parallel-ai-search
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseParallel AI Search (CLI Master)
Parallel AI 搜索(CLI 主控技能)
This is a single “master” skill that replaces the earlier Node-script-based version of .
parallel-ai-searchIt routes to the right capability for the task:
parallel-cli- Search: quick web lookup with citations ()
parallel-cli search - Extract: turn URLs (including PDFs and JS-heavy pages) into clean, LLM-ready text ()
parallel-cli extract - Deep research: multi-source reports with processor tiers ()
parallel-cli research ... - Enrich: add web-sourced columns to CSV/JSON ()
parallel-cli enrich ... - FindAll: discover entities from the web with optional enrichments ()
parallel-cli findall ... - Monitor: track web changes on a cadence, optionally via webhook ()
parallel-cli monitor ...
这是一项单一的“主控”技能,取代了早期基于Node脚本的版本。
parallel-ai-search它会根据任务需求路由到对应的功能:
parallel-cli- 搜索:带引用的快速网页查询()
parallel-cli search - 提取:将URL(包括PDF和JS渲染页面)转换为适合LLM处理的整洁文本()
parallel-cli extract - 深度研究:带处理器层级的多来源报告()
parallel-cli research ... - 增强:为CSV/JSON添加网页来源的列()
parallel-cli enrich ... - FindAll:从网页中发现实体并可选择进行增强()
parallel-cli findall ... - 监控:按周期跟踪网页变化,可通过webhook推送()
parallel-cli monitor ...
Routing rules (pick ONE)
路由规则(选择其中一项)
Choose the smallest / cheapest action that solves the user’s request:
- Extract — if the user gives one or more URLs or says “read/summarise this page”, “extract”, “quote”, “pull the content”, “what does this page say”.
- Deep research — ONLY if the user explicitly asks for deep, exhaustive, comprehensive, thorough investigation, or a multi-source “report”.
- Enrich — if the user provides a list/table (CSV/JSON/inline objects) and wants new columns like CEO, revenue, funding, contact info, etc.
- FindAll — if the user wants you to discover many entities (companies/people/venues/etc.) that match criteria.
- Monitor — if the user wants ongoing tracking (“alert me”, “track changes”, “monitor this weekly”) rather than a one-off answer.
- Search — default for everything else that needs current web info or citations.
Optional manual prefixes if the user invoked this skill directly:
search: ...extract: ...research: ...enrich: ...findall: ...monitor: ...
If a prefix is present, honour it.
选择能解决用户需求的最小/成本最低的操作:
- 提取 — 如果用户提供一个或多个URL,或者提到“读取/总结这个页面”、“提取”、“引用”、“获取内容”、“这个页面讲了什么”。
- 深度研究 — 仅当用户明确要求深度、详尽、全面、彻底调查,或者需要多来源“报告”时使用。
- 增强 — 如果用户提供列表/表格(CSV/JSON/内联对象),并希望添加CEO、收入、融资、联系信息等新列。
- FindAll — 如果用户希望你发现符合条件的大量实体(公司/人物/场所等)。
- 监控 — 如果用户需要持续跟踪(“提醒我”、“跟踪变化”、“每周监控这个内容”)而非一次性答案。
- 搜索 — 所有其他需要最新网页信息或引用的默认选项。
如果用户直接调用此技能,可使用可选的手动前缀:
search: ...extract: ...research: ...enrich: ...findall: ...monitor: ...
如果存在前缀,请遵循该前缀执行操作。
Setup and authentication (only when needed)
设置与身份验证(仅在需要时进行)
Before running any Parallel command, ensure auth works:
bash
parallel-cli authIf is missing, install it:
parallel-clibash
curl -fsSL https://parallel.ai/install.sh | bashIf you cannot use the install script, use pipx:
bash
pipx install "parallel-web-tools[cli]"
pipx ensurepathThen authenticate (choose one):
bash
undefined运行任何Parallel命令前,请确保身份验证正常:
bash
parallel-cli auth如果缺少,请安装:
parallel-clibash
curl -fsSL https://parallel.ai/install.sh | bash如果无法使用安装脚本,可使用pipx:
bash
pipx install "parallel-web-tools[cli]"
pipx ensurepath然后进行身份验证(选择其中一种方式):
bash
undefinedInteractive OAuth (opens browser)
交互式OAuth(打开浏览器)
parallel-cli login
parallel-cli login
Headless / SSH / CI
无界面/SSH/CI环境
parallel-cli login --device
parallel-cli login --device
Or environment variable
或使用环境变量
export PARALLEL_API_KEY="your_api_key"
undefinedexport PARALLEL_API_KEY="your_api_key"
undefinedOutput & citation rules
输出与引用规则
- Always cite web-sourced facts with inline markdown links: .
[Source Title](https://...) - End with a Sources list whenever you used Search/Extract/Research output.
- Prefer official/primary sources when available.
- For long outputs, save to files in and summarise in-chat.
