feat: add weight config panel to 新建评估 and weighted_score card to report
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@@ -127,6 +127,18 @@ const Report = {
|
||||
`;
|
||||
wrap.appendChild(card);
|
||||
});
|
||||
|
||||
// 综合加权得分卡片
|
||||
const wsValue = (report && report.weighted_score_mean !== undefined) ? report.weighted_score_mean : null;
|
||||
const wsCard = document.createElement("div");
|
||||
wsCard.className = "metric-card weighted-score-card";
|
||||
const wsCls = App.scoreClass(wsValue);
|
||||
const wsText = wsValue === null || wsValue === undefined ? "n/a" : wsValue.toFixed(2);
|
||||
wsCard.innerHTML = `
|
||||
<div class="metric-value ${wsCls}">${wsText}</div>
|
||||
<div class="metric-name">综合加权得分</div>
|
||||
`;
|
||||
wrap.appendChild(wsCard);
|
||||
},
|
||||
|
||||
// ② 分数分布直方图(可切换指标)。
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
// runner.js — 新建评估视图:列出场景、LLM角色配置、触发评估、轮询任务状态与日志。
|
||||
// runner.js — 新建评估视图:列出场景、LLM角色配置、权重配置、触发评估、轮询任务状态。
|
||||
|
||||
const Runner = {
|
||||
selectedScenario: null,
|
||||
selectedScenarioInfo: null,
|
||||
pollTimer: null,
|
||||
lastRunId: null,
|
||||
|
||||
// 绑定运行按钮。
|
||||
init() {
|
||||
document.getElementById("run-btn").addEventListener("click", () => Runner.trigger());
|
||||
document.getElementById("view-report-btn").addEventListener("click", () => {
|
||||
@@ -14,9 +14,9 @@ const Runner = {
|
||||
App.navigate("report", Runner.lastRunId);
|
||||
}
|
||||
});
|
||||
document.getElementById("add-doc-weight-btn").addEventListener("click", () => Runner._addDocWeightRow());
|
||||
},
|
||||
|
||||
// 加载并渲染可触发的场景列表。
|
||||
async loadScenarios() {
|
||||
const list = document.getElementById("scenario-list");
|
||||
list.innerHTML = '<p class="muted">加载中…</p>';
|
||||
@@ -32,17 +32,14 @@ const Runner = {
|
||||
} catch (err) {
|
||||
list.innerHTML = `<p class="muted">加载失败:${App.escape(err.message)}</p>`;
|
||||
}
|
||||
// 同时加载 profiles 供角色选择
|
||||
Runner._populateProfileSelects();
|
||||
},
|
||||
|
||||
// 填充三个角色下拉框
|
||||
async _populateProfileSelects() {
|
||||
const cached = Profiles.getAll();
|
||||
const profiles = cached.length > 0
|
||||
? cached
|
||||
: (await API.profiles().catch(() => ({ profiles: [] }))).profiles;
|
||||
|
||||
["role-judge", "role-answer", "role-dataset"].forEach(id => {
|
||||
const sel = document.getElementById(id);
|
||||
sel.innerHTML = '<option value="">— 使用场景原始配置 —</option>';
|
||||
@@ -55,17 +52,14 @@ const Runner = {
|
||||
});
|
||||
},
|
||||
|
||||
// 构造单个场景条目。
|
||||
renderScenarioItem(sc) {
|
||||
const item = document.createElement("div");
|
||||
const invalid = !!sc.error;
|
||||
item.className = "scenario-item" + (invalid ? " invalid" : "");
|
||||
|
||||
const modeTag = sc.mode
|
||||
? `<span class="tag mode-${App.escape(sc.mode)}">${App.escape(sc.mode)}</span>`
|
||||
: "";
|
||||
const metricCount = (sc.metrics || []).length;
|
||||
|
||||
item.innerHTML = `
|
||||
<div>
|
||||
<div class="scenario-name">${App.escape(sc.scenario_name || sc.path)}</div>
|
||||
@@ -77,27 +71,94 @@ const Runner = {
|
||||
<span class="tag">${metricCount} 指标</span>
|
||||
</div>
|
||||
`;
|
||||
|
||||
if (!invalid) {
|
||||
item.addEventListener("click", () => {
|
||||
document.querySelectorAll(".scenario-item").forEach((el) => el.classList.remove("selected"));
|
