You've already forked DataMate
feature: add data-evaluation
* feature: add evaluation task management function * feature: add evaluation task detail page * fix: delete duplicate definition for table t_model_config * refactor: rename package synthesis to ratio * refactor: add eval file table and refactor related code * fix: calling large models in parallel during evaluation
This commit is contained in:
hefanli
GitHub
@@ -1,574 +1,395 @@
|
||||
import { useState } from "react";
|
||||
import {
|
||||
Button,
|
||||
Card,
|
||||
Badge,
|
||||
Input,
|
||||
Select,
|
||||
Checkbox,
|
||||
Form,
|
||||
Typography,
|
||||
} from "antd";
|
||||
import {
|
||||
PlusOutlined,
|
||||
ArrowLeftOutlined,
|
||||
EditOutlined,
|
||||
SaveOutlined,
|
||||
DeleteOutlined,
|
||||
} from "@ant-design/icons";
|
||||
import {
|
||||
evaluationTemplates,
|
||||
presetEvaluationDimensions,
|
||||
sliceOperators,
|
||||
} from "@/mock/evaluation";
|
||||
import { useNavigate } from "react-router";
|
||||
import React, { useState, useEffect } from 'react';
|
||||
import { Button, Form, Input, Select, message, Modal, Row, Col, Table, Space } from 'antd';
|
||||
import { EyeOutlined } from '@ant-design/icons';
|
||||
import { queryDatasetsUsingGet } from "@/pages/DataManagement/dataset.api.ts";
|
||||
import { mapDataset } from "@/pages/DataManagement/dataset.const.tsx";
|
||||
import { queryModelListUsingGet } from "@/pages/SettingsPage/settings.apis.ts";
|
||||
import { ModelI } from "@/pages/SettingsPage/ModelAccess.tsx";
|
||||
import { createEvaluationTaskUsingPost } from "@/pages/DataEvaluation/evaluation.api.ts";
|
||||
import { queryPromptTemplatesUsingGet } from "@/pages/DataEvaluation/evaluation.api.ts";
|
||||
import PreviewPromptModal from "@/pages/DataEvaluation/Create/PreviewPrompt.tsx";
|
||||
|
||||
const { Title, Paragraph } = Typography;
|
||||
const { Option } = Select;
|
||||
interface Dataset {
|
||||
id: string;
|
||||
name: string;
|
||||
fileCount: number;
|
||||
size: string;
|
||||
}
|
||||
|
||||
const EvaluationTaskCreate = () => {
|
||||
const navigate = useNavigate();
|
||||
const [datasets, setDatasets] = useState([]);
|
||||
const [selectedTemplate, setSelectedTemplate] =
|
||||
useState<string>("dialogue_text");
|
||||
const [allDimensions, setAllDimensions] = useState<EvaluationDimension[]>([
|
||||
...presetEvaluationDimensions,
|
||||
]);
|
||||
const [editingDimension, setEditingDimension] = useState<string | null>(null);
|
||||
const [newDimension, setNewDimension] = useState({
|
||||
name: "",
|
||||
description: "",
|
||||
});
|
||||
const [createForm, setCreateForm] = useState({
|
||||
name: "",
|
||||
datasetId: "",
|
||||
evaluationType: "model" as "model" | "manual",
|
||||
dimensions: [] as string[],
|
||||
customDimensions: [] as EvaluationDimension[],
|
||||
sliceConfig: {
|
||||
threshold: 0.8,
|
||||
sampleCount: 100,
|
||||
method: "语义分割",
|
||||
},
|
||||
modelConfig: {
|
||||
url: "",
|
||||
apiKey: "",
|
||||
prompt: "",
|
||||
temperature: 0.3,
|
||||
maxTokens: 2000,
|
||||
},
|
||||
interface Dimension {
|
||||
key: string;
|
||||
dimension: string;
|
||||
description: string;
|
||||
}
|
||||
|
||||
interface PromptTemplate {
|
||||
evalType: string;
|
||||
prompt: string;
|
||||
