Comment on [deleted]

GenderNeutralBro@lemmy.sdf.org ⁨4⁩ ⁨days⁩ ago

• SuspciousCarrot78@lemmy.world ⁨4⁩ ⁨days⁩ ago

  Yes! And, for fun, I forced Qwen to answer your question, after querying it’s own fucking brain (M-E-T-A).

  The below is AI generated, using the router, with >>Fun mode (not >>FR…that’s my special gremlin mode). >>f suspends some of the terseness. Let me know if you want to see the non FR version

  ---

  Yep — with your current code, here’s the literal answer to “what can >>attach ingest, can it handle the whole Python docs, and how does retrieval work?” (based on the files you uploaded).

  ---

  What >>attach actually does (and does not do)

  >>attach <kb> doesn’t ingest anything. It just registers a KB name into state.attached_kbs so later turns know which KB folders are “active.”

  The router’s own docstring is blunt about the intended contract:

  • “KBs are filesystem folders containing SUMM_*.md files.”
  • “/serious answers use filesystem KB retrieval ONLY from attached KBs.”

  So the “ingest” step is really:

  1. drop raw docs in the KB folder
  2. run >>summ new to generate SUMM_*.md
  3. then attach the KB (or keep it attached) and query it

  ---

  What kinds of files can be summarized (and therefore used via attach)?

  In the router’s filesystem SUMM pipeline, _SUPPORTED_RAW_EXTS = {“.md”, “.txt”, “.pdf”, “.html”, “.htm”}

  • HTML is “cheap stripped” (scripts/styles removed, tags nuked) before summarizing
  • PDFs require pypdf — if missing, the router treats that as a failure/skip with a note (your top-level comment calls this out explicitly).
  • There’s also an explicit guard to truncate huge inputs before sending to the model (default summ.max_input_chars = 120_000).

  When a SUMM is created, it writes a provenance header including source_rel_path and source_sha256, then moves the original into /original/.

  So: you do not need “minimalistic plain-text statements.” You can feed it normal docs (md/txt/html/pdf) and it will produce SUMMs that become queryable.

  ---

  “If I dropped the entire Python docs in there…”

  Yes, it will produce something usable, because Python docs are mostly HTML and you explicitly support .html/.htm with stripping.

  But there are two practical gotchas in your implementation:

  1. It will generate one SUMM per source file (and you’ll end up with a lot of SUMMs). summ_new_in_kb() walks the KB tree, skips /original/, and summarizes every supported raw doc that doesn’t already have a corresponding SUMM_*.md.
  2. The SUMM prompt structure matters. Your shipped SUMM.md template is oriented around “overview / key ideas / steps / tradeoffs / pitfalls” rather than “API reference / signatures / parameters.” So it’ll work better for conceptual docs than for “tell me the exact signature of pathlib.Path.glob”.

  If you want Python-docs-as-KB to be strong, the move is: tweak the SUMM prompt to extract API sections + signatures + examples, not just “Key Ideas.”

  ---

  How retrieval works in “attached KB” mode

  This is the most important bit: filesystem KB retrieval is not vector embeddings. It’s a lightweight lexical scorer over SUMM markdown blocks.

  Concretely:

  • It searches only SUMM_*.md under attached KB roots, explicitly excluding /original/.
  • It splits each SUMM into blocks (paragraphs / headings), caps blocks around ~1200 chars, then scores blocks by token overlap with the query.
  • Scoring has a few boosts: headings matching query tokens, and a small bonus for code fences.
  • Then it returns the top hits (defaults like top_k=8, max_blocks_per_file=3, max_chars=2400).

  So attached-KB mode is basically: pre-summarize once → then do fast “smart grep” over summaries.

  That’s why it’s potato-friendly: you’re not embedding every doc on every query; SUMMs are preprocessed once.

  ---

  And “Vault / Mentats” retrieval is different

  When you >>move to vault, you’re no longer doing filesystem lexical search. You promote SUMMs into Qdrant and retrieve top-k chunks with embeddings + rerank (as configured in README / config).

  (Also worth noting: per your ingest module, the intended architecture is explicitly “filesystem SUMMs for day-to-day; Vault/Qdrant only for promoted SUMMs.” )

  ---

  One-liner you can paste as a Lemmy answer

  >>attach doesn’t ingest raw docs — it just activates a KB folder. The KB mode queries SUMM_*.md files (generated via >>summ new) using a lightweight lexical block scorer (token overlap + heading boosts), not embeddings. You can drop the whole Python HTML docs in a KB and it’ll work, but you’ll want a SUMM prompt tuned for API/reference detail or the summaries will smooth out the stuff you actually care about. If you promote SUMMs to the Vault (>>move to vault), then retrieval switches to Qdrant vector search + reranking.

  ###########################

  Is gut, ja?

  source