if (question) {
|
||||
chunkId = question.chunkId;
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 创建评估数据集记录
|
||||
// 默认使用 open_ended 类型，因为通常数据集是问答对，适合作为评估
|
||||
let evalTags = [];
|
||||
try {
|
||||
evalTags = JSON.parse(dataset.tags || '[]');
|
||||
if (!Array.isArray(evalTags)) evalTags = [];
|
||||
} catch (e) {
|
||||
evalTags = [];
|
||||
}
|
||||
|
||||
// 排除 'Eval' 标签，并将数组转为逗号分隔的字符串
|
||||
const evalTagsString = evalTags.filter(tag => tag !== 'Eval').join(',');
|
||||
|
||||
const evalDataset = await db.evalDatasets.create({
|
||||
data: {
|
||||
projectId,
|
||||
question: dataset.question,
|
||||
questionType: 'open_ended',
|
||||
correctAnswer: dataset.answer,
|
||||
tags: evalTagsString,
|
||||
note: dataset.note,
|
||||
chunkId: chunkId,
|
||||
options: '' // 开放题不需要选项
|
||||
}
|
||||
});
|
||||
|
||||
// 4. 更新原数据集，添加 'Eval' 标签
|
||||
let currentTags = [];
|
||||
try {
|
||||
currentTags = JSON.parse(dataset.tags || '[]');
|
||||
} catch (e) {
|
||||
// ignore error
|
||||
}
|
||||
|
||||
if (!currentTags.includes('Eval')) {
|
||||
currentTags.push('Eval');
|
||||
await db.datasets.update({
|
||||
where: { id: datasetId },
|
||||
data: {
|
||||
tags: JSON.stringify(currentTags)
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
return NextResponse.json({ success: true, evalDataset });
|
||||
} catch (error) {
|
||||
console.error('Failed to copy dataset to eval:', error);
|
||||
return NextResponse.json({ error: 'Internal Server Error' }, { status: 500 });
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,36 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { evaluateDataset } from '@/lib/services/datasets/evaluation';
|
||||
|
||||
/**
|
||||
* 评估单个数据集的质量
|
||||
*/
|
||||
export async function POST(request, { params }) {
|
||||
try {
|
||||
const { projectId, datasetId } = params;
|
||||
const { model, language = 'zh-CN' } = await request.json();
|
||||
|
||||
if (!projectId || !datasetId) {
|
||||
return NextResponse.json({ success: false, message: '项目ID和数据集ID不能为空' }, { status: 400 });
|
||||
}
|
||||
|
||||
if (!model) {
|
||||
return NextResponse.json({ success: false, message: '模型配置不能为空' }, { status: 400 });
|
||||
}
|
||||
|
||||
// 使用评估服务进行数据集评估
|
||||
const result = await evaluateDataset(projectId, datasetId, model, language);
|
||||
|
||||
if (!result.success) {
|
||||
return NextResponse.json({ success: false, message: result.error }, { status: 500 });
|
||||
}
|
||||
|
||||
return NextResponse.json({
|
||||
success: true,
|
||||
message: '数据集评估完成',
|
||||
data: result.data
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('数据集评估失败:', error);
|
||||
return NextResponse.json({ success: false, message: `评估失败: ${error.message}` }, { status: 500 });
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,82 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { getDatasetsById, getDatasetsCounts, getNavigationItems, updateDatasetMetadata } from '@/lib/db/datasets';
|
||||
|
||||
/**
|
||||
* 获取项目的所有数据集
|
||||
*/
|
||||
export async function GET(request, { params }) {
|
||||
try {
|
||||
const { projectId, datasetId } = params;
|
||||
// 验证项目ID
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ error: '项目ID不能为空' }, { status: 400 });
|
||||
}
|
||||
if (!datasetId) {
|
||||
return NextResponse.json({ error: '数据集ID不能为空' }, { status: 400 });
|
||||
}
|
||||
const { searchParams } = new URL(request.url);
|
||||
const operateType = searchParams.get('operateType');
|
||||
if (operateType !== null) {
|
||||
const data = await getNavigationItems(projectId, datasetId, operateType);
|
||||
return NextResponse.json(data);
|
||||
}
|
||||
const datasets = await getDatasetsById(datasetId);
|
||||
let counts = await getDatasetsCounts(projectId);
|
||||
|
||||