defaultDimensions: Dimension[];
|
||||
}
|
||||
|
||||
interface CreateTaskModalProps {
|
||||
visible: boolean;
|
||||
onCancel: () => void;
|
||||
onSuccess: () => void;
|
||||
}
|
||||
|
||||
const TASK_TYPES = [
|
||||
{ label: 'QA评估', value: 'QA' },
|
||||
];
|
||||
|
||||
const EVAL_METHODS = [
|
||||
{ label: '模型自动评估', value: 'AUTO' },
|
||||
];
|
||||
|
||||
const DEFAULT_EVAL_METHOD = 'AUTO';
|
||||
const DEFAULT_TASK_TYPE = 'QA';
|
||||
|
||||
const CreateTaskModal: React.FC<CreateTaskModalProps> = ({ visible, onCancel, onSuccess }) => {
|
||||
const [form] = Form.useForm();
|
||||
const [loading, setLoading] = useState(false);
|
||||
const [datasets, setDatasets] = useState<Dataset[]>([]);
|
||||
const [models, setModels] = useState<ModelI[]>([]);
|
||||
const [dimensions, setDimensions] = useState<Dimension[]>([]);
|
||||
const [newDimension, setNewDimension] = useState<Omit<Dimension, 'key'>>({
|
||||
dimension: '',
|
||||
description: ''
|
||||
});
|
||||
const [taskType, setTaskType] = useState<string>("QA");
|
||||
const [promptTemplates, setPromptTemplates] = useState<PromptTemplate[]>([]);
|
||||
const [previewVisible, setPreviewVisible] = useState(false);
|
||||
const [evaluationPrompt, setEvaluationPrompt] = useState('');
|
||||
|
||||
const handleTemplateChange = (templateKey: string) => {
|
||||
setSelectedTemplate(templateKey);
|
||||
const template =
|
||||
evaluationTemplates[templateKey as keyof typeof evaluationTemplates];
|
||||
if (template) {
|
||||
const customDimensions = allDimensions.filter((d) => d.isCustom);
|
||||
setAllDimensions([...template.dimensions, ...customDimensions]);
|
||||
const handleAddDimension = () => {
|
||||
if (!newDimension.dimension.trim()) {
|
||||
message.warning('请输入维度名称');
|
||||
return;
|
||||
}
|
||||
setDimensions([...dimensions, { ...newDimension, key: `dim-${Date.now()}` }]);
|
||||
setNewDimension({ dimension: '', description: '' });
|
||||
};
|
||||
|
||||
const handleDeleteDimension = (key: string) => {
|
||||
if (dimensions.length <= 1) {
|
||||
message.warning('至少需要保留一个评估维度');
|
||||
return;
|
||||
}
|
||||
setDimensions(dimensions.filter(item => item.key !== key));
|
||||
};
|
||||
|
||||
useEffect(() => {
|
||||
if (visible) {
|
||||
fetchDatasets().then();
|
||||
fetchModels().then();
|
||||
fetchPromptTemplates().then();
|
||||
}
|
||||
}, [visible]);
|
||||
|
||||
const fetchDatasets = async () => {
|
||||
try {
|
||||
const { data } = await queryDatasetsUsingGet({ page: 1, size: 1000 });
|
||||
setDatasets(data.content.map(mapDataset) || []);
|
||||
} catch (error) {
|
||||
console.error('Error fetching datasets:', error);
|
||||
message.error('获取数据集列表失败');
|
||||
}
|
||||
};
|
||||
|
||||
const handleAddCustomDimension = () => {
|
||||
if (newDimension.name.trim() && newDimension.description.trim()) {
|
||||
const customDimension: EvaluationDimension = {
|
||||
id: `custom_${Date.now()}`,
|
||||
name: newDimension.name.trim(),
|
||||
description: newDimension.description.trim(),
|
||||
category: "custom",
|
||||
isCustom: true,
|
||||
isEnabled: true,
|
||||
};
|
||||
setAllDimensions([...allDimensions, customDimension]);
|
||||
setNewDimension({ name: "", description: "" });
|
||||
const fetchModels = async () => {
|
||||
try {
|
||||