/tmp/
- 始终使用内嵌markdown链接引用网页来源的事实:。
[来源标题](https://...) - 只要使用了搜索/提取/研究的输出,结尾必须附上来源列表。
- 优先使用官方/原始来源(如果可用)。
- 对于长输出,保存到目录下的文件中,并在对话中提供摘要。
/tmp/
Search (default web lookup)
搜索(默认网页查询)
Use Search for fast, cost-effective answers with citations.
使用搜索功能获取带引用的快速、高性价比答案。
Command template
命令模板
bash
parallel-cli search "$OBJECTIVE" --mode agentic --max-results 10 --jsonAdd any of these only when relevant:
- (freshness constraint)
--after-date YYYY-MM-DD - (restrict sources)
--include-domains a.com b.org - (block sources)
--exclude-domains spam.com - one or more flags (extra keyword probes)
-q "keyword query" - (save full JSON to a file)
-o "/tmp/$SLUG.search.json"
bash
parallel-cli search "$OBJECTIVE" --mode agentic --max-results 10 --json仅在相关时添加以下参数:
- (新鲜度限制)
--after-date YYYY-MM-DD - (限制来源域名)
--include-domains a.com b.org - (屏蔽来源域名)
--exclude-domains spam.com - 一个或多个 标志(额外关键词查询)
-q "keyword query" - (将完整JSON保存到文件)
-o "/tmp/$SLUG.search.json"
Parse + respond
解析与回复
From the JSON results, extract title, url, and any publish_date / excerpt fields.
Answer the user’s question, and cite each claim inline.
从JSON结果中提取标题、url以及任何发布日期/摘要字段。
回答用户的问题,并为每个主张添加内嵌引用。
Extract (read one or more URLs)
提取(读取一个或多个URL)
Use Extract when you need the actual contents of specific URLs (webpages, PDFs, JS-heavy sites).
当你需要获取特定URL(网页、PDF、JS渲染网站)的实际内容时,使用提取功能。
Command template
命令模板
bash
parallel-cli extract "$URL" --jsonAdd when relevant:
- (e.g., pricing, API usage, constraints)
--objective "Focus area" - (only if the user needs the whole page)
--full-content - (if you only want full content)
--no-excerpts - (save full JSON to a file)
-o "/tmp/$SLUG.extract.json"
bash
parallel-cli extract "$URL" --json相关时添加以下参数:
- (重点领域,例如定价、API使用、限制条件)
--objective "Focus area" - (仅当用户需要完整页面内容时使用)
--full-content - (如果只需要完整内容)
--no-excerpts - (将完整JSON保存到文件)
-o "/tmp/$SLUG.extract.json"
Respond
回复
- If the user asked for a summary, summarise with citations to the extracted URL.
- If the user asked for the verbatim text, provide the extracted markdown only if it is reasonably sized; otherwise provide the key sections + offer to read more from the saved output.
- 如果用户要求摘要,则生成摘要并引用提取的URL。
- 如果用户要求原文文本,仅在内容长度合理时提供提取的markdown;否则提供关键章节内容,并告知可从保存的输出中读取更多内容。
Deep research (only when explicitly requested)
深度研究(仅在明确请求时使用)
Deep research is slower and may cost more than Search. Use it only when the user explicitly wants depth.
深度研究比搜索更慢,成本可能更高。仅在用户明确要求深度内容时使用。
Step 1 — start (always async)
步骤1 — 启动(始终异步)
bash
parallel-cli research run "$QUESTION" --processor pro-fast --no-wait --jsonParse (and any monitoring URL) from JSON and tell the user the run started.
run_idbash
parallel-cli research run "$QUESTION" --processor pro-fast --no-wait --json从JSON中解析(以及任何监控URL),并告知用户任务已启动。
run_idStep 2 — poll (bounded timeout)
步骤2 — 轮询(有界超时)
Choose a short slug filename (lowercase-hyphen), then:
bash
parallel-cli research poll "$RUN_ID" -o "/tmp/$SLUG" --timeout 540- Share the executive summary printed by the poll command.
- Mention the output files:
/tmp/$SLUG.md/tmp/$SLUG.json
If polling times out, re-run the same poll command — the run continues server-side.
选择一个简短的小写连字符命名的文件名,然后执行:
bash
parallel-cli research poll "$RUN_ID" -o "/tmp/$SLUG" --timeout 540- 分享轮询命令输出的执行摘要。
- 提及输出文件:
/tmp/$SLUG.md/tmp/$SLUG.json
如果轮询超时,重新执行相同的轮询命令——任务会在服务器端继续运行。
Enrich (CSV/JSON or inline data)
增强(CSV/JSON或内联数据)
Use Enrich to add web-sourced columns to structured data.
