Add CI workflow to build RAG database on release

This commit is contained in:
Yiorgis Gozadinos 2026-04-02 15:07:37 +03:00
parent a0029e9ab9
commit 076916a8cc
No known key found for this signature in database
2 changed files with 66 additions and 0 deletions

8
.github/haiku.rag.yaml vendored Normal file
View file

@ -0,0 +1,8 @@
embeddings:
model:
provider: ollama
name: qwen3-embedding:4b
processing:
conversion_options:
do_ocr: false

58
.github/workflows/build-rag-db.yml vendored Normal file
View file

@ -0,0 +1,58 @@
name: Build RAG database
on:
release:
types: [published]
workflow_dispatch:
jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: astral-sh/setup-uv@v4
with:
enable-cache: true
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version-file: "pyproject.toml"
- name: Install dependencies
run: uv sync
- name: Restore previous RAG database
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
LATEST=$(gh release list --limit 10 --json tagName --jq '.[].tagName' | while read -r tag; do
if gh release view "$tag" --json assets --jq '.assets[].name' 2>/dev/null | grep -q "haiku-rag-docs.lancedb.tar.gz"; then
echo "$tag"
break
fi
done)
if [ -n "$LATEST" ]; then
gh release download "$LATEST" --pattern "haiku-rag-docs.lancedb.tar.gz"
tar xzf haiku-rag-docs.lancedb.tar.gz
rm haiku-rag-docs.lancedb.tar.gz
echo "Restored database from $LATEST"
else
echo "No previous database found, starting fresh"
uv run haiku-rag --config ${{ github.workspace }}/.github/haiku.rag.yaml init --db rag.lancedb
fi
- name: Build RAG database
env:
OLLAMA_BASE_URL: ${{ secrets.OLLAMA_BASE_URL }}
OLLAMA_API_KEY: ${{ secrets.OLLAMA_API_KEY }}
run: uv run haiku-rag --config ${{ github.workspace }}/.github/haiku.rag.yaml add-src docs/ --db rag.lancedb
- name: Package RAG database
run: tar czf haiku-rag-docs.lancedb.tar.gz rag.lancedb/
- name: Upload to release
if: github.event_name == 'release'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: gh release upload ${{ github.event.release.tag_name }} haiku-rag-docs.lancedb.tar.gz --clobber
- name: Upload workflow artifact
if: github.event_name == 'workflow_dispatch'
uses: actions/upload-artifact@v4
with:
name: haiku-rag-docs.lancedb.tar.gz
path: haiku-rag-docs.lancedb.tar.gz
retention-days: 1