const { data } = await queryModelListUsingGet({ page: 0, size: 1000 });
|
||||
setModels(data.content || []);
|
||||
} catch (error) {
|
||||
console.error('Error fetching models:', error);
|
||||
message.error('获取模型列表失败');
|
||||
}
|
||||
};
|
||||
|
||||
const handleDimensionToggle = (id: string, checked: boolean) => {
|
||||
setAllDimensions(
|
||||
allDimensions.map((d) => (d.id === id ? { ...d, isEnabled: checked } : d))
|
||||
);
|
||||
};
|
||||
|
||||
const handleEditDimension = (
|
||||
id: string,
|
||||
field: "name" | "description",
|
||||
value: string
|
||||
) => {
|
||||
setAllDimensions(
|
||||
allDimensions.map((d) => (d.id === id ? { ...d, [field]: value } : d))
|
||||
);
|
||||
};
|
||||
|
||||
const handleDeleteCustomDimension = (id: string) => {
|
||||
setAllDimensions(allDimensions.filter((d) => d.id !== id));
|
||||
};
|
||||
|
||||
const handleDeletePresetDimension = (id: string) => {
|
||||
setAllDimensions(
|
||||
allDimensions.map((d) => (d.id === id ? { ...d, isEnabled: false } : d))
|
||||
);
|
||||
};
|
||||
|
||||
const handleCreateTask = () => {
|
||||
const selectedDataset = datasets.find((d) => d.id === createForm.datasetId);
|
||||
if (!selectedDataset) return;
|
||||
|
||||
const enabledDimensions = allDimensions.filter((d) => d.isEnabled);
|
||||
const presetDimensionIds = enabledDimensions
|
||||
.filter((d) => !d.isCustom)
|
||||
.map((d) => d.id);
|
||||
const customDimensions = enabledDimensions.filter((d) => d.isCustom);
|
||||
|
||||
let finalPrompt = createForm.modelConfig.prompt;
|
||||
if (createForm.evaluationType === "model" && !finalPrompt.trim()) {
|
||||
finalPrompt = generateDefaultPrompt(selectedDataset.name);
|
||||
}
|
||||
|
||||
const newTask: EvaluationTask = {
|
||||
id: Date.now().toString(),
|
||||
name: createForm.name,
|
||||
datasetId: createForm.datasetId,
|
||||
datasetName: selectedDataset.name,
|
||||
evaluationType: createForm.evaluationType,
|
||||
status: "pending",
|
||||
progress: 0,
|
||||
createdAt: new Date().toLocaleString(),
|
||||
description: `${
|
||||
createForm.evaluationType === "model" ? "模型自动" : "人工"
|
||||
}评估${selectedDataset.name}`,
|
||||
dimensions: presetDimensionIds,
|
||||
customDimensions: customDimensions,
|
||||
modelConfig:
|
||||
createForm.evaluationType === "model"
|
||||
? {
|
||||
...createForm.modelConfig,
|
||||
prompt: finalPrompt,
|
||||
}
|
||||
: undefined,
|
||||
metrics: {
|
||||
accuracy: 0,
|
||||
completeness: 0,
|
||||
consistency: 0,
|
||||
relevance: 0,
|
||||
},
|
||||
issues: [],
|
||||
};
|
||||
|
||||
// 重置表单
|
||||
setCreateForm({
|
||||
name: "",
|
||||
datasetId: "",
|
||||
evaluationType: "model",
|
||||
dimensions: [],
|
||||
customDimensions: [],
|
||||
modelConfig: {
|
||||
url: "",
|
||||
apiKey: "",
|
||||
prompt: "",
|
||||
temperature: 0.3,
|
||||
maxTokens: 2000,
|
||||
},
|
||||
const formatDimensionsForPrompt = (dimensions: Dimension[]) => {
|
||||
let result = "\n";
|
||||
dimensions.forEach((dim, index) => {
|
||||
result += `### ${index + 1}. ${dim.dimension}\n**评估标准：**\n${dim.description}\n\n`;
|
||||
});
|
||||
navigate("/data/evaluation");
|
||||
return result;
|
||||
};
|
||||
|
||||
const formatResultExample = (dimensions: Dimension[]) => {
|
||||