return NextResponse.json({ datasets, ...counts });
|
||||
} catch (error) {
|
||||
console.error('获取数据集详情失败:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || '获取数据集详情失败'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 更新数据集元数据（评分、标签、备注）
|
||||
*/
|
||||
export async function PATCH(request, { params }) {
|
||||
try {
|
||||
const { projectId, datasetId } = params;
|
||||
|
||||
// 验证参数
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ error: '项目ID不能为空' }, { status: 400 });
|
||||
}
|
||||
if (!datasetId) {
|
||||
return NextResponse.json({ error: '数据集ID不能为空' }, { status: 400 });
|
||||
}
|
||||
|
||||
const body = await request.json();
|
||||
const { score, tags, note } = body;
|
||||
|
||||
// 验证评分范围
|
||||
if (score !== undefined && (score < 0 || score > 5)) {
|
||||
return NextResponse.json({ error: '评分必须在0-5之间' }, { status: 400 });
|
||||
}
|
||||
|
||||
// 验证标签格式
|
||||
if (tags !== undefined && !Array.isArray(tags)) {
|
||||
return NextResponse.json({ error: '标签必须是数组格式' }, { status: 400 });
|
||||
}
|
||||
|
||||
// 更新数据集元数据
|
||||
const updatedDataset = await updateDatasetMetadata(datasetId, { score, tags, note });
|
||||
|
||||
return NextResponse.json({
|
||||
success: true,
|
||||
dataset: updatedDataset
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('更新数据集元数据失败:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || '更新数据集元数据失败'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,52 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { getDatasetsById } from '@/lib/db/datasets';
|
||||
import { getEncoding } from '@langchain/core/utils/tiktoken';
|
||||
|
||||
/**
|
||||
* 异步计算数据集文本的Token数量
|
||||
*/
|
||||
export async function GET(request, { params }) {
|
||||
try {
|
||||
const { projectId, datasetId } = params;
|
||||
|
||||
if (!datasetId) {
|
||||
return NextResponse.json({ error: '数据集ID不能为空' }, { status: 400 });
|
||||
}
|
||||
|
||||
const datasets = await getDatasetsById(datasetId);
|
||||
const tokenCounts = {
|
||||
answerTokens: 0,
|
||||
cotTokens: 0
|
||||
};
|
||||
|
||||
try {
|
||||
if (datasets.answer || datasets.cot) {
|
||||
// 使用 cl100k_base 编码，适用于 gpt-3.5-turbo 和 gpt-4
|
||||
const encoding = await getEncoding('cl100k_base');
|
||||
|
||||
if (datasets.answer) {
|
||||
const tokens = encoding.encode(datasets.answer);
|
||||
tokenCounts.answerTokens = tokens.length;
|
||||
}
|
||||
|
||||
if (datasets.cot) {
|
||||
const tokens = encoding.encode(datasets.cot);
|
||||
tokenCounts.cotTokens = tokens.length;
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('计算Token数量失败:', String(error));
|
||||
return NextResponse.json({ error: '计算Token数量失败' }, { status: 500 });
|
||||
}
|
||||
|
||||
return NextResponse.json(tokenCounts);
|
||||
} catch (error) {
|
||||
console.error('获取Token计数失败:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || '获取Token计数失败'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,55 @@
|
||||
/**
|
||||
* 批量数据集评估任务API
|
||||
* 创建批量评估数据集质量的异步任务
|
||||
*/
|
||||
|
||||
import { NextResponse } from 'next/server';
|
||||
import { db } from '@/lib/db/index';
|
||||
import { processTask } from '@/lib/services/tasks/index';
|
||||
|
||||
/**
|
||||
* 创建批量数据集评估任务
|
||||
*/
|
||||
export async function POST(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
const { model, language = 'zh-CN' } = await request.json();
|
||||
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ success: false, message: '项目ID不能为空' }, { status: 400 });
|
||||
}
|
||||
|
||||
if (!model || !model.modelId) {
|
||||
return NextResponse.json({ success: false, message: '模型配置不能为空' }, { status: 400 });
|
||||
}
|
||||
|
||||
// 创建批量评估任务
|
||||
const newTask = await db.task.create({
|
||||
data: {
|
||||
projectId,
|
||||
taskType: 'dataset-evaluation',
|
||||
