feat(notebook): aggiunge sezione chunking post-MinerU

Clone del repo RAG, cella config modificabile che sovrascrive
chunks/config.py, esecuzione chunker.py e download automatico
di chunks.json.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

mineru.ipynb

@@ -257,6 +257,32 @@
    "source": [
     "!mineru -p ./ -o ./output -b pipeline"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": "## 3. Chunking\n\nScarica il repo RAG e suddivide il Markdown in chunk pronti per la vettorizzazione."
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": "!git clone https://santantonio.sytes.net/davide/rag-from-scratch.git /content/rag 2>/dev/null || (cd /content/rag && git pull)"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": "# ── Parametri chunking — modifica qui prima di eseguire ──────────────────────\n\nMAX_CHARS = 1200      # lunghezza massima chunk (caratteri)\nMIN_CHARS = 80        # soglia minima (paragrafi più corti vengono fusi)\nCONTEXT_DEPTH = 3     # livelli heading inclusi nel prefisso (1–3)\nMERGE_SHORT_PARAGRAPHS = True\nSKIP_PRE_HEADING = True   # salta contenuto prima del primo heading\nSKIP_HEADINGS = {\n    \"indice\",\n    \"sommario\",\n    \"bibliografia\",\n    \"ringraziamenti\",\n    \"abbreviazioni\",\n}\n\n# ── Applica al config del repo ────────────────────────────────────────────────\n\nconfig_path = \"/content/rag/chunks/config.py\"\nwith open(config_path) as f:\n    src = f.read()\n\nimport re\n\ndef _replace(src, name, value):\n    if isinstance(value, bool):\n        v = \"True\" if value else \"False\"\n        return re.sub(rf\"^{name}\\s*=.*$\", f\"{name}: bool = {v}\", src, flags=re.MULTILINE)\n    elif isinstance(value, int):\n        return re.sub(rf\"^{name}\\s*=.*$\", f\"{name}: int = {value}\", src, flags=re.MULTILINE)\n    elif isinstance(value, set):\n        items = \",\\n    \".join(f'\"{s}\"' for s in sorted(value))\n        block = f\"{name}: set[str] = {{\\n    {items},\\n}}\"\n        return re.sub(rf\"^{name}.*?^\\}}\", block, src, flags=re.MULTILINE | re.DOTALL)\n    return src\n\nfor name, val in [\n    (\"MAX_CHARS\", MAX_CHARS),\n    (\"MIN_CHARS\", MIN_CHARS),\n    (\"CONTEXT_DEPTH\", CONTEXT_DEPTH),\n    (\"MERGE_SHORT_PARAGRAPHS\", MERGE_SHORT_PARAGRAPHS),\n    (\"SKIP_PRE_HEADING\", SKIP_PRE_HEADING),\n    (\"SKIP_HEADINGS\", SKIP_HEADINGS),\n]:\n    src = _replace(src, name, val)\n\nwith open(config_path, \"w\") as f:\n    f.write(src)\n\nprint(\"Config applicato:\", config_path)\n"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": "import os, sys, shutil\nsys.path.insert(0, \"/content/rag\")\n\n# Copia l'output MinerU dove il chunker si aspetta di trovarlo\nstem_output_src = f\"./output/{STEM}/auto\"\nstem_output_dst = f\"/content/rag/sources/{STEM}_output/auto\"\nif os.path.isdir(stem_output_src):\n    os.makedirs(stem_output_dst, exist_ok=True)\n    shutil.copytree(stem_output_src, stem_output_dst, dirs_exist_ok=True)\n\n!python /content/rag/chunks/chunker.py --stem {STEM}\n\n# Scarica chunks.json\nchunks_path = f\"/content/rag/chunks/{STEM}/chunks.json\"\nif os.path.exists(chunks_path):\n    try:\n        from google.colab import files\n        files.download(chunks_path)\n    except ImportError:\n        print(f\"Chunk pronti in: {chunks_path}\")\nelse:\n    print(\"chunks.json non trovato — controlla l'output sopra.\")\n"
   }
  ],
  "metadata": {
@@ -275,4 +301,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 0
-}
+}