shikumi-eval-0.3.0.1: shikumi-eval.cabal

cabal-version: 3.4
name: shikumi-eval
version: 0.3.0.1
synopsis: Typed evaluation framework for shikumi LM programs (EP-8)
category: AI
description:
  The evaluation framework for shikumi: the owned data model (@Example@,
  @Prediction@, @Dataset@, @Metric@, @Score@, @Report@ — MasterPlan integration
  point #5), built-in pure and LM-backed metrics, an @evaluate@ runner that
  scores a 'Shikumi.Program.Program' over a typed dataset with bounded
  parallelism and per-example error boundaries, and golden testing that pins a
  program's behaviour deterministically under a mock or replayed LM.

license: BSD-3-Clause
author: Nadeem Bitar
maintainer: nadeem@gmail.com
build-type: Simple
extra-doc-files: CHANGELOG.md

common common-options
  ghc-options:
    -Wall
    -Wcompat
    -Widentities
    -Wincomplete-uni-patterns
    -Wincomplete-record-updates
    -Wredundant-constraints
    -fhide-source-paths
    -Wmissing-export-lists
    -Wpartial-fields
    -Wmissing-deriving-strategies

  default-language: GHC2024
  default-extensions:
    DeriveAnyClass
    DuplicateRecordFields
    OverloadedLabels
    OverloadedStrings

library
  import: common-options
  hs-source-dirs: src
  exposed-modules:
    Shikumi.Eval
    Shikumi.Eval.Embedding
    Shikumi.Eval.Evaluate
    Shikumi.Eval.Golden
    Shikumi.Eval.Metric
    Shikumi.Eval.Report
    Shikumi.Eval.Types
    Shikumi.Eval.Usage

  build-depends:
    aeson >=2.2 && <2.3,
    baikai >=0.7.1.0 && <0.8,
    base >=4.20 && <5,
    bytestring >=0.11 && <0.13,
    containers >=0.6 && <0.9,
    effectful >=2.6 && <2.8,
    generic-lens >=2.2 && <2.4,
    lens ^>=5.3,
    shikumi ^>=0.4.0.0,
    tasty >=1.4 && <1.6,
    tasty-golden >=2.3 && <2.4,
    text ^>=2.1,
    vector >=0.13 && <0.14,

test-suite shikumi-eval-test
  import: common-options
  type: exitcode-stdio-1.0
  hs-source-dirs: test
  main-is: Main.hs
  ghc-options:
    -threaded
    -with-rtsopts=-N

  other-modules:
    DocSpec
    EmbeddingSpec
    EvalFixtures
    EvaluateSpec
    GoldenSpec
    MetricLMSpec
    MetricSpec
    ReportSpec
    TypesSpec
    UsageSpec

  build-depends:
    aeson,
    baikai >=0.7.1.0 && <0.8,
    base,
    effectful,
    generic-lens,
    lens,
    shikumi ^>=0.4.0.0,
    shikumi-eval ^>=0.3.0.1,
    tasty,
    tasty-golden,
    tasty-hunit,
    text,
    vector,