return dimensions.map(dim => `\n "${dim.dimension}": "Y",`).join('');
|
||||
};
|
||||
|
||||
const fetchPromptTemplates = async () => {
|
||||
try {
|
||||
const response = await queryPromptTemplatesUsingGet();
|
||||
const templates: PromptTemplate[] = response.data?.templates
|
||||
setPromptTemplates(templates)
|
||||
if (taskType) {
|
||||
const template = templates.find(t => t.evalType === taskType);
|
||||
if (template) {
|
||||
setDimensions(template.defaultDimensions.map((dim: any, index: number) => ({
|
||||
key: `dim-${index}`,
|
||||
dimension: dim.dimension,
|
||||
description: dim.description
|
||||
})));
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('Error fetching prompt templates:', error);
|
||||
message.error('获取评估维度失败');
|
||||
}
|
||||
};
|
||||
|
||||
const generateEvaluationPrompt = () => {
|
||||
if (dimensions.length === 0) {
|
||||
message.warning('请先添加评估维度');
|
||||
return;
|
||||
}
|
||||
const template = promptTemplates.find(t => t.evalType === taskType);
|
||||
setEvaluationPrompt(template?.prompt.replace("{dimensions}", formatDimensionsForPrompt(dimensions))
|
||||
.replace('{result_example}', formatResultExample(dimensions)));
|
||||
setPreviewVisible(true);
|
||||
};
|
||||
|
||||
const chatModelOptions = models
|
||||
.filter((model) => model.type === "CHAT")
|
||||
.map((model) => ({
|
||||
label: `${model.modelName} (${model.provider})`,
|
||||
value: model.id,
|
||||
}));
|
||||
|
||||
const handleSubmit = async (values: any) => {
|
||||
if (dimensions.length === 0) {
|
||||
message.warning('请至少添加一个评估维度');
|
||||
return;
|
||||
}
|
||||
|
||||
try {
|
||||
setLoading(true);
|
||||
const { datasetId, modelId, ...rest } = values;
|
||||
const selectedDataset = datasets.find(d => d.id === datasetId);
|
||||
const selectedModel = models.find(d => d.id === modelId);
|
||||
|
||||
const payload = {
|
||||
...rest,
|
||||
sourceType: 'DATASET',
|
||||
sourceId: datasetId,
|
||||
sourceName: selectedDataset?.name,
|
||||
evalConfig: {
|
||||
modelId: selectedModel?.id,
|
||||
dimensions: dimensions.map(d => ({
|
||||
dimension: d.dimension,
|
||||
description: d.description
|
||||
}))
|
||||
}
|
||||
};
|
||||
|
||||
await createEvaluationTaskUsingPost(payload);
|
||||
message.success('评估任务创建成功');
|
||||
onSuccess();
|
||||
form.resetFields();
|
||||
onCancel();
|
||||
} catch (error: any) {
|
||||
console.error('Error creating task:', error);
|
||||
message.error(error.response?.data?.message || '创建评估任务失败');
|
||||
} finally {
|
||||
setLoading(false);
|
||||
}
|
||||
};
|
||||
|
||||
const columns = [
|
||||
{
|
||||
title: '维度',
|
||||
dataIndex: 'dimension',
|
||||
key: 'dimension',
|
||||
width: '30%',
|
||||
},
|
||||
{
|
||||
title: '描述',
|
||||
dataIndex: 'description',
|
||||
key: 'description',
|
||||
width: '60%',
|
||||
},
|
||||
{
|
||||
title: '操作',
|
||||
key: 'action',
|
||||
width: '10%',
|
||||
render: (_: any, record: any) => (
|
||||
<Space size="middle">
|
||||
<a
|
||||
onClick={() => handleDeleteDimension(record.key)}
|
||||
style={{ color: dimensions.length <= 1 ? '#ccc' : '#ff4d4f' }}
|
||||
className={dimensions.length <= 1 ? 'disabled-link' : ''}
|
||||
>
|
||||
删除
|
||||
</a>
|
||||
</Space>
|
||||
),
|
||||
},
|
||||
];
|
||||
|
||||
return (
|
||||
<div className="h-full">
|
||||
