Back to directory

Semantic Search API

A production-ready semantic search API built entirely on Cloudflare's free-tier infrastructure, with OpenAPI documentation and separate reader and writer API keys.

Semantic Search API

Semantic Search API is a document search service deployable to Cloudflare Workers, using a Cloudflare Vectorize index for vector storage and documented with a full OpenAPI specification and Swagger UI. It exposes endpoints to create, update, retrieve, delete and semantically search documents, each carrying arbitrary metadata.

Access is split between writer keys, required for endpoints that create or delete documents, and reader keys, which may only call read and search endpoints; both key types support multiple comma- or newline-separated values so several keys of the same type can be issued at once, letting writer keys stay in trusted server or CI environments while reader keys are safe to embed in public clients. TypeScript, deployed with a one-click option or manually through Wrangler.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.