From cloudflare
Use this skill when the user asks about Cloudflare Vectorize, vector databases on Cloudflare, semantic search, RAG pipelines, embedding storage, or managing Vectorize with Pulumi.
npx claudepluginhub nsheaps/ai-mktpl --plugin cloudflareThis skill uses the workspace's default tool permissions.
Vectorize is Cloudflare's vector database for building semantic search, recommendation engines, and RAG (Retrieval-Augmented Generation) applications. It integrates natively with Workers AI for embedding generation.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides agent creation for Claude Code plugins with file templates, frontmatter specs (name, description, model), triggering examples, system prompts, and best practices.
Vectorize is Cloudflare's vector database for building semantic search, recommendation engines, and RAG (Retrieval-Augmented Generation) applications. It integrates natively with Workers AI for embedding generation.
export default {
async fetch(request: Request, env: Env): Promise<Response> {
// Generate embeddings with Workers AI
const embedding = await env.AI.run("@cf/baai/bge-base-en-v1.5", {
text: ["What is Cloudflare?"],
});
// Insert into Vectorize
await env.VECTORIZE.upsert([
{
id: "doc-1",
values: embedding.data[0],
metadata: { title: "About Cloudflare" },
},
]);
// Query
const results = await env.VECTORIZE.query(embedding.data[0], {
topK: 5,
returnMetadata: "all",
});
return Response.json(results);
},
};
[[vectorize]]
binding = "VECTORIZE"
index_name = "my-index"
# Create an index
npx wrangler vectorize create my-index --dimensions 768 --metric cosine
# Insert vectors
npx wrangler vectorize insert my-index --file vectors.ndjson
// Vectorize indexes are managed via wrangler CLI
// No dedicated Pulumi resource currently exists
// Use Pulumi's Command provider if automation is needed:
import * as command from "@pulumi/command";
const vectorizeIndex = new command.local.Command("vectorize-index", {
create: "npx wrangler vectorize create my-index --dimensions 768 --metric cosine",
delete: "npx wrangler vectorize delete my-index",
});
| Setting | Options | Description |
|---|---|---|
| Dimensions | 1–1536 | Must match your embedding model output |
| Metric | cosine, euclidean, dot-product | Similarity metric |
| Resource | Free | Paid |
|---|---|---|
| Queried dimensions | 30M/month | $0.01/M |
| Stored dimensions | 5M | $0.05/M/month |
| Indexes | 5 | 100 |