{/* 页面头部 */}
|
||||
<div className="flex items-center mb-2">
|
||||
<Button
|
||||
type="text"
|
||||
icon={<ArrowLeftOutlined />}
|
||||
onClick={() => navigate("/data/evaluation")}
|
||||
></Button>
|
||||
<div className="text-xl font-bold">创建评估任务</div>
|
||||
</div>
|
||||
<Modal
|
||||
title="创建评估任务"
|
||||
open={visible}
|
||||
onCancel={onCancel}
|
||||
footer={null}
|
||||
width={800}
|
||||
destroyOnClose
|
||||
>
|
||||
<Form
|
||||
form={form}
|
||||
layout="vertical"
|
||||
onFinish={handleSubmit}
|
||||
initialValues={{
|
||||
evalMethod: DEFAULT_EVAL_METHOD,
|
||||
taskType: DEFAULT_TASK_TYPE,
|
||||
}}
|
||||
>
|
||||
<Row gutter={16}>
|
||||
<Col span={12}>
|
||||
<Form.Item
|
||||
label="任务名称"
|
||||
name="name"
|
||||
rules={[{ required: true, message: '请输入任务名称' }]}
|
||||
>
|
||||
<Input placeholder="输入任务名称" />
|
||||
</Form.Item>
|
||||
</Col>
|
||||
<Col span={12}>
|
||||
<Form.Item
|
||||
label="任务类型"
|
||||
name="taskType"
|
||||
rules={[{ required: true, message: '请选择任务类型' }]}
|
||||
>
|
||||
<Select options={TASK_TYPES} />
|
||||
</Form.Item>
|
||||
</Col>
|
||||
</Row>
|
||||
|
||||
<Form layout="vertical">
|
||||
{/* 基本信息 */}
|
||||
<Card title="基本信息" style={{ marginBottom: 24 }}>
|
||||
<Form.Item label="任务名称" required>
|
||||
<Input
|
||||
value={createForm.name}
|
||||
onChange={(e) =>
|
||||
setCreateForm({ ...createForm, name: e.target.value })
|
||||
}
|
||||
placeholder="输入任务名称"
|
||||
/>
|
||||
</Form.Item>
|
||||
<Form.Item label="选择数据集" required>
|
||||
<Select
|
||||
value={createForm.datasetId || undefined}
|
||||
onChange={(value) =>
|
||||
setCreateForm({ ...createForm, datasetId: value })
|
||||
}
|
||||
placeholder="选择要评估的数据集"
|
||||
>
|
||||
{datasets.map((dataset) => (
|
||||
<Option key={dataset.id} value={dataset.id}>
|
||||
{dataset.name}（{dataset.fileCount} 文件 • {dataset.size}）
|
||||
</Option>
|
||||
))}
|
||||
</Select>
|
||||
</Form.Item>
|
||||
<Form.Item label="评估方式" required>
|
||||
<Select
|
||||
value={createForm.evaluationType}
|
||||
onChange={(value: "model" | "manual") =>
|
||||
setCreateForm({ ...createForm, evaluationType: value })
|
||||
}
|
||||
>
|
||||
<Option value="model">模型自动评估</Option>
|
||||
<Option value="manual">人工评估</Option>
|
||||
</Select>
|
||||
</Form.Item>
|
||||
</Card>
|
||||
|
||||
{/* 算子配置 */}
|
||||
<Card title="切片算子配置" style={{ marginBottom: 24 }}>
|
||||
<Form.Item label="切片算子">
|
||||
<Select
|
||||
value={createForm.sliceConfig.method}
|
||||
onChange={(value) =>
|
||||
setCreateForm({
|
||||
...createForm,
|
||||
sliceConfig: { ...createForm.sliceConfig, method: value },
|
||||
})
|
||||
}
|
||||
placeholder="选择切片算子"
|
||||
>
|
||||
{sliceOperators.map((operator) => (
|
||||
<Option key={operator.id} value={operator.name}>
|
||||
{operator.name}{" "}
|
||||
<Badge style={{ marginLeft: 8 }} count={operator.type} />
|
||||
</Option>
|
||||
))}
|
||||
</Select>
|
||||
</Form.Item>
|
||||
<Form.Item label="分隔符">
|
||||
<Input
|
||||
placeholder="输入分隔符，如 \\n\\n"
|
||||
value={createForm.sliceConfig.delimiter}
|
||||
onChange={(e) =>
|
||||
setCreateForm({
|
||||
...createForm,
|
||||
sliceConfig: {
|
||||
...createForm.sliceConfig,
|
||||
delimiter: e.target.value,
|
||||
},
|
||||
})
|
||||
}
|
||||
/>
|
||||
</Form.Item>
|
||||
