Improve LightRAG knowledge search locator alignment
This commit is contained in:
@@ -0,0 +1,231 @@
|
||||
#!/usr/bin/env node
|
||||
"use strict";
|
||||
|
||||
const assert = require("node:assert");
|
||||
const fs = require("node:fs");
|
||||
const path = require("node:path");
|
||||
const { chromium } = require("playwright");
|
||||
|
||||
const BASE_URL = (process.env.MNOTE_WEB_SMOKE_BASE_URL || "http://127.0.0.1:3000").replace(/\/+$/, "");
|
||||
const ROOT_URI = process.env.MNOTE_KNOWLEDGE_RAG_ROOT_URI || "file:///mnt/Data1T/Mnote_data/users/mnote-e2e/workspaces/my-space";
|
||||
const WORKSPACE_ID = process.env.MNOTE_KNOWLEDGE_RAG_WORKSPACE_ID || "local-ws:mnote-e2e:my-space";
|
||||
const GROUP_QUERY = process.env.MNOTE_KNOWLEDGE_RAG_GROUP_QUERY || "三甲基硅";
|
||||
const SHORT_QUERY = process.env.MNOTE_KNOWLEDGE_RAG_SHORT_QUERY || "吗啉";
|
||||
const TOO_SHORT_QUERY = process.env.MNOTE_KNOWLEDGE_RAG_TOO_SHORT_QUERY || "吗";
|
||||
const OUTPUT_DIR = path.join(process.cwd(), "tmp", "task542-knowledge-rag-search-grouping-and-short-query-smoke");
|
||||
const RESULT_PATH = path.join(OUTPUT_DIR, "result.json");
|
||||
const GROUP_SCREENSHOT_PATH = path.join(OUTPUT_DIR, "grouped-collapsed.png");
|
||||
const EXPANDED_SCREENSHOT_PATH = path.join(OUTPUT_DIR, "grouped-expanded.png");
|
||||
const UI_TIMEOUT_MS = Number(process.env.MNOTE_SMOKE_UI_TIMEOUT_MS || 30_000);
|
||||
const CHROMIUM_EXECUTABLE_PATH = process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH
|
||||
|| ["/usr/bin/google-chrome-stable", "/usr/bin/google-chrome", "/snap/bin/chromium"]
|
||||
.find((candidate) => fs.existsSync(candidate));
|
||||
|
||||
async function main() {
|
||||
fs.mkdirSync(OUTPUT_DIR, { recursive: true });
|
||||
const browser = await chromium.launch({ headless: true, executablePath: CHROMIUM_EXECUTABLE_PATH });
|
||||
const context = await browser.newContext({ viewport: { width: 1360, height: 900 } });
|
||||
try {
|
||||
const auth = await context.request.post(`${BASE_URL}/api/auth`, {
|
||||
data: {
|
||||
action: "auth:signIn",
|
||||
args: {
|
||||
provider: "password",
|
||||
params: {
|
||||
email: "mnote.e2e@example.com",
|
||||
password: process.env.MNOTE_E2E_PASSWORD || "MnoteE2E123!",
|
||||
flow: "signIn",
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
assert(auth.ok(), `登录失败: ${auth.status()} ${await auth.text()}`);
|
||||
|
||||
const localSearch = await context.request.post(`${BASE_URL}/api/search/documents`, {
|
||||
data: {
|
||||
workspaceId: WORKSPACE_ID,
|
||||
sourceKind: "local_folder",
|
||||
rootUri: ROOT_URI,
|
||||
query: SHORT_QUERY,
|
||||
limit: 30,
|
||||
filters: {
|
||||
includeOcr: false,
|
||||
titleOnly: false,
|
||||
exact: false,
|
||||
onlyCurrentPage: false,
|
||||
timeRange: "any",
|
||||
timeField: "updated",
|
||||
},
|
||||
},
|
||||
});
|
||||
assert(localSearch.ok(), `本地搜索失败: ${localSearch.status()} ${await localSearch.text()}`);
|
||||
const localPayload = await localSearch.json();
