add function calling program

docs/docs/examples/llm/mistralai.ipynb

@@ -631,6 +631,66 @@
     "    print(f\"Name: {s.tool_name}, Input: {s.raw_input}, Output: {str(s)}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "96430944-27b6-45e1-8013-41460252ecb2",
+   "metadata": {},
+   "source": [
+    "## Structured Prediction\n",
+    "\n",
+    "An important use case for function calling is extracting structured objects. LlamaIndex provides an intuitive interface for this through `structured_predict` - simply define the target Pydantic class (can be nested), and given a prompt, we extract out the desired object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "13e43ccb-1cbf-49e3-aa34-fdcbe00865bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.mistralai import MistralAI\n",
+    "from llama_index.core.prompts import PromptTemplate\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "\n",
+    "class Restaurant(BaseModel):\n",
+    "    \"\"\"A restaurant with name, city, and cuisine.\"\"\"\n",
+    "\n",
+    "    name: str\n",
+    "    city: str\n",
+    "    cuisine: str\n",
+    "\n",
+    "\n",
+    "llm = MistralAI(model=\"mistral-large-latest\")\n",
+    "prompt_tmpl = PromptTemplate(\n",
+    "    \"Generate a restaurant in a given city {city_name}\"\n",
+    ")\n",
+    "restaurant_obj = llm.structured_predict(\n",
+    "    Restaurant, prompt_tmpl, city_name=\"Miami\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "850f02e7-1bb1-4e5f-870d-6528a36d4d22",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Restaurant(name='Mandolin Aegean Bistro', city='Miami', cuisine='Greek')"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "restaurant_obj"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5152a2b4-78e6-47a5-933d-f5186ec0f775",

docs/docs/examples/llm/openai.ipynb

@@ -322,7 +322,9 @@
    "source": [
     "## Function Calling\n",
     "\n",
-    "OpenAI models have native support for function calling. This conveniently integrates with LlamaIndex tool abstractions, letting you plug in any arbitrary Python function to the LLM."
+    "OpenAI models have native support for function calling. This conveniently integrates with LlamaIndex tool abstractions, letting you plug in any arbitrary Python function to the LLM.\n",
+    "\n",
+    "In the example below, we define a function to generate a Song object."
    ]
   },
   {
@@ -411,6 +413,66 @@
     "    print(f\"Name: {s.tool_name}, Input: {s.raw_input}, Output: {str(s)}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "7ede8d94-524b-4a51-8150-552df952f1bf",
+   "metadata": {},
+   "source": [
+    "## Structured Prediction\n",
+    "\n",
+    "An important use case for function calling is extracting structured objects. LlamaIndex provides an intuitive interface for this through `structured_predict` - simply define the target Pydantic class (can be nested), and given a prompt, we extract out the desired object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "04312089-bf9a-48d0-918f-ca1b3808439b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.core.prompts import PromptTemplate\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "\n",
+    "class Restaurant(BaseModel):\n",
+    "    \"\"\"A restaurant with name, city, and cuisine.\"\"\"\n",
+    "\n",
+    "    name: str\n",
+    "    city: str\n",
+    "    cuisine: str\n",
+    "\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
+    "prompt_tmpl = PromptTemplate(\n",
+    "    \"Generate a restaurant in a given city {city_name}\"\n",
+    ")\n",
+    "restaurant_obj = llm.structured_predict(\n",
+    "    Restaurant, prompt_tmpl, city_name=\"San Francisco\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4b6fffcd-ff1e-4755-a851-1c6757a8075e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Restaurant(name='Tasty Bites', city='San Francisco', cuisine='Italian')"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "restaurant_obj"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "df5fa1ab-f598-46da-80f3-f6af5dd2fe83",