<Form.Item label="分块大小">
|
||||
<Input
|
||||
type="number"
|
||||
value={createForm.sliceConfig.chunkSize}
|
||||
onChange={(e) =>
|
||||
setCreateForm({
|
||||
...createForm,
|
||||
sliceConfig: {
|
||||
...createForm.sliceConfig,
|
||||
chunkSize: Number(e.target.value),
|
||||
},
|
||||
})
|
||||
}
|
||||
/>
|
||||
</Form.Item>
|
||||
<Form.Item label="重叠长度">
|
||||
<Input
|
||||
type="number"
|
||||
value={createForm.sliceConfig.overlapLength}
|
||||
onChange={(e) =>
|
||||
setCreateForm({
|
||||
...createForm,
|
||||
sliceConfig: {
|
||||
...createForm.sliceConfig,
|
||||
overlapLength: Number(e.target.value),
|
||||
},
|
||||
})
|
||||
}
|
||||
/>
|
||||
</Form.Item>
|
||||
<Form.Item label="抽样比例">
|
||||
<Input
|
||||
type="number"
|
||||
value={createForm.sliceConfig.threshold}
|
||||
onChange={(e) =>
|
||||
setCreateForm({
|
||||
...createForm,
|
||||
sliceConfig: {
|
||||
...createForm.sliceConfig,
|
||||
threshold: Number(e.target.value),
|
||||
},
|
||||
})
|
||||
}
|
||||
/>
|
||||
</Form.Item>
|
||||
</Card>
|
||||
|
||||
{/* 评估维度配置 */}
|
||||
<Card
|
||||
title={
|
||||
<div
|
||||
style={{
|
||||
display: "flex",
|
||||
justifyContent: "space-between",
|
||||
alignItems: "center",
|
||||
}}
|
||||
>
|
||||
<span>评估维度配置</span>
|
||||
<div style={{ display: "flex", alignItems: "center", gap: 8 }}>
|
||||
<Select
|
||||
value={selectedTemplate}
|
||||
onChange={handleTemplateChange}
|
||||
style={{ width: 160 }}
|
||||
>
|
||||
{Object.entries(evaluationTemplates).map(
|
||||
([key, template]) => (
|
||||
<Option key={key} value={key}>
|
||||
{template.name}
|
||||
</Option>
|
||||
)
|
||||
)}
|
||||
</Select>
|
||||
<Badge
|
||||
count={allDimensions.filter((d) => d.isEnabled).length}
|
||||
style={{ background: "#f0f0f0", color: "#333" }}
|
||||
/>
|
||||
</div>
|
||||
</div>
|
||||
}
|
||||
style={{ marginBottom: 24 }}
|
||||
<Form.Item
|
||||
label="任务描述"
|
||||
name="description"
|
||||
>
|
||||
{/* 维度表格 */}
|
||||
<div
|
||||
style={{
|
||||
border: "1px solid #f0f0f0",
|
||||
borderRadius: 6,
|
||||
marginBottom: 16,
|
||||
}}
|
||||
>
|
||||
<div
|
||||
style={{
|
||||
background: "#fafafa",
|
||||
padding: "8px 12px",
|
||||
borderBottom: "1px solid #f0f0f0",
|
||||
fontWeight: 500,
|
||||
fontSize: 13,
|
||||
}}
|
||||
<Input.TextArea placeholder="输入任务描述（可选）" rows={3} />
|
||||
</Form.Item>
|
||||
|
||||
<Row gutter={16}>
|
||||
<Col span={12}>
|
||||
<Form.Item
|
||||
label="选择数据集"
|
||||
name="datasetId"
|
||||
rules={[{ required: true, message: '请选择数据集' }]}
|
||||
>
|
||||
<div style={{ display: "flex", alignItems: "center" }}>
|
||||
<div style={{ width: 60 }}>启用</div>
|
||||
<div style={{ width: 160 }}>维度名称</div>
|
||||
<div style={{ flex: 1 }}>描述</div>
|
||||
<div style={{ width: 120 }}>操作</div>
|
||||
</div>
|
||||
</div>
|
||||
<div style={{ maxHeight: 320, overflowY: "auto" }}>
|
||||
{allDimensions.map((dimension) => (
|
||||
<div
|
||||
key={dimension.id}
|
||||
style={{
|
||||
display: "flex",
|
||||
alignItems: "center",
|
||||
padding: "8px 12px",
|
||||
borderBottom: "1px solid #f5f5f5",
|
||||
}}
|
||||
>
|
||||
<div style={{ width: 60 }}>
|
||||
<Checkbox
|
||||
checked={dimension.isEnabled}
|
||||
onChange={(e) =>
|
||||
handleDimensionToggle(dimension.id, e.target.checked!)
