AiSearch

API reference for Cloudflare AI Search resource

AiSearch

Cloudflare AI Search provides RAG (Retrieval-Augmented Generation) capabilities for building AI-powered search and chat applications.

Props

name · string

Name of the AI Search instance.

Hide default

${app}-${stage}-${id} (max 32 characters)

source · R2Bucket | AiSearchR2Source | AiSearchWebCrawlerSource · required

Data source for indexing.

Show AiSearchR2Source properties

type · r2 · required

Source type.

bucket · string | R2Bucket · required

R2 bucket - can be bucket name string or R2Bucket resource.

jurisdiction · default | eu | fedramp · default: "default"

Jurisdiction for the R2 bucket.

prefix · string

Prefix for included items from the R2 bucket.

includePaths · string[]

Path patterns to include (up to 10 patterns). Supports wildcards: * matches any characters except /, ** matches any characters including /.

excludePaths · string[]

Path patterns to exclude (up to 10 patterns). Supports wildcards: * matches any characters except /, ** matches any characters including /.

Show AiSearchWebCrawlerSource properties

type · web-crawler · required

Source type.

domain · string · required

Domain to crawl. Must be onboarded to your Cloudflare account.

Example: "docs.example.com" or "https://docs.example.com" (protocol will be stripped)

includePaths · string[]

Path patterns to include (up to 10 patterns).

excludePaths · string[]

Path patterns to exclude (up to 10 patterns).

aiSearchModel · AiSearch.Model · default: "@cf/meta/llama-3.3-70b-instruct-fp8-fast"

Text generation model for AI responses.

embeddingModel · AiSearch.EmbeddingModel · default: "@cf/baai/bge-m3"

Embedding model for vectorization.

chunk · boolean · default: "true"

Enable chunking of source documents.

chunkSize · number · default: "256"

Size of each chunk (minimum 64).

chunkOverlap · number · default: "10"

Overlap between chunks (0-30).

maxNumResults · number · default: "10"

Maximum search results (1-50).

scoreThreshold · number · default: "0.4"

Minimum match score (0-1).

reranking · boolean · default: "false"

Enable result reranking.

rerankingModel · AiSearch.RerankingModel · default: "@cf/baai/bge-reranker-base"

Reranking model.

rewriteQuery · boolean · default: "false"

Enable query rewriting for better retrieval.

cache · boolean · default: "false"

Enable similarity caching.

indexOnCreate · boolean · default: "true"

Whether to index the source documents when the AI Search instance is created.

delete · boolean · default: "true"

Whether to delete the AI Search instance when removed from Alchemy.

adopt · boolean · default: "false"

Whether to adopt the AI Search instance if it already exists.

Output

id · string

The unique ID of the AI Search instance.

name · string

The name of the AI Search instance.

source · string

Source bucket or domain name.

type · r2 | web-crawler

The source type.

vectorizeName · string

The name of the underlying Vectorize index.

Examples

Basic AI Search with R2

const bucket = await R2Bucket("docs", { dev: { remote: true } });

const aiSearch = await AiSearch("rag", {
  source: bucket
});

const worker = await Worker("search", {
  entrypoint: "./src/search.ts",
  bindings: {
    AI_SEARCH: aiSearch
  }
});

AI Search with R2 Source Config

const aiSearch = await AiSearch("docs-search", {
  source: {
    type: "r2",
    bucket: "my-docs-bucket",
    includePaths: ["docs/**"],
    excludePaths: ["**/*.png", "**/*.jpg"]
  }
});

AI Search with Web Crawler

const aiSearch = await AiSearch("site-search", {
  source: {
    type: "web-crawler",
    domain: "docs.example.com",
    includePaths: ["/guides/**", "/api/**"],
    excludePaths: ["/blog/**"]
  }
});

Advanced AI Search Configuration

const aiSearch = await AiSearch("advanced-search", {
  source: bucket,
  aiSearchModel: "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
  embeddingModel: "@cf/baai/bge-m3",
  chunk: true,
  chunkSize: 512,
  chunkOverlap: 20,
  maxNumResults: 20,
  scoreThreshold: 0.5,
  reranking: true,
  rewriteQuery: true,
  cache: true
});