|
||||
assert.equal(localPayload.results?.length || 0, 0, `本地文档搜索不应把两字 CJK query 匹配到无关文档: ${JSON.stringify(localPayload.results?.slice(0, 3), null, 2)}`);
|
||||
|
||||
const knowledgeSearch = await context.request.post(`${BASE_URL}/api/knowledge-rag/search`, {
|
||||
data: {
|
||||
workspaceId: WORKSPACE_ID,
|
||||
rootUri: ROOT_URI,
|
||||
query: SHORT_QUERY,
|
||||
mode: "mix",
|
||||
topK: 12,
|
||||
chunkTopK: 24,
|
||||
includeChunkContent: true,
|
||||
},
|
||||
});
|
||||
assert(knowledgeSearch.ok(), `资料库短 query 检索失败: ${knowledgeSearch.status()} ${await knowledgeSearch.text()}`);
|
||||
const knowledgePayload = await knowledgeSearch.json();
|
||||
assert((knowledgePayload.results?.length || 0) >= 8, `资料库 2 字 query 应返回段落去重后的 LightRAG 检索命中: ${JSON.stringify(knowledgePayload, null, 2).slice(0, 2000)}`);
|
||||
assert(String(knowledgePayload.results?.[0]?.snippet || "").includes(SHORT_QUERY), `资料库结果未包含 ${SHORT_QUERY}: ${JSON.stringify(knowledgePayload.results?.[0], null, 2)}`);
|
||||
assert(knowledgePayload.references?.some((reference) => reference.matchSource === "lightrag_search"), `2 字 query 应走 LightRAG search provider: ${JSON.stringify(knowledgePayload.references?.slice(0, 3), null, 2)}`);
|
||||
|
||||
const tooShortSearch = await context.request.post(`${BASE_URL}/api/knowledge-rag/search`, {
|
||||
data: {
|
||||
workspaceId: WORKSPACE_ID,
|
||||
rootUri: ROOT_URI,
|
||||
query: TOO_SHORT_QUERY,
|
||||
mode: "mix",
|
||||
topK: 12,
|
||||
chunkTopK: 24,
|
||||
includeChunkContent: true,
|
||||
},
|
||||
});
|
||||
assert.equal(tooShortSearch.status(), 400, `资料库 1 字 query 应返回 400: ${tooShortSearch.status()} ${await tooShortSearch.text()}`);
|
||||
const tooShortPayload = await tooShortSearch.json();
|
||||
assert.equal(tooShortPayload.code, "knowledge_rag_search_query_too_short", `1 字 query 错误码不符合预期: ${JSON.stringify(tooShortPayload)}`);
|
||||
assert(String(tooShortPayload.message || "").includes("至少 2 个字"), `1 字 query 提示不符合预期: ${JSON.stringify(tooShortPayload)}`);
|
||||
|
||||
const page = await context.newPage();
|
||||
const pageErrors = [];
|
||||
const consoleErrors = [];
|
||||
page.on("pageerror", (error) => pageErrors.push(String(error?.stack || error?.message || error)));
|
||||
page.on("console", (message) => {
|
||||
if (["error", "warning"].includes(message.type())) consoleErrors.push(`${message.type()}: ${message.text()}`);
|
||||
});
|
||||
await page.goto(`${BASE_URL}/`, { waitUntil: "domcontentloaded", timeout: UI_TIMEOUT_MS });
|
||||
await page.evaluate(() => {
|
||||
window.localStorage?.setItem("mnote.search.collapseSourcesDefault.v1", "1");
|
||||
});
|
||||
await page.waitForSelector('[data-mnote-action="open-search-modal"]', { timeout: UI_TIMEOUT_MS });
|
||||
await page.click('[data-mnote-action="open-search-modal"]');
|
||||
await page.waitForSelector('[data-testid="wolai-search-input"]', { timeout: UI_TIMEOUT_MS });
|
||||
await page.evaluate(() => {
|
||||
