Add Mathpix pdf loader (#3727)

Inspo
https://twitter.com/danielgross/status/1651695062307274754?s=46&t=1zHLap5WG4I_kQPPjfW9fA

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

docs/modules/indexes/document_loaders/examples/pdf.ipynb

@@ -155,6 +155,46 @@
     "    print(str(doc.metadata[\"page\"]) + \":\", doc.page_content)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "6d5c9879",
+   "metadata": {},
+   "source": [
+    "## Using MathPix\n",
+    "\n",
+    "Inspired by Daniel Gross's [https://gist.github.com/danielgross/3ab4104e14faccc12b49200843adab21](https://gist.github.com/danielgross/3ab4104e14faccc12b49200843adab21)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "950eb58f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import MathpixPDFLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb6fd473",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = MathpixPDFLoader(\"example_data/layout-parser-paper.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a1d41e1a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "09d64998",
@@ -568,7 +608,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f0048206",
+   "id": "15b57eab",
    "metadata": {},
    "source": [
     "## PyPDF Directory\n",
@@ -579,7 +619,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "ecd0cb16",
+   "id": "b9e521d9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -589,7 +629,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "96592167",
+   "id": "4b20590f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -599,7 +639,7 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "c750454c",
+   "id": "e5ead943",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -609,7 +649,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ab7f8fdb",
+   "id": "ea25b03c",
    "metadata": {},
    "outputs": [],
    "source": []