chatbot_multiagent.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import utils\n",
    "\n",
    "utils.load_env()\n",
    "os.environ['LANGCHAIN_TRACING_V2'] = \"false\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.globals import set_debug, set_verbose\n",
    "\n",
    "set_verbose(True)\n",
    "set_debug(False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_core.messages import HumanMessage\n",
    "import operator\n",
    "import functools\n",
    "\n",
    "# for llm model\n",
    "from langchain_openai import ChatOpenAI\n",
    "# from langchain_community.chat_models import ChatOpenAI\n",
    "from tools import (\n",
    "    find_place_from_text, \n",
    "    nearby_search, \n",
    "    nearby_dense_community, \n",
    "    google_search, \n",
    "    population_doc_retriever\n",
    ")\n",
    "from typing import Annotated, Sequence, TypedDict\n",
    "from langchain_core.messages import (\n",
    "    AIMessage, \n",
    "    HumanMessage,\n",
    "    BaseMessage,\n",
    "    ToolMessage\n",
    ")\n",
    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
    "from langgraph.graph import END, StateGraph, START\n",
    "\n",
    "\n",
    "\n",
    "## tools and LLM\n",
    "# Bind the tools to the model\n",
    "tools = [population_doc_retriever, find_place_from_text, nearby_search, nearby_dense_community, google_search]  # Include both tools if needed\n",
    "# tools = [find_place_from_text, nearby_search]\n",
    "\n",
    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0.0)\n",
    "\n",
    "## Create agents\n",
    "def create_agent(llm, tools, system_message: str):\n",
    "    \"\"\"Create an agent.\"\"\"\n",
    "    prompt = ChatPromptTemplate.from_messages(\n",
    "        [\n",
    "            (\n",
    "                \"system\",\n",
    "                \"You are a helpful AI assistant, collaborating with other assistants.\"\n",
    "                \" Use the provided tools to progress towards answering the question.\"\n",
    "                \" If you are unable to fully answer, that's OK, another assistant with different tools \"\n",
    "                \" will help where you left off. Execute what you can to make progress.\"\n",
    "                \" If you or any of the other assistants have the final answer or deliverable,\"\n",
    "                \" \"\n",
    "                \" You have access to the following tools: {tool_names}.\\n{system_message}\",\n",
    "            ),\n",
    "            MessagesPlaceholder(variable_name=\"messages\"),\n",
    "        ]\n",
    "    )\n",
    "    prompt = prompt.partial(system_message=system_message)\n",
    "    prompt = prompt.partial(tool_names=\", \".join([tool.name for tool in tools]))\n",
    "    #llm_with_tools = llm.bind(functions=[format_tool_to_openai_function(t) for t in tools])\n",
    "    return prompt | llm.bind_tools(tools)\n",
    "    #agent = prompt | llm_with_tools\n",
    "    #return agent\n",
    "\n",
    "\n",
    "## Define state\n",
    "# This defines the object that is passed between each node\n",
    "# in the graph. We will create different nodes for each agent and tool\n",
    "class AgentState(TypedDict):\n",
    "    messages: Annotated[Sequence[BaseMessage], operator.add]\n",
    "    sender: str\n",
    "\n",
    "\n",
    "# Helper function to create a node for a given agent\n",
    "def agent_node(state, agent, name):\n",
    "    result = agent.invoke(state)\n",
    "    # We convert the agent output into a format that is suitable to append to the global state\n",
    "    if isinstance(result, ToolMessage):\n",
    "        pass\n",
    "    else:\n",
    "        result = AIMessage(**result.dict(exclude={\"type\", \"name\"}), name=name)\n",
    "    return {\n",
    "        \"messages\": [result],\n",
    "        # Since we have a strict workflow, we can\n",
    "        # track the sender so we know who to pass to next.\n",
    "        \"sender\": name,\n",
    "    }\n",
    "\n",
    "\n",
    "## Define Agents Node\n",
    "# Research agent and node\n",
    "from prompt import agent_meta\n",
    "agent_name = [meta['name'] for meta in agent_meta]\n",
    "\n",
    "agents={}\n",
    "agent_nodes={}\n",
    "\n",
    "for meta in agent_meta:\n",
