10d0a6ba94
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.
35 lines
850 B
TOML
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"
|