const knowledge = document.querySelector('[data-search-switch="knowledge"]');
|
||||
if (knowledge instanceof HTMLElement) {
|
||||
knowledge.setAttribute("aria-checked", "true");
|
||||
knowledge.classList.add("is-on");
|
||||
}
|
||||
const collapse = document.querySelector('[data-search-switch="collapseSource"]');
|
||||
if (collapse instanceof HTMLElement) {
|
||||
collapse.setAttribute("aria-checked", "true");
|
||||
collapse.classList.add("is-on");
|
||||
}
|
||||
});
|
||||
await page.fill('[data-testid="wolai-search-input"]', TOO_SHORT_QUERY);
|
||||
await page.evaluate(() => {
|
||||
document.querySelector('[data-testid="wolai-search-input"]')
|
||||
?.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
});
|
||||
await page.waitForSelector('[data-search-empty="true"]', { timeout: UI_TIMEOUT_MS });
|
||||
const tooShortUi = await page.evaluate(() => ({
|
||||
meta: document.querySelector('[data-testid="wolai-search-result-meta"]')?.textContent || "",
|
||||
empty: document.querySelector('[data-search-empty="true"]')?.textContent || "",
|
||||
rows: document.querySelectorAll('[data-testid="wolai-search-result-row"]').length,
|
||||
}));
|
||||
assert(tooShortUi.empty.includes("至少 2 个字"), `1 字 query UI 未提示至少 2 个字: ${JSON.stringify(tooShortUi)}`);
|
||||
assert.equal(tooShortUi.rows, 0, `1 字 query 不应发起并渲染结果: ${JSON.stringify(tooShortUi)}`);
|
||||
|
||||
await page.fill('[data-testid="wolai-search-input"]', GROUP_QUERY);
|
||||
await page.evaluate(() => {
|
||||
document.querySelector('[data-testid="wolai-search-input"]')
|
||||
?.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
});
|
||||
await page.waitForSelector(".wolai-search-source-group", { timeout: UI_TIMEOUT_MS });
|
||||
const collapsed = await page.evaluate(() => ({
|
||||
switchOn: document.querySelector('[data-search-switch="collapseSource"]')?.getAttribute("aria-checked") === "true",
|
||||
groups: document.querySelectorAll(".wolai-search-source-group").length,
|
||||
visibleRows: Array.from(document.querySelectorAll('[data-testid="wolai-search-result-row"]'))
|
||||
.filter((row) => row.offsetParent !== null).length,
|
||||
meta: document.querySelector('[data-testid="wolai-search-result-meta"]')?.textContent || "",
|
||||
firstHeader: document.querySelector(".wolai-search-source-header")?.textContent || "",
|
||||
}));
|
||||
await page.screenshot({ path: GROUP_SCREENSHOT_PATH, fullPage: true });
|
||||
assert.equal(collapsed.switchOn, true, `折叠同来源开关未默认打开: ${JSON.stringify(collapsed)}`);
|
||||
assert(collapsed.groups >= 1, `未按来源分组: ${JSON.stringify(collapsed)}`);
|
||||
assert.equal(collapsed.visibleRows, 0, `默认折叠时不应展示重复来源子结果: ${JSON.stringify(collapsed)}`);
|
||||
assert(
|
||||
!String(collapsed.firstHeader || "").includes("有机合成中的保护基/[OCR]"),
|
||||
`来源组标题不应再在标题下重复显示完整来源路径: ${JSON.stringify(collapsed)}`
|
||||
);
|
||||
|
||||
await page.click(".wolai-search-source-header");
|
||||
await page.waitForFunction(() => {
|
||||
