AskDB RAG layer: deterministic chunker over Schema v2, BYO embedder + vector store (in-memory, file-backed, pgvector), and an optional retriever wired into @askdb/core ask().
AskDB Studio: local browser UI for Schema v2 enrichment and sample NL-to-SQL checks.
AskDB core: dialect-agnostic NL→SQL pipeline. Provides ask() orchestration, schema/IR types, modes, logging, and retrieval input. Bring your own dialect (e.g. @askdb/postgres).
AskDB TUI: interactive terminal authoring surface that enriches a Schema v2 directory with descriptions, aliases, common query language, and example questions. AI-suggest + human-confirm; BYO LanguageModel.
AskDB schema introspection: engine-agnostic Connector contract + orchestrator + Schema v2 renderer. Integration packages (e.g. @askdb/postgres) supply connectors.
AskDB CLI: ask natural-language questions and get validated SQL from the configured dialect.
A a collection of languages stemmers and stopwords for Lunr Javascript library
The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.
A rag component for Convex.
AskDB Prisma integration: schema-file introspection connector for Prisma schemas.
AskDB MySQL integration: introspection connector via information_schema and a mysql2-backed catalog query runner. Pairs with @askdb/core's MYSQL_DIALECT.
AskDB HTTP API: minimal HTTP wrapper around @askdb/core. POST /ask returns validated SQL only.
AskDB Postgres integration: re-exports the Postgres DialectSpec from @askdb/core and ships the introspection connector (live + from-export bundle), catalog SQL templates, and a `pg`-backed catalog query runner.
AskDB Microsoft SQL Server integration: introspection connector via sys.* catalog views and an mssql-backed catalog query runner. Pairs with @askdb/core's SQLSERVER_DIALECT.
AskDB enrichment workspace helpers for Schema v2 authoring surfaces.
AskDB configuration helpers: Prisma-style env() and askdb.config file discovery for first-party apps.
AskDB SQLite integration: introspection connector via sqlite_master + PRAGMA functions and a better-sqlite3-backed catalog query runner. Pairs with @askdb/core's SQLITE_DIALECT.
A agent component for Convex.
Phase 2 of the catalog plane. Adds vector embeddings, AI-agent access patterns, and the MCP server scaffolding on top of the Phase 1 foundation in `@voyantjs/catalog`.
Retrivora AI is a plug-and-play AI engine for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.
The official Pinecone TypeScript SDK for building vector search applications with AI/ML.
Extract clean, timestamped YouTube captions, subtitles, transcripts, and video metadata for AI summaries, RAG, search, and slide-ready workflows.
Local RAG MCP Server - Easy-to-setup document search with minimal configuration
A JavaScript library for Retrieval-Augmented Generation (RAG) within the QVAC ecosystem. Build powerful, context-aware AI applications with seamless document ingestion, vector search, and LLM integration.