Add file filter param to Git loader (#2904)

Allows users to specify what files should be loaded instead of
indiscriminately loading the entire repo.

extends #2851 

NOTE: for reviewers, `hide whitespace` option recommended since I
changed the indentation of an if-block to use `continue` instead so it
looks less like a Christmas tree :)

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

@@ -18,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -32,7 +32,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -59,27 +59,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "1040"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "len(data)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -103,7 +92,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -112,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -125,7 +114,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -134,16 +123,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "1040"
+       "1074"
       ]
      },
-     "execution_count": 30,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -152,6 +141,25 @@
     "len(data)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Filtering files to load"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GitLoader\n",
+    "\n",
+    "# eg. loading only python files\n",
+    "loader = GitLoader(repo_path=\"./example_data/test_repo1/\", file_filter=lambda file_path: file_path.endswith(\".py\"))"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -176,7 +184,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.3"
   }
  },
  "nbformat": 4,