return Array.from(document.querySelectorAll('[data-testid="wolai-search-result-row"]'))
|
||||
.some((row) => row.offsetParent !== null);
|
||||
}, null, { timeout: UI_TIMEOUT_MS });
|
||||
const expanded = await page.evaluate(() => ({
|
||||
expanded: document.querySelector(".wolai-search-source-header")?.getAttribute("aria-expanded") === "true",
|
||||
visibleRows: Array.from(document.querySelectorAll('[data-testid="wolai-search-result-row"]'))
|
||||
.filter((row) => row.offsetParent !== null).length,
|
||||
firstRows: Array.from(document.querySelectorAll('[data-testid="wolai-search-result-row"]'))
|
||||
.slice(0, 3)
|
||||
.map((row) => row.textContent),
|
||||
}));
|
||||
await page.screenshot({ path: EXPANDED_SCREENSHOT_PATH, fullPage: true });
|
||||
assert.equal(expanded.expanded, true, `来源组未展开: ${JSON.stringify(expanded)}`);
|
||||
assert(expanded.visibleRows > 0, `展开后未展示来源下结果: ${JSON.stringify(expanded)}`);
|
||||
assert(
|
||||
expanded.firstRows.every((text) => !String(text || "").includes("有机合成中的保护基/[OCR]")),
|
||||
`折叠同来源展开后,子结果不应重复显示完整来源路径: ${JSON.stringify(expanded.firstRows)}`
|
||||
);
|
||||
assert(
|
||||
expanded.firstRows.every((text) => !String(text || "").trim().endsWith("docx")),
|
||||
`折叠同来源展开后,子结果不应重复显示来源类型: ${JSON.stringify(expanded.firstRows)}`
|
||||
);
|
||||
assert(
|
||||
expanded.firstRows.every((text) => !/(?:<\/?e(?:q(?:uation)?)?\b|<\/?drawing\b|format=["']?latex|\blatex\b)/i.test(String(text || ""))),
|
||||
`资料库搜索结果仍暴露原始公式/绘图标记: ${JSON.stringify(expanded.firstRows)}`
|
||||
);
|
||||
|
||||
const result = {
|
||||
ok: true,
|
||||
baseUrl: BASE_URL,
|
||||
rootUri: ROOT_URI,
|
||||
workspaceId: WORKSPACE_ID,
|
||||
shortQuery: SHORT_QUERY,
|
||||
tooShortQuery: TOO_SHORT_QUERY,
|
||||
groupQuery: GROUP_QUERY,
|
||||
localCount: localPayload.results?.length || 0,
|
||||
knowledgeCount: knowledgePayload.results?.length || 0,
|
||||
knowledgeFirst: {
|
||||
title: knowledgePayload.results?.[0]?.title,
|
||||
snippet: knowledgePayload.results?.[0]?.snippet,
|
||||
blockId: knowledgePayload.results?.[0]?.locator?.blockId,
|
||||
},
|
||||
tooShortUi,
|
||||
collapsed,
|
||||
expanded,
|
||||
pageErrors,
|
||||
consoleErrors,
|
||||
screenshots: {
|
||||
collapsed: GROUP_SCREENSHOT_PATH,
|
||||
expanded: EXPANDED_SCREENSHOT_PATH,
|
||||
},
|
||||
};
|
||||
fs.writeFileSync(RESULT_PATH, `${JSON.stringify(result, null, 2)}\n`, "utf8");
|
||||
console.log(JSON.stringify(result, null, 2));
|
||||
} finally {
|
||||
await browser.close().catch(() => undefined);
|
||||
}
|
||||
}
|
||||
|
||||
main().catch((error) => {
|
||||
fs.mkdirSync(OUTPUT_DIR, { recursive: true });
|
||||
fs.writeFileSync(
|
||||
path.join(OUTPUT_DIR, "failure.json"),
|
||||
`${JSON.stringify({ ok: false, error: error.stack || error.message || String(error) }, null, 2)}\n`,
|
||||
"utf8",
|
||||
);
|
||||
console.error(error.stack || error.message || String(error));
|
||||
process.exit(1);
|
||||
});
|
||||
Reference in New Issue
Block a user