diff --git a/EverNote_To_OpenAI.ipynb b/EverNote_To_OpenAI.ipynb
index 31a4681..dd77ae4 100644
--- a/EverNote_To_OpenAI.ipynb
+++ b/EverNote_To_OpenAI.ipynb
@@ -4,7 +4,10 @@
    "cell_type": "markdown",
    "id": "18d62071e34b0d53",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "# This is an experiment: create vectorized embeddings out of an EverNote DB (PDF, DOCX, HTML, TXT)\n",
@@ -23,7 +26,10 @@
    "cell_type": "markdown",
    "id": "a8c8692786d83c00",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Dependencies\n",
@@ -40,7 +46,10 @@
      "end_time": "2024-03-21T15:10:31.827945Z",
      "start_time": "2024-03-21T15:10:29.646399Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -69,7 +78,10 @@
    "cell_type": "markdown",
    "id": "297746c807e95fbf",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "* pikepdf is used to repair some PDFs"
@@ -84,7 +96,10 @@
      "end_time": "2024-03-21T15:12:47.900384Z",
      "start_time": "2024-03-21T15:12:45.782477Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -113,7 +128,10 @@
    "cell_type": "markdown",
    "id": "7c7a7f6b0db3719e",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "* pypdf with all features is needed because this DB consists of 100+ PDFs "
@@ -128,7 +146,10 @@
      "end_time": "2024-03-21T15:17:00.760871Z",
      "start_time": "2024-03-21T15:16:58.635484Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -157,7 +178,10 @@
    "cell_type": "markdown",
    "id": "ce1350d2d6e3ed63",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Text extraction\n",
@@ -179,7 +203,10 @@
      "end_time": "2024-03-17T15:34:05.847778Z",
      "start_time": "2024-03-17T15:25:49.787814Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -1038,7 +1065,10 @@
    "cell_type": "markdown",
    "id": "e1bcc07f980c865f",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Chunking of the texts\n",
@@ -1055,7 +1085,10 @@
      "end_time": "2024-03-17T16:13:14.479469Z",
      "start_time": "2024-03-17T16:13:14.476765Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -1071,7 +1104,10 @@
      "end_time": "2024-03-21T15:17:53.867414Z",
      "start_time": "2024-03-21T15:17:32.731232Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -1107,7 +1143,10 @@
    "cell_type": "markdown",
    "id": "aea7ceb111fed5f3",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Embedding costs - why no OpenAI?\n",
@@ -1126,7 +1165,10 @@
      "end_time": "2024-03-21T15:18:51.003585Z",
      "start_time": "2024-03-21T15:18:31.411234Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -1153,7 +1195,10 @@
    "cell_type": "markdown",
    "id": "8012516604037e2f",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Use Hugging Face Embeddings Sentence Transformers\n",
@@ -1177,7 +1222,10 @@
      "end_time": "2024-03-21T15:19:15.167038Z",
      "start_time": "2024-03-21T15:19:15.031139Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -1201,7 +1249,10 @@
      "end_time": "2024-03-21T15:42:28.163005Z",
      "start_time": "2024-03-21T15:42:26.222594Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -1224,7 +1275,10 @@
      "end_time": "2024-03-21T16:18:45.930652Z",
      "start_time": "2024-03-21T16:18:42.989032Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -1246,7 +1300,10 @@
    "cell_type": "markdown",
    "id": "b347fb5ee68daf60",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Batch process the embedding\n",
@@ -1270,7 +1327,10 @@
      "end_time": "2024-03-21T16:04:44.572979Z",
      "start_time": "2024-03-21T16:04:43.521107Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -1293,7 +1353,10 @@
      "end_time": "2024-03-21T16:10:22.121211Z",
      "start_time": "2024-03-21T16:08:20.585372Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -1397,9 +1460,13 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "5f01a969c4aedac8",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -1410,21 +1477,21 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,