Perplexity 发布 pplx：单二进制 CLI 工具，将 Search API 带入终端供编码智能体使用

Perplexity：https://www.perplexity.ai/ 已发布 pplx，这是其搜索 API 的官方命令行客户端。该工具返回有根据的搜索结果和提取的页面文本，全部以 JSON 格式呈现。根据其文档，该工具的目标用户是人类和编码代理，二者同样适用。它不是一个聊天客户端。没有会话模式、没有模型选择，也没有生成答案。

该工具恰好提供两个工作界面。pplx search web 可进行实时网页搜索。pplx content fetch 会抓取 URL 并返回清理后的页面文本。

有趣的部分在于它们的契约。根据官方 pplx-cli Agent Skill：https://github.com/perplexityai/api-platform-developers/blob/main/skills/pplx-cli/SKILL.md，成功的标志是退出码为 0，并且在 stdout 上输出恰好一个 JSON 对象。搜索返回 {hits: [{url, title, domain, snippet, ...}], total, saved_to?}。

每次失败会以退出码 1 退出，并且 stdout 是空的。一个 JSON 错误对象会发送到 stderr，格式为 {"error":{"code","message","command","hint"?}}。记录的代码包括 AUTHENTICATION、UNKNOWN_ARGUMENT、ARGUMENT_ERROR 和 BAD_REQUEST。该技能指出，此列表不是详尽无遗的，因此调用方应根据 error.code 分支处理。

安装只需一个 shell 命令，将脚本通过管道传入 sh：

查看 install.sh：https://github.com/perplexityai/perplexity-cli/blob/main/install.sh 可以了解它实际做了什么。它会从最新发布版本下载 manifest.json 并提取 tag 和 version。然后，它会将每个剩余下载固定到该 tag，以明确避免与同时发布发生竞赛。

它会获取 SHA256SUMS 和平台二进制文件，验证校验和，并安装到 ~/.local/bin/pplx。无需 sudo。安装成功后，收据会写入 ~/.config/pplx/pplx-receipt.json。

平台覆盖范围仅限三个目标：Apple Silicon 的 macOS、Linux x86_64 以及 Linux arm64。其他任何系统都会报错退出。没有 Windows 版本，也没有 Intel macOS 版本。

最针对代理的功能是令牌预算。--output-dir 会将完整结果集写入 JSON 文件。--stdout-preview[= ] 会截断 stdout 中的长字符串字段，并添加 ... 标记。

该技能直言不讳地说明了陷阱：没有保存目录时，--stdout-preview 是无操作的。它只有在通过 --output-dir 或 $PPLX_OUTPUT_DIR 也保存结果时才会截断。单独使用时，它会返回完整输出，每次命中可能有数 KB 大小。

保存的搜索结果位于 {dir}/web/{rand}.json，抓取的内容位于 {dir}/fetch/{rand}.json。文件只有在请求成功后才会写入。PPLX_OUTPUT_DIR 设置工作区默认值，因此无需重复使用该标志。

对于内容抓取，该技能添加了正确性检查而非成本检查。信任内容前请验证输出中的 error 和 is_paywall。--html 会添加一个通过爬虫实时抓取的 raw_html 字段，而 --no-cache 会强制进行实时抓取。

来源：perplexityai/perplexity-cli：https://github.com/perplexityai/perplexity-cli，pplx-cli SKILL.md：https://github.com/perplexityai/api-platform-developers/blob/main/skills/pplx-cli/SKILL.md，api-platform-developers：https://github.com/perplexityai/api-platform-developers，Perplexity API 定价：https://docs.perplexity.ai/docs/getting-started/pricing，速率限制和使用层级：https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers，以及 Search API 快速入门：https://docs.perplexity.ai/docs/search/quickstart

Michal Sutter 是一名数据科学专业人士，拥有帕多瓦大学的数据科学硕士学位。凭借统计分析、机器学习和数据工程的坚实基础，Michal 擅长将复杂数据集转化为可操作的洞察。

构建一个 Agentic 活动场地运营者 [完整代码]：https://pxllnk.co/twdn5

谢谢！我们的团队将很快联系您 🙌

Perplexity：https://www.perplexity.ai/ has released pplx , an official command line client for its Search API. The tool returns grounded search results and extracted page text, all as JSON. According to its docs, it targets humans and coding agents equally. It is not a chat client. There is no conversational mode, no model selection and no synthesized answer.

The tool exposes exactly two working surfaces. pplx search web runs a live web search. pplx content fetch pulls a URL and returns cleaned page text.

The contract around them is the interesting part. Per the official pplx-cli Agent Skill：https://github.com/perplexityai/api-platform-developers/blob/main/skills/pplx-cli/SKILL.md, success means exit code 0 and exactly one JSON object on stdout. Search returns {hits: [{url, title, domain, snippet, ...}], total, saved_to?} .

Every failure exits 1 with an empty stdout. One JSON error object goes to stderr, shaped {"error":{"code","message","command","hint"?}} . Documented codes include AUTHENTICATION , UNKNOWN_ARGUMENT , ARGUMENT_ERROR and BAD_REQUEST . The skill notes that list is not exhaustive, so callers should branch on error.code .

Installation is a single shell command that pipes a script into sh :

Reading install.sh ：https://github.com/perplexityai/perplexity-cli/blob/main/install.sh shows what it actually does. It downloads manifest.json from the latest release and extracts the tag and version. It then pins every remaining download to that tag, explicitly to avoid racing a concurrent publish.

It fetches SHA256SUMS and the platform binary, verifies the checksum, and installs to ~/.local/bin/pplx . No sudo is required. A receipt is written to ~/.config/pplx/pplx-receipt.json , but only after the installed binary runs successfully.

Platform coverage is limited to three targets: macOS on Apple Silicon, Linux x86_64 and Linux arm64. Anything else exits with an error. There is no Windows build and no Intel macOS build.

The most agent-specific feature is token budgeting. --output-dir writes the full result set to a JSON file. --stdout-preview[= ] truncates long string fields in stdout, adding ... markers.

The skill is blunt about the trap: --stdout-preview is a no-op without a save directory. It truncates only when the result is also saved via --output-dir or $PPLX_OUTPUT_DIR . Used alone it returns full-size output, and hits can be multiple KB each.

Saved search results land at {dir}/web/{rand}.json and fetches at {dir}/fetch/{rand}.json . Files are written only after a successful request. PPLX_OUTPUT_DIR sets a workspace default so the flag need not be repeated.

For content fetch, the skill adds a correctness check rather than a cost one. Verify error and is_paywall in the output before trusting content . --html adds a raw_html field fetched live via crawler, and --no-cache forces a live fetch.

Sources: perplexityai/perplexity-cli：https://github.com/perplexityai/perplexity-cli, pplx-cli SKILL.md：https://github.com/perplexityai/api-platform-developers/blob/main/skills/pplx-cli/SKILL.md, api-platform-developers：https://github.com/perplexityai/api-platform-developers, Perplexity API pricing：https://docs.perplexity.ai/docs/getting-started/pricing, Rate limits and usage tiers：https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers, and Search API quickstart：https://docs.perplexity.ai/docs/search/quickstart

Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data engineering, Michal excels at transforming complex datasets into actionable insights.

Build an Agentic Event Venue Operator [Full Codes]：https://pxllnk.co/twdn5

Thanks! Our team will contact you soon 🙌