|
||||
}
|
||||
/>
|
||||
</div>
|
||||
<div style={{ width: 160 }}>
|
||||
{editingDimension === dimension.id && dimension.isCustom ? (
|
||||
<Input
|
||||
value={dimension.name}
|
||||
onChange={(e) =>
|
||||
handleEditDimension(
|
||||
dimension.id,
|
||||
"name",
|
||||
e.target.value
|
||||
)
|
||||
}
|
||||
size="small"
|
||||
/>
|
||||
) : (
|
||||
<span style={{ fontWeight: 500 }}>
|
||||
{dimension.name}
|
||||
{dimension.isCustom && (
|
||||
<Badge
|
||||
style={{
|
||||
marginLeft: 4,
|
||||
background: "#f9f0ff",
|
||||
color: "#722ed1",
|
||||
}}
|
||||
count="自定义"
|
||||
/>
|
||||
)}
|
||||
</span>
|
||||
)}
|
||||
</div>
|
||||
<div style={{ flex: 1 }}>
|
||||
{editingDimension === dimension.id && dimension.isCustom ? (
|
||||
<Input
|
||||
value={dimension.description}
|
||||
onChange={(e) =>
|
||||
handleEditDimension(
|
||||
dimension.id,
|
||||
"description",
|
||||
e.target.value
|
||||
)
|
||||
}
|
||||
size="small"
|
||||
/>
|
||||
) : (
|
||||
<span style={{ color: "#888" }}>
|
||||
{dimension.description}
|
||||
</span>
|
||||
)}
|
||||
</div>
|
||||
<div style={{ width: 120 }}>
|
||||
{editingDimension === dimension.id && dimension.isCustom ? (
|
||||
<Button
|
||||
type="text"
|
||||
icon={<SaveOutlined />}
|
||||
size="small"
|
||||
onClick={() => setEditingDimension(null)}
|
||||
/>
|
||||
) : (
|
||||
dimension.isCustom && (
|
||||
<Button
|
||||
type="text"
|
||||
icon={<EditOutlined />}
|
||||
size="small"
|
||||
onClick={() => setEditingDimension(dimension.id)}
|
||||
/>
|
||||
)
|
||||
)}
|
||||
<Button
|
||||
type="text"
|
||||
icon={<DeleteOutlined />}
|
||||
size="small"
|
||||
danger
|
||||
onClick={() =>
|
||||
dimension.isCustom
|
||||
? handleDeleteCustomDimension(dimension.id)
|
||||
: handleDeletePresetDimension(dimension.id)
|
||||
}
|
||||
disabled={
|
||||
allDimensions.filter((d) => d.isEnabled).length <= 1 &&
|
||||
dimension.isEnabled
|
||||
}
|
||||
/>
|
||||
</div>
|
||||
<Select
|
||||
placeholder="请选择要评估的数据集"
|
||||
showSearch
|
||||
optionFilterProp="label"
|
||||
>
|
||||
{datasets.map((dataset) => (
|
||||
<Select.Option key={dataset.id} value={dataset.id} label={dataset.name}>
|
||||
<div className="flex justify-between w-full">
|
||||
<span>{dataset.name}</span>
|
||||
<span className="text-gray-500">{dataset.size}</span>
|
||||
</div>
|
||||
</Select.Option>
|
||||
))}
|
||||
</Select>
|
||||
</Form.Item>
|
||||
</Col>
|
||||
<Col span={12}>
|
||||
<Form.Item
|
||||
label="评估方式"
|
||||
name="evalMethod"
|
||||
initialValue={DEFAULT_EVAL_METHOD}
|
||||
>
|
||||
<Select options={EVAL_METHODS} />
|
||||
</Form.Item>
|
||||
</Col>
|
||||
</Row>
|
||||
|
||||
<Form.Item
|
||||
noStyle
|
||||
shouldUpdate={(prevValues, currentValues) =>
|
||||
prevValues.evalMethod !== currentValues.evalMethod
|
||||
}
|
||||
>
|
||||
{({ getFieldValue }) => getFieldValue('evalMethod') === 'AUTO' && (
|
||||
<>
|
||||
<Form.Item
|
||||
label="评估模型"
|
||||
name="modelId"
|
||||
rules={[{ required: true, message: '请选择评估模型' }]}
|
||||
>
|
||||
<Select
|
||||
placeholder="请选择模型"
|
||||
options={chatModelOptions}
|
||||
showSearch
|
||||
optionFilterProp="label"
|
||||
/>
|
||||
</Form.Item>
|
||||
|
||||
<Form.Item label="评估维度">
|
||||
<Table
|
||||
columns={columns}
|
||||
dataSource={dimensions}
|
||||
pagination={false}
|
||||
size="small"
|
||||
rowKey="key"
|
||||
/>
|
||||
<div style={{ display: 'flex', gap: 8, marginBottom: 16 }}>
|
||||
<Input
|
||||
placeholder="输入维度名称"
|
||||
value={newDimension.dimension}
|
||||
onChange={(e) => setNewDimension({...newDimension, dimension: e.target.value})}
|
||||
style={{ flex: 1 }}
|
||||
/>
|
||||
<Input
|
||||
placeholder="输入维度描述"
|
||||
value={newDimension.description}
|
||||