status: 0, // 初始状态: 处理中
|
||||
modelInfo: JSON.stringify(model),
|
||||
language: language || 'zh-CN',
|
||||
detail: '',
|
||||
totalCount: 0,
|
||||
note: '准备开始批量评估数据集质量...',
|
||||
completedCount: 0
|
||||
}
|
||||
});
|
||||
|
||||
// 异步处理任务
|
||||
processTask(newTask.id).catch(err => {
|
||||
console.error(`批量评估任务启动失败: ${newTask.id}`, String(err));
|
||||
});
|
||||
|
||||
return NextResponse.json({
|
||||
success: true,
|
||||
message: '批量评估任务已创建',
|
||||
data: { taskId: newTask.id }
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('创建批量评估任务失败:', error);
|
||||
return NextResponse.json({ success: false, message: `创建任务失败: ${error.message}` }, { status: 500 });
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,128 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import {
|
||||
getDatasets,
|
||||
getBalancedDatasetsByTags,
|
||||
getTagsWithDatasetCounts,
|
||||
getDatasetsBatch,
|
||||
getBalancedDatasetsByTagsBatch,
|
||||
getDatasetsByIds,
|
||||
getDatasetsByIdsBatch
|
||||
} from '@/lib/db/datasets';
|
||||
|
||||
/**
|
||||
* 获取导出数据集
|
||||
*/
|
||||
export async function GET(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
const { searchParams } = new URL(request.url);
|
||||
|
||||
// 验证项目ID
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ error: 'Project ID cannot be empty' }, { status: 400 });
|
||||
}
|
||||
|
||||
const confirmedParam = searchParams.get('confirmed');
|
||||
const confirmed = confirmedParam === null ? undefined : confirmedParam === 'true';
|
||||
|
||||
// 获取标签统计信息
|
||||
const tagStats = await getTagsWithDatasetCounts(projectId, confirmed);
|
||||
return NextResponse.json(tagStats);
|
||||
} catch (error) {
|
||||
console.error('Failed to get tag statistics:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || 'Failed to get tag statistics'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取标签统计信息
|
||||
*/
|
||||
export async function POST(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
const body = await request.json();
|
||||
|
||||
// 验证项目ID
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ error: 'Project ID cannot be empty' }, { status: 400 });
|
||||
}
|
||||
|
||||
let status = body.status;
|
||||
let confirmed = undefined;
|
||||
if (status === 'confirmed') confirmed = true;
|
||||
if (status === 'unconfirmed') confirmed = false;
|
||||
|
||||
// 检查是否是分批导出模式
|
||||
const batchMode = body.batchMode ? 'true' : 'false';
|
||||
const offset = body.offset ?? 0;
|
||||
const batchSize = body.batchSize ?? 1000;
|
||||
|
||||
// 检查是否是平衡导出
|
||||
const balanceMode = body.balanceMode ? 'true' : 'false';
|
||||
const balanceConfig = body.balanceConfig;
|
||||
|
||||
// 检查是否有选中的数据集 ID
|
||||
const selectedIds = Array.isArray(body.selectedIds) ? body.selectedIds : null;
|
||||
|
||||
if (batchMode === 'true') {
|
||||
// 分批导出模式
|
||||
if (selectedIds && selectedIds.length > 0) {
|
||||
// 按选中 ID 分批导出
|
||||
const datasets = await getDatasetsByIdsBatch(projectId, selectedIds, offset, batchSize);
|
||||
const hasMore = datasets.length === batchSize;
|
||||
return NextResponse.json({
|
||||
data: datasets,
|
||||
hasMore,
|
||||
offset: offset + datasets.length
|
||||
});
|
||||
} else if (balanceMode === 'true' && balanceConfig) {
|
||||
// 平衡分批导出
|
||||
const parsedConfig = typeof balanceConfig === 'string' ? JSON.parse(balanceConfig) : balanceConfig;
|
||||
const result = await getBalancedDatasetsByTagsBatch(projectId, parsedConfig, confirmed, offset, batchSize);
|
||||
return NextResponse.json({
|
||||
data: result.data,
|
||||
hasMore: result.hasMore,
|
||||
offset: offset + result.data.length
|
||||
});
|
||||
} else {
|
||||
// 常规分批导出
|
||||
const datasets = await getDatasetsBatch(projectId, confirmed, offset, batchSize);
|
||||
