chatbot_multiagent.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "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": 8,
   "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": 9,
   "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 langchain.agents.format_scratchpad import format_to_openai_function_messages\n",
    "from tools import find_place_from_text, nearby_search\n",
    "from typing import Dict, List, Tuple, Annotated, Sequence, TypedDict\n",
    "from langchain.agents import (\n",
    "    AgentExecutor,\n",
    ")\n",
    "from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser\n",
    "from langchain_community.tools.convert_to_openai import format_tool_to_openai_function\n",
    "from langchain_core.messages import (\n",
    "    AIMessage, \n",
    "    HumanMessage,\n",
    "    BaseMessage,\n",
    "    ToolMessage\n",
    ")\n",
    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
    "from langgraph.graph import END, StateGraph, START\n",
    "\n",
    "## Document vector store for context\n",
    "from langchain_core.runnables import RunnablePassthrough\n",
    "from langchain_chroma import Chroma\n",
    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
    "from langchain_community.document_loaders import CSVLoader\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "import glob\n",
    "from langchain.tools.retriever import create_retriever_tool\n",
    "\n",
    "def format_docs(docs):\n",
    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
    "\n",
    "\n",
    "## Document csv\n",
    "# Specify the pattern\n",
    "file_pattern = \"document/*.csv\"\n",
    "file_paths = tuple(glob.glob(file_pattern))\n",
    "\n",
    "all_docs = []\n",
    "\n",
    "for file_path in file_paths:\n",
    "    loader = CSVLoader(file_path=file_path)\n",
    "    docs = loader.load()\n",
    "    all_docs.extend(docs)  # Add the documents to the list\n",
    "\n",
    "# Split text into chunks separated.\n",
    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n",
    "splits = text_splitter.split_documents(all_docs)\n",
    "\n",
    "# Text Vectorization.\n",
    "vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())\n",
    "\n",
    "# Retrieve and generate using the relevant snippets of the blog.\n",
    "retriever = vectorstore.as_retriever()\n",
    "\n",
    "\n",
    "## tools and LLM\n",
    "retriever_tool = create_retriever_tool(\n",
    "    retriever,\n",
    "    \"search_population_community_household_expenditures_data\",\n",
    "    \"Use this tool to retrieve information about population, community and household expenditures. by searching distinct or province\"\n",
    ")\n",
    "\n",
    "# Bind the tools to the model\n",
    "tools = [retriever_tool, find_place_from_text, nearby_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 last_message.tool_calls:\n",
    "        # The previous agent is invoking a tool\n",
    "        return \"call_tool\"\n",
    "    if \"FINAL ANSWER\" in last_message.content:\n",
    "        # Any agent decided the work is done\n",
    "        return \"__end__\"\n",
    "    return \"continue\"\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": 10,
   "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": 11,
   "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_sJKgmWv9BPLFsMKtiwEVEGSF)\n",
      " Call ID: call_sJKgmWv9BPLFsMKtiwEVEGSF\n",
      "  Args:\n",
      "    location: Siam Paragon\n",
      "  nearby_search (call_CU1V3x2KZ2JhZwNjfFThBksy)\n",
      " Call ID: call_CU1V3x2KZ2JhZwNjfFThBksy\n",
      "  Args:\n",
      "    input_dict: {'keyword': 'restaurant', 'location_name': 'Siam Paragon', 'radius': 1000, 'place_type': 'restaurant'}\n",
      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
      "Name: find_place_from_text\n",
      "\n",
      "\n",
      "    address: 991/1 ถ. พระรามที่ 1 แขวงปทุมวัน เขตปทุมวัน กรุงเทพมหานคร 10330 ไทย\n",
      "\n",
      "    location: {'lat': 13.7457749, 'lng': 100.5344017}\n",
      "\n",
      "    location_name: สยามพารากอน\n",
      "\n",
      "    \n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: analyst\n",
      "\n",
      "I have gathered information regarding restaurants near Siam Paragon. Here are some notable options:\n",
      "\n",
      "1. **Shree Bhavan Pure South Indian Vegetarian Restaurant**\n",
      "   - Address: 120 Pratunam Market, 45 Ratchaprarop Rd, Thanon Phaya Thai, Ratchathewi\n",
