groq: Add tool calling support (#19971)

**Description:** Add with_structured_output to groq chat models
**Issue:** 
**Dependencies:** N/A
**Twitter handle:** N/A

docs/docs/guides/structured_output.ipynb

@@ -358,13 +358,119 @@
     "model_with_structure.invoke(\"Tell me a joke about cats\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "6214781d",
+   "metadata": {},
+   "source": [
+    "## Groq\n",
+    "\n",
+    "Groq provides an OpenAI-compatible function calling API"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "3066b2af",
+   "execution_count": 11,
+   "id": "70511bc3",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from langchain_groq import ChatGroq"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b7e97a6",
+   "metadata": {},
+   "source": [
+    "### Function Calling\n",
+    "\n",
+    "By default, we will use `function_calling`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "be9fdf04",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/reag/src/langchain/libs/core/langchain_core/_api/beta_decorator.py:87: LangChainBetaWarning: The function `with_structured_output` is in beta. It is actively being worked on, so the API may change.\n",
+      "  warn_beta(\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = ChatGroq()\n",
+    "model_with_structure = model.with_structured_output(Joke)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "e13f4676",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Joke(setup=\"Why don't cats play poker in the jungle?\", punchline='Too many cheetahs!')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model_with_structure.invoke(\"Tell me a joke about cats\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a82c2f55",
+   "metadata": {},
+   "source": [
+    "### JSON Mode\n",
+    "\n",
+    "We also support JSON mode. Note that we need to specify in the prompt the format that it should respond in."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "86574fb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_with_structure = model.with_structured_output(Joke, method=\"json_mode\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "01dced9c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Joke(setup=\"Why don't cats play poker in the jungle?\", punchline='Too many cheetahs!')"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model_with_structure.invoke(\n",
+    "    \"Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys\"\n",
+    ")"
+   ]
   }
  ],
  "metadata": {