const hasMore = datasets.length === batchSize;
|
||||
return NextResponse.json({
|
||||
data: datasets,
|
||||
hasMore,
|
||||
offset: offset + datasets.length
|
||||
});
|
||||
}
|
||||
} else {
|
||||
// 传统一次性导出模式（保持向后兼容）
|
||||
if (selectedIds && selectedIds.length > 0) {
|
||||
// 按选中 ID 导出
|
||||
const datasets = await getDatasetsByIds(projectId, selectedIds);
|
||||
return NextResponse.json(datasets);
|
||||
} else if (balanceMode === 'true' && balanceConfig) {
|
||||
// 平衡导出模式
|
||||
const parsedConfig = typeof balanceConfig === 'string' ? JSON.parse(balanceConfig) : balanceConfig;
|
||||
const datasets = await getBalancedDatasetsByTags(projectId, parsedConfig, confirmed);
|
||||
return NextResponse.json(datasets);
|
||||
} else {
|
||||
// 常规导出模式
|
||||
const datasets = await getDatasets(projectId, confirmed);
|
||||
return NextResponse.json(datasets);
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('Failed to get datasets:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || 'Failed to get datasets'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { getDatasetsById } from '@/lib/db/datasets';
|
||||
import LLMClient from '@/lib/llm/core/index';
|
||||
import { getEvalQuestionPrompt } from '@/lib/llm/prompts/evalQuestion';
|
||||
import { extractJsonFromLLMOutput } from '@/lib/llm/common/util';
|
||||
|
||||
export async function POST(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
const { datasetId, model, language, questionType = 'open_ended', count = 1 } = await request.json();
|
||||
|
||||
if (!datasetId || !model) {
|
||||
return NextResponse.json({ error: 'Missing required parameters' }, { status: 400 });
|
||||
}
|
||||
|
||||
// 1. 获取原数据集
|
||||
const dataset = await getDatasetsById(datasetId);
|
||||
if (!dataset) {
|
||||
return NextResponse.json({ error: 'Dataset not found' }, { status: 404 });
|
||||
}
|
||||
|
||||
// 2. 构建提示词
|
||||
// 将原问题和答案合并作为上下文文本
|
||||
const text = `Question: ${dataset.question}\nAnswer: ${dataset.answer}`;
|
||||
|
||||
const prompt = await getEvalQuestionPrompt(language || 'zh-CN', questionType, { text, number: count }, projectId);
|
||||
|
||||
// 3. 调用 LLM
|
||||
const client = new LLMClient(model);
|
||||
|
||||
const response = await client.getResponse(prompt);
|
||||
const result = extractJsonFromLLMOutput(response);
|
||||
|
||||
// 结果应该是一个数组
|
||||
if (!result || !Array.isArray(result)) {
|
||||
throw new Error('Failed to parse LLM output or output is not an array');
|
||||
}
|
||||
|
||||
return NextResponse.json({ success: true, data: result });
|
||||
} catch (error) {
|
||||
console.error('Generate eval variant failed:', error);
|
||||
return NextResponse.json({ error: error.message || 'Internal Server Error' }, { status: 500 });
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,109 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { createDataset } from '@/lib/db/datasets';
|
||||
import { nanoid } from 'nanoid';
|
||||
|
||||
export async function POST(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
const { datasets, sourceInfo } = await request.json();
|
||||
|
||||
if (!datasets || !Array.isArray(datasets)) {
|
||||
return NextResponse.json({ error: 'Invalid datasets data' }, { status: 400 });
|
||||
}
|
||||
|
||||
const results = [];
|
||||
const errors = [];
|
||||
let successCount = 0;
|
||||
let skippedCount = 0;
|
||||
|
||||
for (let i = 0; i < datasets.length; i++) {
|
||||
try {
|
||||
const dataset = datasets[i];
|
||||
|
||||
// 安全获取与清洗字段
|
||||
const q = typeof dataset?.question === 'string' ? dataset.question.trim() : '';
|
||||
const a = typeof dataset?.answer === 'string' ? dataset.answer.trim() : '';
|
||||
|
||||
// 验证必填字段：缺失则跳过
|
||||
if (!q || !a) {
|
||||
errors.push(`第 ${i + 1} 条记录缺少必填字段(question/answer)，已跳过`);
