add docling

book/cooltools/Chapter.ipynb

@@ -2393,7 +2393,7 @@
    "source": [
     "Transform any Python object into a CLI with `fire`.\n",
     "\n",
-    "`fire` is a neat library for turn your Python object into a CLI and to make the transition between Python and Bash easier."
+    "`fire` is a neat library for turning your Python object into a CLI and making the transition between Python and Bash easier."
    ]
   },
   {

book/llm/Chapter.ipynb

@@ -489,6 +489,48 @@
     "\n",
     "embeddings = list(embedding_model.embed(documents))"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Convert Files to Markdown & JSON with `docling`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Preparing your data for LLMs is a crucial step in RAG applications.\n",
+    "\n",
+    "`docling` simplifies this step for you by converting popular document formats like PDF or PPT to Markdown or JSON.\n",
+    "\n",
+    "It uses two models, layout analyis model and table structure recognition model, to process the files."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install docling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from docling.document_converter import DocumentConverter\n",
+    "\n",
+    "source = \"https://arxiv.org/pdf/2408.09869\"\n",
+    "converter = DocumentConverter()\n",
+    "result = converter.convert(source)\n",
+    "print(result.document.export_to_markdown())  \n",
+    "# Output: \"## Docling Technical Report[...]\""
+   ]
   }
  ],
  "metadata": {