Cloudflare Extends AI Search to Make it Easier for Agents and Developers to Search Custom Data

Cloudflare 扩展 AI 搜索功能，让智能体和开发者更轻松地搜索自定义数据

作者：Sergio De Simone · InfoQ 原文

摘要：Cloudflare 推出 AI Search 服务，为 AI 智能体和应用程序提供内置的搜索和检索功能，支持多模态搜索、自动爬取和索引，并与 Cloudflare 其他工具无缝集成。该服务可自动处理端到端搜索管道，支持“发现”模式自动抓取页面，提供单一公共端点进行跨实例搜索，并采用可预测的定价模式。

Cloudflare AI Search is a built-in search and retrieval service designed to give AI agents and applications a ready-to-use search engine over custom data.

Cloudflare AI Search 是一项内置的搜索和检索服务，旨在为 AI 智能体和应用程序提供可直接使用的自定义数据搜索引擎。

It supports agent integration, multimodal search, and seamless integration with other Cloudflare tools.

它支持智能体集成、多模态搜索，并能与 Cloudflare 其他工具无缝集成。

A search pipeline typically involves several components, including a crawler, parser, embedding model, vector database, search API, and more.

搜索管道通常包含多个组件，如爬虫、解析器、嵌入模型、向量数据库、搜索 API 等。

Cloudflare already provides many of these as "primitives", including Workers AI, AI Gateway, Vectorize, R2, Browser Run, and others.

Cloudflare 已经以“原语”形式提供了其中许多组件，包括 Workers AI、AI Gateway、Vectorize、R2、Browser Run 等。

AI Search now brings these capabilities together, automatically handling the end-to-end search pipeline and doing so "better", the company says.

该公司表示，AI Search 现在将这些能力整合在一起，自动处理端到端搜索管道，并且做得“更好”。

Our goal is to give your agents their own search engine, where they can easily find data to provide better answers for themselves and their humans.

我们的目标是让您的智能体拥有自己的搜索引擎，它们可以轻松找到数据，从而为自己和人类提供更好的答案。

AI Search enables organizations to index collections of structured or unstructured data and make them accessible to agents.

AI Search 使组织能够索引结构化或非结构化数据集合，并让智能体可以访问这些数据。

Previously, each indexed website was required to publish a sitemap, but AI Search is now able to work in "discover" mode, automatically discovering pages even without one.

以前，每个被索引的网站都需要发布站点地图，但现在 AI Search 能够以“发现”模式运行，即使没有站点地图也能自动发现页面。

The engine provides a single public endpoint for searching across multiple instances or websites at once without requiring authentication.

该引擎提供了一个单一的公共端点，无需身份验证即可同时搜索多个实例或网站。

For websites built using the open-source CMS EmDash, AI Search can be easily integrated using a specific plugin.

对于使用开源 CMS EmDash 构建的网站，可以通过特定插件轻松集成 AI Search。

To create a search instance, you run a single command that handles crawling, ingestion, embedding, and retrieval:

要创建搜索实例，只需运行一条命令，该命令即可处理爬取、摄取、嵌入和检索：

npx wrangler ai-search create cloudflare-community \ --namespace dev-stack \ --source https://community.cloudflare.com \ --type web-crawler \ --parse-type discover

Cloudflare AI Search is available across several Cloudflare-managed services, including its API and developer documentation, Astro, Vite, Hono, Replicate, and others.

Cloudflare AI Search 可用于多个 Cloudflare 管理的服务，包括其 API 和开发者文档、Astro、Vite、Hono、Replicate 等。

This allows these sources to be indexed and searched as a single corpus rather than as independent entities, enabling a single query to answer a question using data from the different sources.

这使得这些来源可以被索引和搜索为一个单一的语料库，而不是独立的实体，从而允许单个查询使用来自不同来源的数据来回答问题。

Search can be integrated into an existing application or MCP server through a Worker, which Cloudflare recommends, or exposed through public /mcp and /search endpoints that require no authentication or deployment and can be easily shared with others.

搜索可以通过 Worker 集成到现有应用程序或 MCP 服务器中（Cloudflare 推荐此方式），或者通过公共的 /mcp 和 /search 端点公开，这些端点无需身份验证或部署，并且可以轻松与他人共享。

As a final note about AI Search, Cloudflare emphasizes that it designed its pricing model to make it predictable and scalable.

最后，关于 AI Search，Cloudflare 强调其定价模式设计得可预测且可扩展。

In particular, embedding and re-ranking are free when using the default models or select models from the Workers AI catalog, while answer generation and query rewriting are billed based on model usage.

特别是，当使用默认模型或 Workers AI 目录中的选定模型时，嵌入和重新排序是免费的，而答案生成和查询重写则根据模型使用量计费。

This pricing model will take effect once the service reaches general availability, while during the beta period, AI Search is available for free.

此定价模式将在服务正式上线后生效，而在测试期间，AI Search 可免费使用。

阅读理解

1. What is a key improvement of AI Search compared to its previous version?

2. How does Cloudflare recommend integrating AI Search into an existing application?

3. Which of the following is true about the pricing model of AI Search?

温故复习 →每日一句 →