1. Public content chunks
The book, wiki, glossary, trust, and release material can now be exported into structured chunks ready for ingestion.
Online Vector Database Foundation
v1.6.0 installs the connection foundation for a real online vector database. The public Ask layer remains safe in fallback mode until Supabase, pgvector, embeddings, and ingestion are fully activated.
The book, wiki, glossary, trust, and release material can now be exported into structured chunks ready for ingestion.
v1.6.0 defines the Supabase/pgvector schema, environment variables, connection health check, and provider boundary.
Until credentials and embeddings are activated, BEYOND keeps working through the local mock corpus instead of breaking public search.
After embeddings are generated, the Ask layer can retrieve relevant BEYOND chunks by meaning, not only by keyword.
The same retrieval foundation can later feed spoken answers, audio lessons, and voice-guided navigation.
/api/beyond/rag/health/api/beyond/rag/vector-health/api/beyond/rag/search?q=trustThis release prepares the online vector database connection, schema, scripts, and runtime health checks. It does not expose secrets and it does not require credentials to build. The next phase can activate real ingestion and semantic search.