    "    name = meta['name']\n",
    "    prompt = meta['prompt']\n",
    "    \n",
    "    agents[name] = create_agent(\n",
    "            llm,\n",
    "            tools,\n",
    "            system_message=prompt,\n",
    "        )\n",
    "    \n",
    "    agent_nodes[name] = functools.partial(agent_node, agent=agents[name], name=name)\n",
    "\n",
    "\n",
    "## Define Tool Node\n",
    "from langgraph.prebuilt import ToolNode\n",
    "from typing import Literal\n",
    "\n",
    "tool_node = ToolNode(tools)\n",
    "\n",
    "def router(state) -> Literal[\"call_tool\", \"__end__\", \"continue\"]:\n",
    "    # This is the router\n",
    "    messages = state[\"messages\"]\n",
    "    last_message = messages[-1]\n",
    "    if \"continue\" in last_message.content:\n",
    "        return \"continue\"\n",
    "    if last_message.tool_calls:\n",
    "        # The previous agent is invoking a tool\n",
    "        return \"call_tool\"\n",
    "    if \"%SIjfE923hf\" in last_message.content:\n",
    "        # Any agent decided the work is done\n",
    "        return \"__end__\"\n",
    "    else:\n",
    "        return \"continue\"\n",
    "\n",
    "\n",
    "\n",
    "## Workflow Graph\n",
    "workflow = StateGraph(AgentState)\n",
    "\n",
    "# add agent nodes\n",
    "for name, node in agent_nodes.items():\n",
    "    workflow.add_node(name, node)\n",
    "    \n",
    "workflow.add_node(\"call_tool\", tool_node)\n",
    "\n",
    "\n",
    "workflow.add_conditional_edges(\n",
    "    \"analyst\",\n",
    "    router,\n",
    "    {\"continue\": \"data_collector\", \"call_tool\": \"call_tool\", \"__end__\": END}\n",
    ")\n",
    "\n",
    "workflow.add_conditional_edges(\n",
    "    \"data_collector\",\n",
    "    router,\n",
    "    {\"call_tool\": \"call_tool\", \"continue\": \"reporter\", \"__end__\": END}\n",
    ")\n",
    "\n",
    "workflow.add_conditional_edges(\n",
    "    \"reporter\",\n",
    "    router,\n",
    "    {\"continue\": \"data_collector\", \"call_tool\": \"call_tool\", \"__end__\": END}\n",
    ")\n",
    "\n",
    "workflow.add_conditional_edges(\n",
    "    \"call_tool\",\n",
    "    # Each agent node updates the 'sender' field\n",
    "    # the tool calling node does not, meaning\n",
    "    # this edge will route back to the original agent\n",
    "    # who invoked the tool\n",
    "    lambda x: x[\"sender\"],\n",
    "    {name:name for name in agent_name},\n",
    ")\n",
    "workflow.add_edge(START, \"analyst\")\n",
    "graph = workflow.compile()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from IPython.display import Image, display\n",
    "\n",
    "# try:\n",
    "#     display(Image(graph.get_graph(xray=True).draw_mermaid_png()))\n",
    "# except Exception:\n",
    "#     # This requires some extra dependencies and is optional\n",
    "#     pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: analyst\n",
      "Tool Calls:\n",
      "  find_place_from_text (call_GYUgNNbPxdxKpJI5gxtUjdF0)\n",
      " Call ID: call_GYUgNNbPxdxKpJI5gxtUjdF0\n",
      "  Args:\n",
      "    location: ทองหล่อ\n",
      "  search_population_community_household_expenditures_data (call_9QJBdwVh2bUtTlsshuftteDa)\n",
      " Call ID: call_9QJBdwVh2bUtTlsshuftteDa\n",
      "  Args:\n",
      "    query: โรงแรม ทองหล่อ\n",
      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
      "Name: find_place_from_text\n",
      "\n",
      "\n",
      "    address: ถ. ทองหล่อ กรุงเทพมหานคร ประเทศไทย\n",
      "\n",
      "    location: {'lat': 13.7424537, 'lng': 100.5854359}\n",
      "\n",
      "    location_name: ถ. ทองหล่อ\n",
      "\n",
      "    \n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: analyst\n",
      "\n",
      "I have gathered some initial data regarding hotels in the Thonglor area. Here are the details:\n",
      "\n",
      "1. **Location**: Thonglor, Bangkok\n",
      "   - Latitude: 13.7424537\n",
      "   - Longitude: 100.5854359\n",
      "\n",
      "2. **Hotel Business Analysis**:\n",
      "   - The data indicates various aspects of hotel operations in the area, including occupancy rates and trends over the years. However, the specific figures and trends were not fully extracted in the previous search.\n",
