openserp-search
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseWeb search with OpenSERP
使用 OpenSERP 进行网页搜索
OpenSERP returns real results pages from named engines, with original ranks, plus page content as Markdown. Use the MCP tools (, , , , , ). Without MCP, call the HTTP API on (or ).
searchmega_searchany_searchextractbatch_extractlist_engineshttp://localhost:7000$OPENSERP_BASE_URLOpenSERP 会返回指定搜索引擎的真实结果页面及原始排名,并将页面内容转换为 Markdown。可以使用 MCP 工具(、、、、、)。如果没有 MCP,请调用 (或 )上的 HTTP API。
searchmega_searchany_searchextractbatch_extractlist_engineshttp://localhost:7000$OPENSERP_BASE_URLWorkflow
工作流程
- Search one engine first. with
searchfor general queries. Useengine: "google"for Russian-language,yandexfor Chinese-language queries. Keepbaiduat 10 unless you need more.limit - Pick sources by rank and domain. Prefer official docs, release notes and primary sources over aggregators. Skip .
type: "ad" - Read with one call for the 2-4 URLs you need, not repeated
batch_extractcalls. Avoid archive or changelog index pages: they can be hundreds of KB. Pick the single post or section page instead.extract - Answer with links. Cite each claim with the URL you read. Mention the engine and rank when ranking matters (SEO questions).
- 先搜索一个搜索引擎。 对于常规查询,使用 并设置
search。俄语查询使用engine: "google",中文查询使用yandex。除非需要更多结果,否则将baidu保持为 10。limit - 根据排名和域名选择来源。 优先选择官方文档、发布说明和第一手来源,而不是聚合网站。跳过 的结果。
type: "ad" - 只调用一次 ,以读取所需的 2-4 个 URL,不要重复调用
batch_extract。避免使用存档页或变更日志索引页,因为这些页面可能达到数百 KB。应选择具体的文章页或章节页。extract - 回答时附上链接。 每项结论都应引用已阅读页面的 URL。当排名很重要时(SEO 问题),请注明搜索引擎和排名。
When a search fails
搜索失败时
- ,
captcha detectedorblockedfrom one engine: do not retry the same engine more than once. Userate_limitedwithany_search, orengines: ["google", "duckduckgo", "bing"]on another engine.search - Results that do not match the query (unrelated brands, dictionary pages, a single keyword) mean the engine served a degraded page. Treat them as a failure and switch engine; do not use them as evidence.
- An empty result set is not proof that nothing exists. Rephrase once or try another engine.
- In , an item with
batch_extractfailed; the others are still valid.metadata.error
- 如果某个搜索引擎返回 、
captcha detected或blocked,不要以相同搜索引擎重试超过一次。请使用rate_limited并设置any_search,或改用其他搜索引擎执行engines: ["google", "duckduckgo", "bing"]。search - 如果结果与查询不匹配(出现无关品牌、词典页面或仅有单个关键词),说明该搜索引擎返回了降级页面。将其视为搜索失败并切换搜索引擎;不要将这些结果作为证据。
- 空结果集并不能证明不存在相关内容。可以重新表述一次查询,或尝试其他搜索引擎。
- 在 中,如果某个条目出现
batch_extract,则表示该条目提取失败;其他条目仍然有效。metadata.error
HTTP fallback
HTTP 回退方案
bash
curl "http://localhost:7000/google/search?text=QUERY&limit=10"
curl "http://localhost:7000/mega/search?text=QUERY&engines=google,duckduckgo&mode=any"
curl -X POST "http://localhost:7000/extract/batch" -H "Content-Type: application/json" \
-d '{"urls":["https://example.com/a","https://example.com/b"],"mode":"auto"}'extract=Nbash
curl "http://localhost:7000/google/search?text=QUERY&limit=10"
curl "http://localhost:7000/mega/search?text=QUERY&engines=google,duckduckgo&mode=any"
curl -X POST "http://localhost:7000/extract/batch" -H "Content-Type: application/json" \
-d '{"urls":["https://example.com/a","https://example.com/b"],"mode":"auto"}'extract=N