cloudflare-vectorize

Index and query vector embeddings with metadata filtering in Cloudflare Vectorize.

52|6|Updated Nov 24, 2025

Search Tags:#semantic search #vector database #RAG #vector embeddings #vectorize #vector index

Ready to run

npx skills add https://github.com/ovachiever/droid-tings --skill cloudflare-vectorize-ovachiever

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cloudflare-vectorize
Source: https://github.com/ovachiever/droid-tings/tree/main/skills/cloudflare-vectorize
Command: npx skills add https://github.com/ovachiever/droid-tings --skill cloudflare-vectorize-ovachiever

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Build semantic search, RAG, and AI-powered apps using Cloudflare Vectorize. This skill provides ready-to-use templates, metadata filtering patterns, and resilient vector operations to reduce integration complexity and tokens spent on boilerplate.

Core Features & Use Cases

Index Management: create indices with fixed dimensions and metadata filters
Vector Operations: insert/upsert/query/delete/list vectors with metadata
Metadata Filtering: 10 metadata indexes per index for precise queries
RAG Workflows: integration patterns for retrieval-augmented generation
Embeddings Integration: Workers AI and OpenAI model support
Multi-Environment Namespaces: multi-tenant isolation with namespaces
Use cases include semantic document search, product recommendations, and content discovery

Quick Start

Create a working index with 768 dimensions for Workers AI bge-base-en-v1.5, then insert vectors with metadata and run a topK search.

Frequently Asked Questions about cloudflare-vectorize

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build semantic search using vector embeddings?▼

Semantic search uses vector embeddings to find meaning-based matches instead of keyword matches. Cloudflare Vectorize indexes and queries embeddings, enabling you to search documents, products, or content by semantic similarity rather than exact text.

Can I use Cloudflare Vectorize for RAG and knowledge-base Q&A?▼

Yes. Vectorize supports retrieval-augmented generation by storing document embeddings with metadata, then retrieving relevant chunks during queries. This powers knowledge-base Q&A, product recommendations, and content discovery workflows.

What metadata filtering capabilities does Vectorize provide?▼

Vectorize supports up to 10 metadata indexes per index, enabling precise filtering on query results. You can filter vectors by metadata fields during retrieval, combine metadata with namespace isolation for multi-tenant workflows, and upsert vectors with attached metadata.

How do I index PDF documents for semantic search?▼

Extract text and images from PDFs using pypdf or pdfplumber, convert to embeddings via Workers AI or OpenAI, then insert vectors with metadata into a Vectorize index. This prepares documents for semantic retrieval and Q&A.

Does Vectorize work with Workers AI embeddings?▼

Yes. Vectorize integrates with Workers AI's bge-base-en-v1.5 model and OpenAI embeddings. Create a 768-dimension index for Workers AI, insert vectors, and query using the same embedding model for consistent semantic matching.

What are the constraints when setting up a Vectorize index?▼

Vectorize requires fixed embedding dimensions at index creation, metadata indexes must be created before vector insertion, and indexes support up to 10 metadata filters. Namespace and metadata filtering enable multi-tenant isolation but require careful schema planning upfront.