onChange={(e) => setNewDimension({...newDimension, description: e.target.value})}
|
||||
style={{ flex: 2 }}
|
||||
/>
|
||||
<Button
|
||||
type="primary"
|
||||
onClick={handleAddDimension}
|
||||
disabled={!newDimension.dimension.trim()}
|
||||
>
|
||||
添加维度
|
||||
</Button>
|
||||
</div>
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
{/* 添加自定义维度 */}
|
||||
<div style={{ background: "#fafafa", borderRadius: 6, padding: 16 }}>
|
||||
<div style={{ fontWeight: 500, marginBottom: 8 }}>
|
||||
添加自定义维度
|
||||
</div>
|
||||
<Input
|
||||
value={newDimension.name}
|
||||
onChange={(e) =>
|
||||
setNewDimension({ ...newDimension, name: e.target.value })
|
||||
}
|
||||
placeholder="维度名称"
|
||||
style={{ width: 180, marginRight: 8 }}
|
||||
size="small"
|
||||
/>
|
||||
<Input
|
||||
value={newDimension.description}
|
||||
onChange={(e) =>
|
||||
setNewDimension({
|
||||
...newDimension,
|
||||
description: e.target.value,
|
||||
})
|
||||
}
|
||||
placeholder="维度描述"
|
||||
style={{ width: 260, marginRight: 8 }}
|
||||
size="small"
|
||||
/>
|
||||
</Form.Item>
|
||||
</>
|
||||
)}
|
||||
</Form.Item>
|
||||
<Form.Item>
|
||||
<div style={{ display: 'flex', justifyContent: 'space-between', marginTop: '16px' }}>
|
||||
<Button
|
||||
icon={<PlusOutlined />}
|
||||
onClick={handleAddCustomDimension}
|
||||
disabled={
|
||||
!newDimension.name.trim() || !newDimension.description.trim()
|
||||
}
|
||||
size="small"
|
||||
type="link"
|
||||
icon={<EyeOutlined />}
|
||||
onClick={generateEvaluationPrompt}
|
||||
>
|
||||
添加维度
|
||||
查看评估提示词
|
||||
</Button>
|
||||
</div>
|
||||
</Card>
|
||||
</Form.Item>
|
||||
|
||||
{/* 模型配置（仅在选择模型评估时显示） */}
|
||||
{createForm.evaluationType === "model" && (
|
||||
<Card title="模型配置" style={{ marginBottom: 24 }}>
|
||||
<Form.Item label="模型 URL" required>
|
||||
<Input
|
||||
value={createForm.modelConfig.url}
|
||||
onChange={(e) =>
|
||||
setCreateForm({
|
||||
...createForm,
|
||||
modelConfig: {
|
||||
...createForm.modelConfig,
|
||||
url: e.target.value,
|
||||
},
|
||||
})
|
||||
}
|
||||
placeholder="https://api.openai.com/v1/chat/completions"
|
||||
/>
|
||||
</Form.Item>
|
||||
<Form.Item label="API Key" required>
|
||||
<Input.Password
|
||||
value={createForm.modelConfig.apiKey}
|
||||
onChange={(e) =>
|
||||
setCreateForm({
|
||||
...createForm,
|
||||
modelConfig: {
|
||||
...createForm.modelConfig,
|
||||
apiKey: e.target.value,
|
||||
},
|
||||
})
|
||||
}
|
||||
placeholder="sk-***"
|
||||
/>
|
||||
</Form.Item>
|
||||
</Card>
|
||||
)}
|
||||
|
||||
{/* 操作按钮 */}
|
||||
<Form.Item>
|
||||
<div style={{ display: "flex", justifyContent: "flex-end", gap: 12 }}>
|
||||
<Button onClick={() => navigate("/data/evaluation")}>取消</Button>
|
||||
<Button
|
||||
type="primary"
|
||||
onClick={handleCreateTask}
|
||||
disabled={
|
||||
!createForm.name ||
|
||||
!createForm.datasetId ||
|
||||
allDimensions.filter((d) => d.isEnabled).length === 0 ||
|
||||
(createForm.evaluationType === "model" &&
|
||||
(!createForm.modelConfig.url ||
|
||||
!createForm.modelConfig.apiKey))
|
||||
}
|
||||
>
|
||||
创建评估任务
|
||||
<div style={{ textAlign: 'right' }}>
|
||||
<Button onClick={onCancel} style={{ marginRight: 8 }}>
|
||||
取消
|
||||
</Button>
|
||||
<Button type="primary" htmlType="submit" loading={loading}>
|
||||
创建任务
|
||||
</Button>
|
||||
</div>
|
||||
</Form.Item>
|
||||
</Form>
|
||||
</div>
|
||||
<PreviewPromptModal
|
||||
previewVisible={previewVisible}
|
||||
onCancel={() => setPreviewVisible(false)}
|
||||
evaluationPrompt={evaluationPrompt}
|
||||
/>
|
||||
</Modal>
|
||||
);
|
||||
};
|
||||
|
||||
export default EvaluationTaskCreate;
|
||||
export default CreateTaskModal;
|
||||
|
||||
Reference in New Issue
Block a user