Files
doctate/experiments/Cargo.toml
T
Brummel 10d0a6ba94 Add experiments sandbox: prompt iteration tooling
Nested Cargo-Workspace unter experiments/ als Pfad-Dependency auf
../server. Reproduziert die Production-Pipeline 1:1 durch direkte
Wiederverwendung der Server-Module (transcribe::whisper, analyze::llm,
gazetteer, ffmpeg-Remux) — kein eigenes HTTP-Re-Implementieren, kein
Drift-Risiko zur Live-Pipeline.

Drei bin-Targets:
- run_full_case: volle Pipeline (ffmpeg → whisper → pre-gazetteer → llm
  → post-gazetteer), n Runs einer Variante
- run_llm_only: schneller LLM-Iterations-Pfad auf existierenden,
  gazetteer-bereinigten Transkripten — spart Whisper-Calls
- diff_runs: qualitativer Vergleich zwischen zwei Run-Verzeichnissen

Repo-Hygiene: case_*/ (Patientendaten, Symlinks zu tmpdata) und _data/
(Run-Outputs) sind komplett gitignored. Nur Code und fall-übergreifende
Prompt-Hypothesen (prompts/) werden versioniert.

Erste Prompt-Varianten zur Treue-Klausel und Konflikt-Auflösung:
prompts/llm/v1_treue.txt, v2_treue.txt.
2026-04-27 22:43:02 +02:00

35 lines
850 B
TOML

[workspace]
resolver = "3"
[package]
name = "doctate-experiments"
version = "0.1.0"
edition = "2024"
[dependencies]
doctate-server = { path = "../server" }
doctate-common = { path = "../doctate-common" }
tokio = { version = "1", features = ["full"] }
reqwest = { version = "0.12", default-features = false, features = ["json", "multipart", "rustls-tls"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
clap = { version = "4", features = ["derive"] }
anyhow = "1"
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
time = { version = "0.3", features = ["formatting", "macros"] }
similar = "2"
tempfile = "3"
[[bin]]
name = "run_full_case"
path = "src/bin/run_full_case.rs"
[[bin]]
name = "run_llm_only"
path = "src/bin/run_llm_only.rs"
[[bin]]
name = "diff_runs"
path = "src/bin/diff_runs.rs"