{
 "cells": [
  {
   "cell_type": "raw",
   "id": "529aeba9",
   "metadata": {},
   "source": [
    "---\n",
    "sidebar_label: Fireworks\n",
    "---"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "642fd21c-600a-47a1-be96-6e1438b421a9",
   "metadata": {},
   "source": [
    "# ChatFireworks\n",
    "\n",
    ">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
    "\n",
    "This example goes over how to use LangChain to interact with `ChatFireworks` models."
   ]
  },
  {
   "cell_type": "raw",
   "id": "4a7c795e",
   "metadata": {},
   "source": [
    "%pip install langchain-fireworks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d00d850917865298",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "from langchain_core.messages import HumanMessage, SystemMessage\n",
    "from langchain_fireworks import ChatFireworks"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f28ebf8b-f14f-46c7-9962-8b8dc42e31be",
   "metadata": {},
   "source": [
    "# Setup\n",
    "\n",
    "1. Make sure the `langchain-fireworks` package is installed in your environment.\n",
    "2. Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
    "3. Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat. See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d096fb14-8acc-4047-9cd0-c842430c3a1d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import getpass\n",
    "import os\n",
    "\n",
    "if \"FIREWORKS_API_KEY\" not in os.environ:\n",
    "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
    "\n",
    "# Initialize a Fireworks chat model\n",
    "chat = ChatFireworks(model=\"accounts/fireworks/models/mixtral-8x7b-instruct\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8f13144-37cf-47a5-b5a0-e3cdf76d9a72",
   "metadata": {},
   "source": [
    "# Calling the Model Directly\n",
    "\n",
    "You can call the model directly with a system and human message to get answers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "72340871-ae2f-415f-b399-0777d32dc379",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content=\"Hello! I'm an AI language model, a helpful assistant designed to chat and assist you with any questions or information you might need. I'm here to make your experience as smooth and enjoyable as possible. How can I assist you today?\")"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ChatFireworks Wrapper\n",
    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
    "human_message = HumanMessage(content=\"Who are you?\")\n",
    "\n",
    "chat.invoke([system_message, human_message])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content=\"I'm an AI and do not have the ability to experience the weather firsthand. However,\")"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Setting additional parameters: temperature, max_tokens, top_p\n",
    "chat = ChatFireworks(\n",
    "    model=\"accounts/fireworks/models/mixtral-8x7b-instruct\",\n",
    "    temperature=1,\n",
    "    max_tokens=20,\n",
    ")\n",
    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
    "human_message = HumanMessage(content=\"How's the weather today?\")\n",
    "chat.invoke([system_message, human_message])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8c44cb36",
   "metadata": {},
   "source": [
    "# Tool Calling\n",
    "\n",
    "Fireworks offers the [`FireFunction-v1` tool calling model](https://fireworks.ai/blog/firefunction-v1-gpt-4-level-function-calling). You can use it for structured output and function calling use cases:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ee2db682",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'function': {'arguments': '{\"name\": \"Erick\", \"age\": 27}',\n",
      "              'name': 'ExtractFields'},\n",
      " 'id': 'call_J0WYP2TLenaFw3UeVU0UnWqx',\n",
      " 'index': 0,\n",
      " 'type': 'function'}\n"
     ]
    }
   ],
   "source": [
    "from pprint import pprint\n",
    "\n",
    "from langchain_core.pydantic_v1 import BaseModel\n",
    "\n",
    "\n",
    "class ExtractFields(BaseModel):\n",
    "    name: str\n",
    "    age: int\n",
    "\n",
    "\n",
    "chat = ChatFireworks(\n",
    "    model=\"accounts/fireworks/models/firefunction-v1\",\n",
    ").bind_tools([ExtractFields])\n",
    "\n",
    "result = chat.invoke(\"I am a 27 year old named Erick\")\n",
    "\n",
    "pprint(result.additional_kwargs[\"tool_calls\"][0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2321a4e6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}