Skip to content

tya5/rag

v0.1.0

Builtin turnkey user RAG (ADR 0064 P5): chunker + vector-store MCP servers, ingest/query pipelines, and its RAG skill (install, embedding-provider setup, the ingest/query workflow, and corpus internals, all bundled with references). External sqlite store the operator names and owns (FP-0057 C2) -- distinct from reyn's own OS-internal index (not agent-callable, FP-0066 P1b).

build-and-query-rag-corpus

Make a folder of the operator's own documents (txt/md/pdf/xlsx/pptx/docx) searchable by meaning via a user-named sqlite vector store. Covers installing the rag plugin, embedding-provider setup, the exact rag_ingest/rag_query pipeline calls, and corpus internals -- via bundled references. Read this before running the builtin rag_ingest / rag_query pipelines, or when the operator asks you to search a folder/file of their own documents.

Read SKILL.md at the source

Pinned to revision cfa62f0fe349, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.