.github/workflows/push_to_hf_space.yml

name: Sync to Hugging Face Space (always strip binaries)

on:
  push:
    branches: [ "hf-deploy" ]
  workflow_dispatch:

jobs:
  deploy:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout source
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          ref: hf-deploy         

      - name: Create clean snapshot (remove .pkl/.faiss no matter what)
        run: |
          set -euxo pipefail

          # Export current commit as plain files (no .git history)
          rm -rf /tmp/snapshot
          mkdir -p /tmp/snapshot
          git archive --format=tar HEAD | tar -x -C /tmp/snapshot

          echo "== Files matching .pkl/.faiss BEFORE removal =="
          (cd /tmp/snapshot && find . -type f \( -name "*.pkl" -o -name "*.faiss" \) -print) || true

          # Always delete these binaries (even if someone committed them)
          (cd /tmp/snapshot && find . -type f \( -name "*.pkl" -o -name "*.faiss" \) -print -delete) || true

          echo "== Files matching .pkl/.faiss AFTER removal =="
          (cd /tmp/snapshot && find . -type f \( -name "*.pkl" -o -name "*.faiss" \) -print) || true

          # Ensure they won't be committed into the snapshot repo
          printf "\n# Never deploy vectorstore binaries to Spaces\n*.pkl\n*.faiss\n" >> /tmp/snapshot/.gitignore

          # Build a new single-commit git repo from the cleaned snapshot
          cd /tmp/snapshot
          git init
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
          git add -A
          git commit -m "Deploy snapshot to HF (binaries stripped)"

      - name: Push snapshot to Hugging Face Space (HF main)
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN }}
          HF_USERNAME: ritup3          # CHANGE if needed
          SPACE_NAME: PersonaRag       # CHANGE if needed
        run: |
          set -euxo pipefail
          cd /tmp/snapshot

          # Authenticated remote for HF Space
          git remote add space https://$HF_USERNAME:$HF_TOKEN@huggingface.co/spaces/$HF_USERNAME/$SPACE_NAME

          # Spaces deploy from branch "main"
          git branch -M main
          git push space main --force