      "\n",
      "To further analyze the hotel business in Thonglor, I recommend looking into the following aspects:\n",
      "- **Occupancy Rates**: Historical data on how many rooms are filled over time.\n",
      "- **Average Daily Rate (ADR)**: The average revenue earned for an occupied room.\n",
      "- **Revenue Per Available Room (RevPAR)**: A key performance metric in the hotel industry.\n",
      "- **Market Trends**: Insights into the competitive landscape and customer preferences.\n",
      "\n",
      "Would you like me to search for specific data on occupancy rates, ADR, or any other particular aspect of the hotel business in Thonglor?\n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: data_collector\n",
      "Tool Calls:\n",
      "  nearby_search (call_Gztb2XtVgwFG8CizWFDfDjQW)\n",
      " Call ID: call_Gztb2XtVgwFG8CizWFDfDjQW\n",
      "  Args:\n",
      "    input_dict: {'keyword': 'hotel', 'location_name': 'Thonglor', 'radius': 1000, 'place_type': 'hotel'}\n",
      "  google_search (call_cyycO0Dy4mP0jwTg1LfsoPoy)\n",
      " Call ID: call_cyycO0Dy4mP0jwTg1LfsoPoy\n",
      "  Args:\n",
      "    input_dict: {'keyword': 'number of rooms in hotels in Thonglor'}\n",
      "  search_population_community_household_expenditures_data (call_v1FAVlUjTAzWFL0bRZueuGY7)\n",
      " Call ID: call_v1FAVlUjTAzWFL0bRZueuGY7\n",
      "  Args:\n",
      "    query: Thonglor\n",
      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
      "Name: nearby_search\n",
      "\n",
      "number of results: 21\n",
      "\n",
      "        **Metropole Bangkok**\n",
      "\n",
      "        address: 2802 Thong Lo, Bang Kapi, Huai Khwang\n",
      "\n",
      "        rating: 4.1\n",
      "\n",
      "\n",
      "        \n",
      "        **Mövenpick Ekkamai Bangkok**\n",
      "\n",
      "        address: 559 Sukhumvit 63, Khlong Tan Nuea, Watthana\n",
      "\n",
      "        rating: 4.4\n",
      "\n",
      "\n",
      "        \n",
      "        **Nice Residence Hotel @Ekamai 14**\n",
      "\n",
      "        address: 8 ถนน สุขุมวิท Khlong Tan Nuea, Watthana\n",
      "\n",
      "        rating: 4.1\n",
      "\n",
      "\n",
      "        \n",
      "        **Maitria Hotel Rama 9 Bangkok**\n",
      "\n",
      "        address: 908 Khlong Samsen Rd, Bang Kapi, Huai Khwang\n",
      "\n",
      "        rating: 4.3\n",
      "\n",
      "\n",
      "        \n",
      "        **Ashley Hotel BKK**\n",
      "\n",
      "        address: 138 Sukhumvit 53 Alley, Khlong Tan Nuea, Watthana\n",
      "\n",
      "        rating: 4.7\n",
      "\n",
      "\n",
      "        \n",
      "        **The Residence on Thonglor by UHG**\n",
      "\n",
      "        address: 73 Thong Lo, Khlong Tan Nuea, Watthana\n",
      "\n",
      "        rating: 4.1\n",
      "\n",
      "\n",
      "        \n",
      "        **Chiva Bangkok Hotel**\n",
      "\n",
      "        address: 39/1 Soi Soonvijai 7 New Petchburi Road Soi 47, Bangkapi, Huay Kwang\n",
      "\n",
      "        rating: 3.9\n",
      "\n",
      "\n",
      "        \n",
      "        **Montana Hotel & Residence**\n",
      "\n",
      "        address: 1 Sun Wichai 14 Alley, Khwaeng Bang Kapi, Huai Khwang\n",
      "\n",
      "        rating: 4.3\n",
      "\n",
      "\n",
      "        \n",
      "        **Holiday Inn Express Bangkok Soi Soonvijai, an IHG Hotel**\n",
      "\n",
      "        address: 19 Soi Phetchaburi 47, Khwaeng Bang Kapi, Bangkapi\n",
      "\n",
      "        rating: 4.3\n",
      "\n",
      "\n",
      "        \n",
      "        **OB-OON Boutique Hotel & Café**\n",
      "\n",
      "        address: 12/13 ถนน สุขุมวิท ซอย 49/6 Khlong Tan Nuea, Watthana\n",
      "\n",
      "        rating: 4.3\n",
      "\n",
      "\n",
      "        \n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: data_collector\n",
      "\n",
      "Here is the detailed analysis of the hotel business in the Thonglor area:\n",
      "\n",
      "### Nearby Hotels in Thonglor\n",
      "1. **Metropole Bangkok**\n",
      "   - Address: 2802 Thong Lo, Bang Kapi, Huai Khwang\n",
      "   - Rating: 4.1\n",
      "\n",
      "2. **Mövenpick Ekkamai Bangkok**\n",
      "   - Address: 559 Sukhumvit 63, Khlong Tan Nuea, Watthana\n",
