Files
lean-bench/.gitea/workflows/ingest.yml
T
Zayden-Jung d3555d9a52
ci / test (push) Failing after 12s
ci / lean-project (push) Successful in 5s
docker / image (push) Failing after 5s
Rebuild lean-bench: pages in, verified indexed Lean out
Replaces the previous tree entirely. The pipeline is four separable pieces, each
testable on its own:

1. leanbench/llm.py      provider-neutral OpenAI-compatible connector, stdlib only,
                        with retries, JSON coercion and a scripted client so the
                        rest of the code is testable without a network.
2. leanbench/detect.py   per-page detection of formalizable mathematics. Case 1 is
                        mathematics asserted as fact (definition/theorem/lemma/...,
                        deliberately not sub-classified); case 2 is a problem left
                        open to the reader. Hits come back as spans -- start page
                        and index, end page and index -- so several per page is
                        normal. A hit cut off by the page end makes the detector
                        re-read that page together with the next, repeatedly, so an
                        item spread over three pages is found whole.
                        Offsets come from verbatim quotes resolved by
                        leanbench/anchors.py (exact -> whitespace-insensitive ->
                        fuzzy), because models quote well and count badly.
3. leanbench/formalize.py + leanbench/verify.py
                        each span becomes one Lean 4 declaration, judged by the real
                        compiler: full elaboration for case 1, statement legality
                        only for case 2, which has no proof to check. Lean's own
                        diagnostics feed back for a repair attempt. "verified" (Lean
                        accepted it) and "proved" (accepted with no sorry) are kept
                        strictly apart.
4. leanbench/db.py       indexed SQLite plus JSONL export. Every item is indexed by
                        the types of its inputs, or by its own type when it is not a
                        proof, and records the source book (sha256) and the page it
                        starts on -- so `drop --source H --pages A-B` followed by a
                        re-ingest redoes exactly those pages and nothing else.

Also: lean/ Lake project pinned to Mathlib, docker/ image carrying Lean 4 and a
prebuilt Mathlib (the Mathlib revision and the toolchain are resolved against each
other at build time rather than both hardcoded), and .gitea/workflows for tests,
image build and push to the Gitea registry, and a manual "submit a book" run.

58 tests; they need neither network nor Lean.
2026-09-19 07:05:52 +00:00

101 lines
3.4 KiB
YAML

name: ingest
# Submit a book and run the whole pipeline on the runner, inside the image the
# docker workflow built. The database and the JSONL export come back as artifacts.
#
# The source can be a path inside the repository or a URL the runner can reach.
# Set the DASHSCOPE_API_KEY secret (or whichever key your provider uses) first.
on:
workflow_dispatch:
inputs:
source:
description: "Path in the repo, or a URL, of the book to ingest"
required: true
pages:
description: "Page range, e.g. 30-60 (blank = the whole book)"
required: false
default: ""
title:
description: "Human title for this source"
required: false
default: ""
image:
description: "Image to run"
required: false
default: "gitea.entroia.com/zayden-jung/lean-bench:latest"
verify:
description: "Run Lean verification (slow but the point)"
required: false
default: "true"
jobs:
ingest:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Fetch the source
id: source
run: |
set -eu
mkdir -p books data out
src='${{ inputs.source }}'
case "$src" in
http://*|https://*)
name="$(basename "${src%%\?*}")"
curl -fsSL --retry 3 -o "books/$name" "$src"
;;
*)
[ -f "$src" ] || { echo "::error::$src is not in the repository"; exit 1; }
name="$(basename "$src")"
cp "$src" "books/$name"
;;
esac
ls -l "books/$name"
echo "name=$name" >> "$GITHUB_OUTPUT"
- name: Log in to the registry
run: |
set -eu
token='${{ secrets.GITEA_TOKEN }}'
[ -n "$token" ] || token='${{ secrets.GITHUB_TOKEN }}'
echo "$token" | docker login gitea.entroia.com -u '${{ github.actor }}' --password-stdin
- name: Ingest
env:
DASHSCOPE_API_KEY: ${{ secrets.DASHSCOPE_API_KEY }}
LEANBENCH_LLM_MODEL: ${{ vars.LEANBENCH_LLM_MODEL }}
LEANBENCH_LLM_BASE_URL: ${{ vars.LEANBENCH_LLM_BASE_URL }}
run: |
set -eu
[ -n "${DASHSCOPE_API_KEY:-}" ] || { echo "::error::Set the DASHSCOPE_API_KEY secret"; exit 1; }
docker pull '${{ inputs.image }}'
args="ingest /books/${{ steps.source.outputs.name }} --export /data/items.jsonl --detections /data/detections.jsonl"
[ -n "${{ inputs.pages }}" ] && args="$args --pages ${{ inputs.pages }}"
[ -n "${{ inputs.title }}" ] && args="$args --title '${{ inputs.title }}'"
[ '${{ inputs.verify }}' = 'true' ] || args="$args --no-verify"
docker run --rm \
-e DASHSCOPE_API_KEY \
-e LEANBENCH_LLM_MODEL \
-e LEANBENCH_LLM_BASE_URL \
-v "$PWD/books:/books:ro" \
-v "$PWD/data:/data" \
'${{ inputs.image }}' \
sh -c "lean-bench $args && lean-bench stats"
- name: Collect
if: always()
run: |
set -eu
cp -f data/*.jsonl out/ 2>/dev/null || true
cp -f data/leanbench.sqlite out/ 2>/dev/null || true
ls -l out || true
- uses: actions/upload-artifact@v3
if: always()
with:
name: leanbench-${{ steps.source.outputs.name }}
path: out/
retention-days: 30