|
||||
skippedCount++;
|
||||
continue;
|
||||
}
|
||||
|
||||
// 规范化可选字段
|
||||
const chunkName = dataset?.chunkName || 'Imported Data';
|
||||
const chunkContent = dataset?.chunkContent || 'Imported from external source';
|
||||
const model = dataset?.model || 'imported';
|
||||
const questionLabel = dataset?.questionLabel || '';
|
||||
const cot = typeof dataset?.cot === 'string' ? dataset.cot : '';
|
||||
const confirmed = typeof dataset?.confirmed === 'boolean' ? dataset.confirmed : false;
|
||||
const score = typeof dataset?.score === 'number' ? dataset.score : 0;
|
||||
// tags: 支持数组/字符串/对象
|
||||
let tags = '[]';
|
||||
if (Array.isArray(dataset?.tags)) {
|
||||
try {
|
||||
tags = JSON.stringify(dataset.tags);
|
||||
} catch {
|
||||
tags = '[]';
|
||||
}
|
||||
} else if (typeof dataset?.tags === 'string') {
|
||||
tags = dataset.tags;
|
||||
} else if (dataset?.tags && typeof dataset.tags === 'object') {
|
||||
try {
|
||||
tags = JSON.stringify(dataset.tags);
|
||||
} catch {
|
||||
tags = '[]';
|
||||
}
|
||||
}
|
||||
// other: 对象或字符串
|
||||
let other = '{}';
|
||||
if (typeof dataset?.other === 'string') {
|
||||
other = dataset.other;
|
||||
} else if (dataset?.other && typeof dataset.other === 'object') {
|
||||
try {
|
||||
other = JSON.stringify(dataset.other);
|
||||
} catch {
|
||||
other = '{}';
|
||||
}
|
||||
}
|
||||
const note = typeof dataset?.note === 'string' ? dataset.note : '';
|
||||
|
||||
// 创建数据集记录
|
||||
const newDataset = await createDataset({
|
||||
projectId,
|
||||
questionId: nanoid(), // 生成唯一的问题ID
|
||||
question: q,
|
||||
answer: a,
|
||||
chunkName,
|
||||
chunkContent,
|
||||
model,
|
||||
questionLabel,
|
||||
cot,
|
||||
confirmed,
|
||||
score,
|
||||
tags,
|
||||
note,
|
||||
other
|
||||
});
|
||||
|
||||
results.push(newDataset);
|
||||
successCount++;
|
||||
} catch (error) {
|
||||
errors.push(`第 ${i + 1} 条记录: ${error.message}`);
|
||||
}
|
||||
}
|
||||
|
||||
return NextResponse.json({
|
||||
success: successCount,
|
||||
total: datasets.length,
|
||||
failed: errors.length,
|
||||
skipped: skippedCount,
|
||||
errors,
|
||||
sourceInfo
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('Import datasets error:', error);
|
||||
return NextResponse.json({ error: error.message }, { status: 500 });
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { getDatasetsById, updateDataset } from '@/lib/db/datasets';
|
||||
import { getQuestionById } from '@/lib/db/questions';
|
||||
import { getChunkById } from '@/lib/db/chunks';
|
||||
import LLMClient from '@/lib/llm/core/index';
|
||||
import { getNewAnswerPrompt } from '@/lib/llm/prompts/newAnswer';
|
||||
import { extractJsonFromLLMOutput } from '@/lib/llm/common/util';
|
||||
|
||||
// 优化数据集答案
|
||||
export async function POST(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
|
||||
// 验证项目ID
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ error: 'Project ID cannot be empty' }, { status: 400 });
|
||||
}
|
||||
|
||||
// 获取请求体
|
||||
const { datasetId, model, advice, language } = await request.json();
|
||||
|
||||
if (!datasetId) {
|
||||
return NextResponse.json({ error: 'Dataset ID cannot be empty' }, { status: 400 });
|
||||
}
|
||||
|
||||
if (!model) {
|
||||
return NextResponse.json({ error: 'Model cannot be empty' }, { status: 400 });
|
||||
}
|
||||
|
||||
if (!advice) {
|
||||
return NextResponse.json({ error: 'Please provide optimization suggestions' }, { status: 400 });
|
||||
}
|
||||
|
||||
// 获取数据集内容
|
||||
const dataset = await getDatasetsById(datasetId);
|
||||
if (!dataset) {
|
||||
return NextResponse.json({ error: 'Dataset does not exist' }, { status: 404 });
|
||||
}
|
||||
|
||||
// 创建LLM客户端
|
||||
const llmClient = new LLMClient(model);
