Semantic Search (Planned)

This use case is in development. Want to contribute? See the arcadedb-usecases repository.

Standalone vector search for e-commerce product discovery and document retrieval. Demonstrates ArcadeDB’s vector capabilities without requiring graph traversal — pure semantic search with filtering, faceting, and hybrid keyword+vector ranking.

Planned Features

  • Vector Similarity — Product and document embeddings with LSM_VECTOR, HNSW, and DiskANN indexes

  • Full-Text Search — Hybrid keyword + semantic search with reciprocal rank fusion

  • Document Model — Faceted filtering on product attributes

  • Python — Primary implementation language targeting data science and AI workflows

Target Scenarios

  • E-commerce product search with natural language queries

  • Document retrieval with semantic understanding

  • Hybrid search combining keyword matching and vector similarity

  • Multi-vector search (title embeddings + description embeddings)