feat(backend): add PDF extraction with OCR fallback and cache

backend/Dockerfile

@@ -0,0 +1,32 @@
+FROM python:3.11-slim
+
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_NO_CACHE_DIR=1 \
+    OMP_NUM_THREADS=2 \
+    TOKENIZERS_PARALLELISM=false
+
+# tesseract-ocr + pacote de idioma português + libs de imagem do MuPDF
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        tesseract-ocr \
+        tesseract-ocr-por \
+        tesseract-ocr-eng \
+        curl \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY requirements.txt requirements-dev.txt ./
+RUN pip install --no-cache-dir -r requirements-dev.txt
+
+COPY app ./app
+COPY tests ./tests
+
+RUN mkdir -p /data/vector_db /data/pdfs
+
+EXPOSE 8000
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 \
+    CMD curl -fsS http://localhost:8000/api/health || exit 1
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]