|
||||
|
||||
const { question, answer, cot, chunkContent: storedChunkContent, questionId } = dataset;
|
||||
|
||||
let chunkContent = storedChunkContent || '';
|
||||
|
||||
if (!chunkContent && questionId) {
|
||||
try {
|
||||
const questionRecord = await getQuestionById(questionId);
|
||||
if (questionRecord?.chunkId) {
|
||||
const chunkRecord = await getChunkById(questionRecord.chunkId);
|
||||
chunkContent = chunkRecord?.content || '';
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('Failed to load chunk content by questionId:', error);
|
||||
}
|
||||
}
|
||||
|
||||
// 生成优化后的答案和思维链
|
||||
const prompt = await getNewAnswerPrompt(language, { question, answer, cot, advice, chunkContent }, projectId);
|
||||
|
||||
const response = await llmClient.getResponse(prompt);
|
||||
|
||||
// 从LLM输出中提取JSON格式的优化结果
|
||||
const optimizedResult = extractJsonFromLLMOutput(response);
|
||||
|
||||
if (!optimizedResult || !optimizedResult.answer) {
|
||||
return NextResponse.json({ error: 'Failed to optimize answer, please try again' }, { status: 500 });
|
||||
}
|
||||
|
||||
// 更新数据集
|
||||
const updatedDataset = {
|
||||
...dataset,
|
||||
answer: optimizedResult.answer,
|
||||
cot: cot ? optimizedResult.cot || cot : '' // 如果没有提供思考过程，则不更新
|
||||
};
|
||||
|
||||
await updateDataset(updatedDataset);
|
||||
|
||||
// 返回优化后的数据集
|
||||
return NextResponse.json({
|
||||
success: true,
|
||||
dataset: updatedDataset
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('Failed to optimize answer:', String(error));
|
||||
return NextResponse.json({ error: error.message || 'Failed to optimize answer' }, { status: 500 });
|
||||
}
|
||||
}
|
||||
193
easy-dataset-main/app/api/projects/[projectId]/datasets/route.js
Normal file
193
easy-dataset-main/app/api/projects/[projectId]/datasets/route.js
Normal file
@@ -0,0 +1,193 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import {
|
||||
deleteDataset,
|
||||
getDatasetsByPagination,
|
||||
getDatasetsIds,
|
||||
getDatasetsById,
|
||||
updateDataset
|
||||
} from '@/lib/db/datasets';
|
||||
import datasetService from '@/lib/services/datasets';
|
||||
|
||||
// 优化思维链函数已移至服务层
|
||||
|
||||
/**
|
||||
* 生成数据集（为单个问题生成答案）
|
||||
*/
|
||||
export async function POST(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
const { questionId, model, language } = await request.json();
|
||||
|
||||
// 使用数据集生成服务
|
||||
const result = await datasetService.generateDatasetForQuestion(projectId, questionId, {
|
||||
model,
|
||||
language
|
||||
});
|
||||
|
||||
return NextResponse.json(result);
|
||||
} catch (error) {
|
||||
console.error('Failed to generate dataset:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || 'Failed to generate dataset'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取项目的所有数据集
|
||||
*/
|
||||
export async function GET(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
const { searchParams } = new URL(request.url);
|
||||
// 验证项目ID
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ error: '项目ID不能为空' }, { status: 400 });
|
||||
}
|
||||
const page = parseInt(searchParams.get('page')) || 1;
|
||||
const size = parseInt(searchParams.get('size')) || 10;
|
||||
const input = searchParams.get('input');
|
||||
const field = searchParams.get('field') || 'question';
|
||||
const status = searchParams.get('status');
|
||||
const hasCot = searchParams.get('hasCot');
|
||||
const isDistill = searchParams.get('isDistill');
|
||||
const scoreRange = searchParams.get('scoreRange');
|
||||
const customTag = searchParams.get('customTag');
|
||||
const noteKeyword = searchParams.get('noteKeyword');
|
||||
const chunkName = searchParams.get('chunkName');
|
||||
let confirmed = undefined;
|
||||
if (status === 'confirmed') confirmed = true;
