{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "16f2c32e",
   "metadata": {},
   "source": [
    "## Document Loading\n",
    "\n",
    "Load a blog post on agents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c9fadce0",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import WebBaseLoader\n",
    "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
    "text = loader.load()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4086be03",
   "metadata": {},
   "source": [
    "## Run Template\n",
    "\n",
    "\n",
    "As shown in the README, add template and start server:\n",
    "```\n",
    "langchain serve add openai-functions\n",
    "langchain start\n",
    "```\n",
    "\n",
    "We can now look at the endpoints:\n",
    "\n",
    "http://127.0.0.1:8000/docs#\n",
    "\n",
    "And specifically at our loaded template:\n",
    "\n",
    "http://127.0.0.1:8000/docs#/default/invoke_openai_functions_invoke_post\n",
    " \n",
    "We can also use remote runnable to call it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ed507784",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langserve.client import RemoteRunnable\n",
    "oai_function = RemoteRunnable('http://localhost:8000/openai-functions')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "68046695",
   "metadata": {},
   "source": [
    "The function call will perform tagging:\n",
    "\n",
    "* summarize\n",
    "* provide keywords\n",
    "* provide language"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6dace748",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'Overview', 'arguments': '{\\n  \"summary\": \"This article discusses the concept of building agents with LLM (large language model) as their core controller. It explores the potentiality of LLM as a general problem solver and describes the key components of an LLM-powered autonomous agent system, including planning, memory, and tool use. The article also presents case studies and challenges related to building LLM-powered agents.\",\\n  \"language\": \"English\",\\n  \"keywords\": \"LLM, autonomous agents, planning, memory, tool use, case studies, challenges\"\\n}'}})"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "oai_function.invoke(text[0].page_content[0:1500])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "langserve",
   "language": "python",
   "name": "langserve"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}