||||
item.classList.add("selected");
|
||||
Runner.selectedScenario = sc.path;
|
||||
Runner.selectedScenarioInfo = sc;
|
||||
document.getElementById("selected-scenario").textContent = sc.path;
|
||||
document.getElementById("run-btn").disabled = false;
|
||||
// 显示 LLM 角色面板
|
||||
document.getElementById("llm-assignment-panel").hidden = false;
|
||||
Runner._renderWeightPanel(sc);
|
||||
document.getElementById("weight-config-panel").hidden = false;
|
||||
});
|
||||
}
|
||||
return item;
|
||||
},
|
||||
|
||||
// 触发评估:先 apply profiles(若选了),再触发任务。
|
||||
// 根据选中场景渲染指标权重行(动态生成,按场景 metrics 列表)
|
||||
_renderWeightPanel(sc) {
|
||||
const metricRows = document.getElementById("metric-weight-rows");
|
||||
metricRows.innerHTML = "";
|
||||
const metrics = sc.metrics || [];
|
||||
const existingWeights = sc.metric_weights || {};
|
||||
metrics.forEach(metric => {
|
||||
const row = document.createElement("div");
|
||||
row.className = "weight-row";
|
||||
const currentVal = existingWeights[metric] != null ? existingWeights[metric] : 1.0;
|
||||
row.innerHTML = `
|
||||
<span class="weight-row-label">${App.escape(metric)}</span>
|
||||
<input class="weight-row-input" type="number" min="0" step="0.1"
|
||||
data-metric="${App.escape(metric)}" value="${currentVal}" />
|
||||
`;
|
||||
metricRows.appendChild(row);
|
||||
});
|
||||
|
||||
// 填充已有文档权重
|
||||
const docRows = document.getElementById("doc-weight-rows");
|
||||
docRows.innerHTML = "";
|
||||
const existingDocWeights = sc.doc_weights || {};
|
||||
Object.entries(existingDocWeights).forEach(([docName, w]) => {
|
||||
Runner._addDocWeightRow(docName, w);
|
||||
});
|
||||
},
|
||||
|
||||
// 添加一行文档权重输入
|
||||
_addDocWeightRow(docName, weight) {
|
||||
const name = docName !== undefined ? docName : "";
|
||||
const w = weight !== undefined ? weight : 1.0;
|
||||
const container = document.getElementById("doc-weight-rows");
|
||||
const row = document.createElement("div");
|
||||
row.className = "weight-row";
|
||||
row.innerHTML = `
|
||||
<input class="doc-weight-name" type="text" placeholder="PDF 文件名(如 322_双源CT.pdf)" value="${App.escape(String(name))}" />
|
||||
<input class="weight-row-input" type="number" min="0" step="0.1" value="${w}" />
|
||||
<button class="weight-row-remove" title="删除">✕</button>
|
||||
`;
|
||||
row.querySelector(".weight-row-remove").addEventListener("click", () => row.remove());
|
||||
container.appendChild(row);
|
||||
},
|
||||
|
||||
// 收集权重面板当前值;全等权时返回 null(不发送)
|
||||
_collectWeights() {
|
||||
const metricWeights = {};
|
||||
document.querySelectorAll("#metric-weight-rows .weight-row-input").forEach(input => {
|
||||
const metric = input.dataset.metric;
|
||||
const val = parseFloat(input.value);
|
||||
if (metric && !isNaN(val)) metricWeights[metric] = val;
|
||||
});
|
||||
|
||||
const docWeights = {};
|
||||
document.querySelectorAll("#doc-weight-rows .weight-row").forEach(row => {
|
||||
const nameInput = row.querySelector(".doc-weight-name");
|
||||
const valInput = row.querySelector(".weight-row-input");
|
||||
if (!nameInput || !valInput) return;
|
||||
const name = nameInput.value.trim();
|
||||
const val = parseFloat(valInput.value);
|
||||
if (name && !isNaN(val)) docWeights[name] = val;
|
||||
});
|
||||
|
||||
const allMetricDefault = Object.values(metricWeights).every(v => Math.abs(v - 1.0) < 1e-9);