|
||||
if (status === 'unconfirmed') confirmed = false;
|
||||
|
||||
let selectedAll = searchParams.get('selectedAll');
|
||||
|
||||
if (selectedAll) {
|
||||
let data = await getDatasetsIds(
|
||||
projectId,
|
||||
confirmed,
|
||||
input,
|
||||
field,
|
||||
hasCot,
|
||||
isDistill,
|
||||
scoreRange,
|
||||
customTag,
|
||||
noteKeyword,
|
||||
chunkName
|
||||
);
|
||||
return NextResponse.json(data);
|
||||
}
|
||||
|
||||
// 获取数据集
|
||||
const datasets = await getDatasetsByPagination(
|
||||
projectId,
|
||||
page,
|
||||
size,
|
||||
confirmed,
|
||||
input,
|
||||
field, // 传递搜索字段参数
|
||||
hasCot, // 传递思维链筛选参数
|
||||
isDistill, // 传递蒸馏数据集筛选参数
|
||||
scoreRange, // 传递评分范围筛选参数
|
||||
customTag, // 传递自定义标签筛选参数
|
||||
noteKeyword, // 传递备注关键字筛选参数
|
||||
chunkName // 传递文本块名称筛选参数
|
||||
);
|
||||
|
||||
return NextResponse.json(datasets);
|
||||
} catch (error) {
|
||||
console.error('获取数据集失败:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || '获取数据集失败'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 删除数据集
|
||||
*/
|
||||
export async function DELETE(request) {
|
||||
try {
|
||||
const { searchParams } = new URL(request.url);
|
||||
const datasetId = searchParams.get('id');
|
||||
if (!datasetId) {
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: 'Dataset ID cannot be empty'
|
||||
},
|
||||
{ status: 400 }
|
||||
);
|
||||
}
|
||||
|
||||
await deleteDataset(datasetId);
|
||||
|
||||
return NextResponse.json({
|
||||
success: true,
|
||||
message: 'Dataset deleted successfully'
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('Failed to delete dataset:', error);
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || 'Failed to delete dataset'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 编辑数据集
|
||||
*/
|
||||
export async function PATCH(request) {
|
||||
try {
|
||||
const { searchParams } = new URL(request.url);
|
||||
const datasetId = searchParams.get('id');
|
||||
const { answer, cot, question, confirmed } = await request.json();
|
||||
if (!datasetId) {
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: 'Dataset ID cannot be empty'
|
||||
},
|
||||
{ status: 400 }
|
||||
);
|
||||
}
|
||||
// 获取所有数据集
|
||||
let dataset = await getDatasetsById(datasetId);
|
||||
if (!dataset) {
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: 'Dataset does not exist'
|
||||
},
|
||||
{ status: 404 }
|
||||
);
|
||||
}
|
||||
let data = { id: datasetId };
|
||||
if (confirmed !== undefined) data.confirmed = confirmed;
|
||||
if (answer) data.answer = answer;
|
||||
if (cot) data.cot = cot;
|
||||
if (question) data.question = question;
|
||||
|
||||
// 保存更新后的数据集列表
|
||||
await updateDataset(data);
|
||||
|
||||
return NextResponse.json({
|
||||
success: true,
|
||||
message: 'Dataset updated successfully',
|
||||
dataset: dataset
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('Failed to update dataset:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || 'Failed to update dataset'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
import { NextResponse } from 'next/server';
|
||||
import { getUsedCustomTags } from '@/lib/db/datasets';
|
||||
|
||||
/**
|
||||
* 获取项目中使用过的自定义标签
|
||||
*/
|
||||
export async function GET(request, { params }) {
|
||||
try {
|
||||
const { projectId } = params;
|
||||
|
||||
// 验证项目ID
|
||||
if (!projectId) {
|
||||
return NextResponse.json({ error: '项目ID不能为空' }, { status: 400 });
|
||||
}
|
||||
|
||||
const tags = await getUsedCustomTags(projectId);
|
||||
|
||||
return NextResponse.json({ tags });
|
||||
} catch (error) {
|
||||
console.error('获取自定义标签失败:', String(error));
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: error.message || '获取自定义标签失败'
|
||||
},
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user