      "   - Rating: 4.4\n",
      "\n",
      "3. **Nice Residence Hotel @Ekamai 14**\n",
      "   - Address: 8 Thonglor 19, Khlong Tan Nuea, Watthana\n",
      "   - Rating: 4.1\n",
      "\n",
      "4. **Maitria Hotel Rama 9 Bangkok**\n",
      "   - Address: 908 Khlong Samsen Rd, Bang Kapi, Huai Khwang\n",
      "   - Rating: 4.3\n",
      "\n",
      "5. **Ashley Hotel BKK**\n",
      "   - Address: 138 Sukhumvit 53 Alley, Khlong Tan Nuea, Watthana\n",
      "   - Rating: 4.7\n",
      "\n",
      "6. **The Residence on Thonglor by UHG**\n",
      "   - Address: 73 Thong Lo, Khlong Tan Nuea, Watthana\n",
      "   - Rating: 4.1\n",
      "\n",
      "7. **Chiva Bangkok Hotel**\n",
      "   - Address: 39/1 Soi Soonvijai 7 New Petchburi Road Soi 47, Bangkapi, Huay Kwang\n",
      "   - Rating: 3.9\n",
      "\n",
      "8. **Montana Hotel & Residence**\n",
      "   - Address: 1 Sun Wichai 14 Alley, Khwaeng Bang Kapi, Huai Khwang\n",
      "   - Rating: 4.3\n",
      "\n",
      "9. **Holiday Inn Express Bangkok Soi Soonvijai, an IHG Hotel**\n",
      "   - Address: 19 Soi Phetchaburi 47, Khwaeng Bang Kapi, Bangkapi\n",
      "   - Rating: 4.3\n",
      "\n",
      "10. **OB-OON Boutique Hotel & Café**\n",
      "    - Address: 12/13 Thonglor 19, Khlong Tan Nuea, Watthana\n",
      "    - Rating: 4.3\n",
      "\n",
      "### Number of Rooms in Hotels\n",
      "- The search for the number of rooms in hotels in Thonglor yielded various results, but specific numbers were not consistently available. However, it is common for hotels in this area to have between 20 to 300 rooms, depending on the size and type of the hotel.\n",
      "\n",
      "### Population and Community Data\n",
      "- **Population**: The population in the Thonglor area is approximately 45,000 residents.\n",
      "- **Community Type**: Thonglor is known as an upscale urban community with a mix of residential and commercial properties.\n",
      "- **Household Expenditures**: The average household expenditure in this area is around 39,000 THB per month, reflecting the affluent nature of the community.\n",
      "\n",
      "### Summary\n",
      "Thonglor is a vibrant area with a variety of hotels catering to different market segments. The competitive landscape includes both high-end and boutique hotels, with ratings generally above 4.0. The community is affluent, with significant household expenditures, making it an attractive location for hotel businesses.\n",
      "\n",
      "If you need more specific data or further analysis, please let me know!\n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: reporter\n",
      "\n",
      "%SIjfE923hf\n"
     ]
    }
   ],
   "source": [
    "question = \"วิเคราะห์ธุรกิจโรงแรมแถวทองหล่อ\"\n",
    "\n",
    "graph = workflow.compile()\n",
    "\n",
    "events = graph.stream(\n",
    "    {\n",
    "        \"messages\": [\n",
    "            HumanMessage(\n",
    "                question\n",
    "            )\n",
    "        ],\n",
    "    },\n",
    "    # Maximum number of steps to take in the graph\n",
    "    {\"recursion_limit\": 20},\n",
    ")\n",
    "for s in events:\n",
    "    # print(s)\n",
    "    a = list(s.items())[0]\n",
    "    a[1]['messages'][0].pretty_print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def submitUserMessage(user_input: str) -> str:\n",
    "    graph = workflow.compile()\n",
    "\n",
    "    events = graph.stream(\n",
    "        {\n",
    "            \"messages\": [\n",
    "                HumanMessage(\n",
    "                    user_input\n",
    "                )\n",
    "            ],\n",
    "        },\n",
    "        # Maximum number of steps to take in the graph\n",
    "        {\"recursion_limit\": 20},\n",
    "    )\n",
    "    \n",
    "    events = [e for e in events]\n",
    "    \n",
    "    response = list(events[-1].values())[0][\"messages\"][0]\n",
    "    response = response.content\n",
    "    response = response.replace(\"%SIjfE923hf\", \"\")\n",
    "    \n",
    "    return response\n",
    "\n",
    "\n",
    "# question = \"วิเคราะห์ร้านอาหารแถวลุมพินี เซ็นเตอร์ ลาดพร้าว\"\n",
    "# submitUserMessage(question)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}