zeppelin

What problem does it solve?

Provides a hosted vector search engine that removes the friction of storing, indexing, and retrieving text by semantic similarity or BM25 full-text ranking so users can build fast, production-ready semantic search over documents.

Core Features & Use Cases

• Namespace management with server-generated UUIDs for isolated vector collections.
• Text embedding via a hosted embed service, upsert of 384-dim vectors, and attribute-based filtering.
• Vector nearest-neighbor search (ANN) and BM25 full-text ranking, with strong vs eventual consistency modes and S3-native segment compaction.
• Use Case: embed and upsert product descriptions or documents, then run semantic queries and filtered searches to surface the most relevant items.

Quick Start

Create a 384-dimension namespace, embed your texts with the Embed API, upsert the returned vectors into that namespace, and run a similarity or BM25 query to retrieve top results.