shikumi-optimize: The optimizer framework for shikumi LM programs (EP-10)

[ ai, bsd3, library ] [ Propose Tags ] [ Report a vulnerability ]

The optimizer framework for shikumi: search procedures that automatically improve a Shikumi.Program.Program by rewriting its per-node optimizable parameters (instruction strings and few-shot demonstrations) and scoring each candidate with evaluate (EP-8) over a typed dataset and metric. Four strategies ship — labeled few-shot demo selection, bootstrap few-shot (recover demonstrations from a teacher's successful runs), instruction search (MIPRO/COPRO-style coordinate ascent under an explicit call budget), and ensemble search (combine complementary candidates by majority vote). Each optimizer returns a CompiledProgram (EP-9, MasterPlan integration point #6). Every acceptance assertion runs fully offline against a deterministic stub LM, so the whole package tests with no network and no API key.

Downloads

Maintainer's Corner

Package maintainers

For package maintainers and hackage trustees

Candidates

  • No Candidates
Versions [RSS] 0.1.0.0, 0.1.0.1, 0.2.0.0, 0.2.1.0, 0.2.1.1, 0.2.1.2, 0.2.1.3, 0.3.0.0
Change log CHANGELOG.md
Dependencies aeson (>=2.2 && <2.3), base (>=4.20 && <5), containers (>=0.6 && <0.9), effectful (>=2.5 && <2.7), generic-lens (>=2.2 && <2.4), lens (>=5.3 && <5.4), shikumi (>=0.4.0.0 && <0.5), shikumi-compile (>=0.2.1.0 && <0.3), shikumi-eval (>=0.3.0.0 && <0.4), shikumi-trace (>=0.3.0.0 && <0.4), text (>=2.1 && <2.2), vector (>=0.13 && <0.14) [details]
License BSD-3-Clause
Author Nadeem Bitar
Maintainer nadeem@gmail.com
Uploaded by shinzui at 2026-09-08T19:35:20Z
Category AI
Distributions
Downloads 51 total (21 in the last 30 days)
Rating (no votes yet) [estimated by Bayesian average]
Your Rating
  • λ
  • λ
  • λ
Status Docs uploaded by user [build log]
All reported builds failed as of 2026-09-08 [all 1 reports]