# Quickstart ## Install mcaligner needs Python 3.11 or later and depends on MCParser (a pre-release): ```bash pip install --pre mcaligner # or: uv tool install --prerelease allow mcaligner export ANTHROPIC_API_KEY=... # the key for whichever provider your models use mcaligner --version ``` To work from a clone, run `uv sync` in the repository and prefix the commands in these docs with `uv run`. ## Data You need two parsed CoNLL-U files (see [Preparing files with MCParser](preparing.md)) (the same `sent_id` on both sides) and, for evaluation or evidence, an alignment set in JSON Lines (see [Data](data.md)). Below, `A` and `B` stand for the two CoNLL-U files: ```bash SRC="-s ar=data/A.conllu -s grc=data/B.conllu" ``` ## Align ```bash mcaligner run $SRC \ -a silver=ar,grc,data/ArabicAligned.jsonl:ro \ -a pred=ar,grc,out/pred.jsonl \ --target pred --max-sentences 5 ``` `silver` is read-only evidence; `pred` is written (created on first save, with an edit history in `out/pred.jsonl.history.jsonl`). The run prints its progress, then the tokens and the estimated cost per model. ## Evaluate and export ```bash mcaligner evaluate out/pred.jsonl gold.jsonl --annotated-only mcaligner lexicon $SRC -a pred=ar,grc,out/pred.jsonl -o lexicon.yaml ``` ## Settings ```bash mcaligner settings > settings.yaml # edit, then: run --settings settings.yaml ```