|
||||
const noDocWeights = Object.keys(docWeights).length === 0;
|
||||
if (allMetricDefault && noDocWeights) return { metricWeights: null, docWeights: null };
|
||||
return { metricWeights, docWeights };
|
||||
},
|
||||
|
||||
async trigger() {
|
||||
if (!Runner.selectedScenario) return;
|
||||
const runBtn = document.getElementById("run-btn");
|
||||
runBtn.disabled = true;
|
||||
|
||||
const panel = document.getElementById("task-panel");
|
||||
const logBox = document.getElementById("task-log");
|
||||
const statusBadge = document.getElementById("task-status");
|
||||
@@ -106,12 +167,8 @@ const Runner = {
|
||||
reportBtn.hidden = true;
|
||||
logBox.textContent = "";
|
||||
Runner._setStatus(statusBadge, "queued");
|
||||
|
||||
try {
|
||||
// Step 1: apply LLM profiles to YAML if any selected
|
||||
await Runner._applyProfilesIfNeeded(logBox);
|
||||
|
||||
// Step 2: trigger evaluation
|
||||
const resp = await API.triggerEvaluation(Runner.selectedScenario);
|
||||
Runner.poll(resp.task_id);
|
||||
} catch (err) {
|
||||
@@ -121,20 +178,22 @@ const Runner = {
|
||||
}
|
||||
},
|
||||
|
||||
// 如果用户选了 profile,就先 apply 写回 YAML
|
||||
async _applyProfilesIfNeeded(logBox) {
|
||||
const judgeId = document.getElementById("role-judge").value;
|
||||
const answerId = document.getElementById("role-answer").value;
|
||||
const datasetId = document.getElementById("role-dataset").value;
|
||||
const { metricWeights, docWeights } = Runner._collectWeights();
|
||||
|
||||
if (!judgeId && !answerId && !datasetId) return; // 全空,跳过
|
||||
if (!judgeId && !answerId && !datasetId && !metricWeights && !docWeights) return;
|
||||
|
||||
logBox.textContent = "正在将 LLM 配置写入场景文件…\n";
|
||||
logBox.textContent = "正在将 LLM 配置和权重写入场景文件…\n";
|
||||
const body = {
|
||||
scenario_path: Runner.selectedScenario,
|
||||
judge_profile_id: judgeId || null,
|
||||
answer_profile_id: answerId || null,
|
||||
dataset_profile_id: datasetId || null,
|
||||
metric_weights: metricWeights,
|
||||
doc_weights: docWeights,
|
||||
};
|
||||
const result = await API.applyProfiles(body);
|
||||
const fields = (result.patched_fields || []).join(", ");
|
||||
@@ -143,13 +202,11 @@ const Runner = {
|
||||
: "(未找到可更新的字段,继续运行)\n";
|
||||
},
|
||||
|
||||
// 周期性轮询任务状态,刷新日志与徽标。
|
||||
poll(taskId) {
|
||||
const logBox = document.getElementById("task-log");
|
||||
const statusBadge = document.getElementById("task-status");
|
||||
const reportBtn = document.getElementById("view-report-btn");
|
||||
const runBtn = document.getElementById("run-btn");
|
||||
|
||||
if (Runner.pollTimer) clearInterval(Runner.pollTimer);
|
||||
Runner.pollTimer = setInterval(async () => {
|
||||
try {
|
||||
@@ -157,7 +214,6 @@ const Runner = {
|
||||
logBox.textContent = (status.logs || []).join("\n");
|
||||
logBox.scrollTop = logBox.scrollHeight;
|
||||
Runner._setStatus(statusBadge, status.status);
|
||||
|
||||
if (status.status === "completed" || status.status === "failed") {
|
||||
clearInterval(Runner.pollTimer);
|
||||
runBtn.disabled = false;
|
||||
@@ -175,7 +231,6 @@ const Runner = {
|
||||
}, 1200);
|
||||
},
|
||||
|
||||
// 更新状态徽标的文本与配色类。
|
||||
_setStatus(badge, status) {
|
||||
badge.textContent = status;
|
||||
badge.className = "badge " + status;
|
||||
|
||||
Reference in New Issue
Block a user