shoney.arickathil
9d1689be55
- jarvis 1 (chat loop) brainstormed to ready with forks AUTO-APPROVED for autonomous execution and flagged in `review_pending` frontmatter for the developer's second review: Anthropic Messages API backend, env-var API key, actor-per-conversation SSE relay, durable @table history, session-gated routes - jarvis 2 (tool use) + 3 (retrieval/RAG) created at refine with forks named - 00-story iterations table linked to the new files - blocked until rv2 9 TLS reaches phase F; pure .wo on porch 2/3/6/7 + the seam (cherry picked from commit 8e160c3fcf9c50a05af073c036c693b192c9e595)
1.9 KiB
1.9 KiB
| track | iteration | status | readiness |
|---|---|---|---|
| jarvis | 3 | pending | refine |
jarvis 3 — retrieval (RAG): grounded answers over a document set
Part of Story — jarvis, the writeonce AI assistant. Answers grounded in a corpus: embed documents, embed the query, retrieve the nearest chunks, and put them in the prompt. Needs jarvis 1 and the embeddings/vector decision below.
Why this exists
A chat/agent loop knows only the model's training and the tools it can call. Retrieval lets jarvis answer over the developer's own documents — the on-brand "ask my codebase / my notes" use case — without fine-tuning.
What it should deliver (to be refined)
- Embeddings for documents and queries — an embeddings API call over the same outbound TLS path jarvis 1 uses.
- A vector store: chunk text, store
{chunk, vector}durably, and a similarity search (cosine / dot-product) over it. - Retrieval into the prompt: top-k chunks prepended as context in the chat loop.
Forks the brainstorm must settle
- The vector store: pure
.woor a new runtime primitive. A brute-force cosine scan over a@tableofBytesvectors is pure.woand fine for a modest corpus; an approximate-nearest-neighbour index or a SIMD dot-product builtin is a runtime iteration if scale demands it. Decide on a measured need, not up front. - Chunking strategy — fixed-size vs semantic; overlap; where metadata (source, offset) lives.
- Embedding storage — vectors as
Bytes(packed floats) in a@table, and whether Float arrays need a better carrier than iteration 19'sBytes.
Out of scope
- Re-ranking models, hybrid keyword+vector search, and multi-corpus tenancy — each its own later slice.
Info
Depends on jarvis 1's outbound path (for embeddings) and the vector-store fork. The only possible new runtime work is fork 1's ANN/SIMD option, deferred until a corpus size measures the need.