ci.yml

name: CI

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

jobs:
  lint:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements.txt

      - name: Syntax check
        run: |
          python -m py_compile ingest.py
          python -m py_compile query.py
          python -m py_compile rag/loader.py
          python -m py_compile rag/chunker.py
          python -m py_compile rag/embeddings.py
          python -m py_compile rag/vectorstore.py
          python -m py_compile rag/retriever.py
          python -m py_compile rag/generator.py
          echo "Todos os modulos OK"

      - name: Unit tests
        run: |
          python -c "
          from rag.chunker import chunk_text

          # Chunking basico
          texto = 'palavra ' * 600
          chunks = chunk_text(texto, chunk_size=500, overlap=50)
          assert len(chunks) > 1, 'deve gerar mais de 1 chunk'
          print(f'chunk_text: {len(chunks)} chunks gerados OK')

          # Overlap — segundo chunk deve comecar antes do fim do primeiro
          c1_words = set(chunks[0].split())
          c2_words = set(chunks[1].split())
          assert len(c1_words & c2_words) > 0, 'overlap esperado entre chunks'
          print('overlap entre chunks OK')

          from rag.embeddings import cosine_similarity
          a = [1.0, 0.0, 0.0]
          b = [1.0, 0.0, 0.0]
          assert cosine_similarity(a, b) == 1.0, 'vetores identicos devem ter sim=1'
          c = [0.0, 1.0, 0.0]
          assert cosine_similarity(a, c) == 0.0, 'vetores ortogonais devem ter sim=0'
          print('cosine_similarity OK')
          "