使用增强功能为结构化数据添加网页来源的列。
Step 1 — (optional) suggest columns
步骤1 —(可选)建议列
bash
parallel-cli enrich suggest "$INTENT" --jsonUse this when the user knows the goal but not the exact output schema.
bash
parallel-cli enrich suggest "$INTENT" --json当用户知道目标但不确定确切输出模式时使用此命令。
Step 2 — run (always async for large jobs)
步骤2 — 运行(大型任务始终异步)
For CSV:
bash
parallel-cli enrich run --source-type csv --source "input.csv" --target "/tmp/enriched.csv" --source-columns '[{"name":"company","description":"Company name"}]' --intent "$INTENT" --no-wait --jsonFor inline JSON rows:
bash
parallel-cli enrich run --data '[{"company":"Google"},{"company":"Apple"}]' --target "/tmp/enriched.csv" --intent "$INTENT" --no-wait --jsonParse from JSON.
taskgroup_id针对CSV:
bash
parallel-cli enrich run --source-type csv --source "input.csv" --target "/tmp/enriched.csv" --source-columns '[{"name":"company","description":"Company name"}]' --intent "$INTENT" --no-wait --json针对内联JSON行:
bash
parallel-cli enrich run --data '[{"company":"Google"},{"company":"Apple"}]' --target "/tmp/enriched.csv" --intent "$INTENT" --no-wait --json从JSON中解析。
taskgroup_idStep 3 — poll
步骤3 — 轮询
bash
parallel-cli enrich poll "$TASKGROUP_ID" --timeout 540 --jsonAfter completion:
- Tell the user the output file path (the you chose).
--target - Preview a few rows (using file read tools if available) and report row counts.
If poll times out, re-run it — the job continues server-side.
bash
parallel-cli enrich poll "$TASKGROUP_ID" --timeout 540 --json完成后:
- 告知用户输出文件路径(你选择的路径)。
--target - 预览几行内容(如果可用,使用文件读取工具)并报告行数。
如果轮询超时,重新执行——任务会在服务器端继续运行。
FindAll (entity discovery)
FindAll(实体发现)
Use FindAll when the user wants you to discover a set of entities (e.g., “AI startups in healthcare”, “roofing companies in Charlotte”, “YC devtools companies”).
当用户希望你发现一组实体时(例如“医疗领域的AI初创公司”、“夏洛特的屋顶公司”、“YC旗下的开发工具公司”),使用FindAll功能。
Step 1 — run
步骤1 — 运行
bash
parallel-cli findall run "$OBJECTIVE" --generator core --match-limit 25 --no-wait --jsonUseful options:
- to preview schema before spending money
--dry-run --json - to avoid known entities
--exclude '[{"name":"Example Corp","url":"example.com"}]' - (core default; pro for hardest queries)
--generator preview|base|core|pro
Parse from JSON.
run_idbash
parallel-cli findall run "$OBJECTIVE" --generator core --match-limit 25 --no-wait --json实用选项:
- (在消耗成本前预览模式)
--dry-run --json - (排除已知实体)
--exclude '[{"name":"Example Corp","url":"example.com"}]' - (默认core;难度最高的查询使用pro)
--generator preview|base|core|pro
从JSON中解析。
run_idStep 2 — poll + fetch results
步骤2 — 轮询并获取结果
bash
parallel-cli findall poll "$RUN_ID" --json
parallel-cli findall result "$RUN_ID" --jsonRespond with:
- total entities found
- a clean list/table of the best matches (name + URL + key attributes)
- any caveats about ambiguous matches
bash
parallel-cli findall poll "$RUN_ID" --json
parallel-cli findall result "$RUN_ID" --json回复内容包括:
- 发现的实体总数
- 匹配度最高的实体的整洁列表/表格(名称 + URL + 关键属性)
- 关于模糊匹配的注意事项
Monitor (web change tracking)
监控(网页变化跟踪)
Use Monitor when the user wants ongoing tracking.
Create:
bash
parallel-cli monitor create "$OBJECTIVE" --cadence daily --jsonOptional:
--cadence hourly|daily|weekly|every_two_weeks- (deliver events externally)
--webhook https://example.com/hook - (structured events)
--output-schema '<JSON schema string>'
Manage:
bash
parallel-cli monitor list --json
parallel-cli monitor get "$MONITOR_ID" --json
parallel-cli monitor update "$MONITOR_ID" --cadence weekly --json
parallel-cli monitor delete "$MONITOR_ID"
parallel-cli monitor events "$MONITOR_ID" --json
parallel-cli monitor simulate "$MONITOR_ID" --jsonRespond with the monitor id and how to retrieve events (or confirm webhook delivery).
当用户需要持续跟踪时,使用监控功能。
创建监控任务:
bash
parallel-cli monitor create "$OBJECTIVE" --cadence daily --json可选参数:
--cadence hourly|daily|weekly|every_two_weeks- (向外部推送事件)
--webhook https://example.com/hook - (结构化事件)
--output-schema '<JSON schema string>'
管理监控任务:
bash
parallel-cli monitor list --json
parallel-cli monitor get "$MONITOR_ID" --json
parallel-cli monitor update "$MONITOR_ID" --cadence weekly --json
parallel-cli monitor delete "$MONITOR_ID"
parallel-cli monitor events "$MONITOR_ID" --json
parallel-cli monitor simulate "$MONITOR_ID" --json回复监控ID以及获取事件的方式(或确认webhook推送状态)。
Reference material
参考资料
- Copy/paste command templates and patterns:
references/command-templates.md - Troubleshooting common failures:
references/troubleshooting.md
- 复制粘贴命令模板与模式:
references/command-templates.md - 常见故障排查:
references/troubleshooting.md