      "   - Rating: 4.9\n",
      "\n",
      "2. **I Food Bar & Restaurant**\n",
      "   - Address: No.49/26, Soi Petchburi 15, Phetchaburi Rd, Subdistrict, Ratchathewi\n",
      "   - Rating: 4.8\n",
      "\n",
      "3. **Tan Kun (Central World)**\n",
      "   - Address: 1st fl, Central World, Pathum Wan\n",
      "   - Rating: 4.7\n",
      "\n",
      "4. **Jasmine Siam Kitchen**\n",
      "   - Address: 497, 14-15 Phetchaburi Rd, Thung Phaya Thai, Ratchathewi\n",
      "   - Rating: 4.7\n",
      "\n",
      "5. **Metro Square SiamParagon**\n",
      "   - Address: 991 Rama I Rd, Khwaeng Pathum Wan, Pathum Wan\n",
      "   - Rating: 4.7\n",
      "\n",
      "6. **KAI Japanese Restaurant Gaysorn Amarin**\n",
      "   - Address: 4th Fl, Gaysorn Amarin, 496, 502 Phloen Chit Rd, Lumphini, Pathum Wan\n",
      "   - Rating: 5.0\n",
      "\n",
      "7. **Madras Darbar Indian Restaurant**\n",
      "   - Address: 120/35-36 Ratchaprarop Rd, Thanon Phaya Thai, Ratchathewi\n",
      "   - Rating: 4.7\n",
      "\n",
      "8. **Bangkok'78**\n",
      "   - Address: 68 Soi Langsuan, Lumphini, Pathum Wan\n",
      "   - Rating: 4.3\n",
      "\n",
      "These restaurants vary in cuisine and offer a range of dining experiences. If you need more specific information or further analysis, feel free to ask!\n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: data_collector\n",
      "Tool Calls:\n",
      "  search_population_community_household_expenditures_data (call_w9bXzqFrVmZDN6wRL10GjFPm)\n",
      " Call ID: call_w9bXzqFrVmZDN6wRL10GjFPm\n",
      "  Args:\n",
      "    query: Pathum Wan\n",
      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
      "Name: search_population_community_household_expenditures_data\n",
      "\n",
      "จำนวนชุมชนประเภทต่าง ๆ ในกรุงเทพมหานคร พ.ศ. 2564: พญาไท\n",
      ": 22\n",
      "\n",
      "จำนวนชุมชนประเภทต่าง ๆ ในกรุงเทพมหานคร พ.ศ. 2564: พญาไท\n",
      ": 22\n",
      "\n",
      "จำนวนชุมชนประเภทต่าง ๆ ในกรุงเทพมหานคร พ.ศ. 2564: ยานนาวา\n",
      ": 17\n",
      "\n",
      "จำนวนชุมชนประเภทต่าง ๆ ในกรุงเทพมหานคร พ.ศ. 2564: ยานนาวา\n",
      ": 17\n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: data_collector\n",
      "\n",
      "Here is the additional data regarding the community and population around Siam Paragon (Pathum Wan area):\n",
      "\n",
      "- **Community Type**: Pathum Wan has a diverse community with various types of neighborhoods.\n",
      "- **Number of Communities**: There are approximately 22 communities in the Pathum Wan area.\n",
      "- **Population**: The population in the Pathum Wan area is diverse, with a mix of locals and tourists due to the presence of shopping centers and attractions like Siam Paragon.\n",
      "\n",
      "If you need more specific data on household expenditures or any other details, please let me know!\n",
      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
      "Name: reporter\n",
      "\n",
      "FINAL ANSWER\n",
      "\n",
      "### 1. Competitors List\n",
      "Here are some notable restaurants near Siam Paragon:\n",
      "- Shree Bhavan Pure South Indian Vegetarian Restaurant (Rating: 4.9)\n",
      "- I Food Bar & Restaurant (Rating: 4.8)\n",
      "- Tan Kun (Central World) (Rating: 4.7)\n",
      "- Jasmine Siam Kitchen (Rating: 4.7)\n",
      "- Metro Square SiamParagon (Rating: 4.7)\n",
      "- KAI Japanese Restaurant Gaysorn Amarin (Rating: 5.0)\n",
      "- Madras Darbar Indian Restaurant (Rating: 4.7)\n",
      "- Bangkok'78 (Rating: 4.3)\n",
      "\n",
      "### 2. Numerical Data\n",
      "- **Number of Competitors**: 8 notable restaurants listed.\n",
      "- **Range of Competitors Ratings**: 3.3 to 5.0\n",
      "- **Community Type**: Diverse communities in Pathum Wan.\n",
      "- **Number of Communities**: Approximately 22 communities in the Pathum Wan area.\n",
      "- **Population**: A mix of locals and tourists.\n",
      "\n",
      "### 3. Descriptive Analytical Summary\n",
      "The area surrounding Siam Paragon is vibrant and competitive for the restaurant business, with a variety of dining options that cater to both locals and tourists. The presence of high-rated restaurants, such as KAI Japanese Restaurant and Shree Bhavan, indicates a strong demand for quality dining experiences. The diverse community and the high foot traffic from shopping and tourism create a favorable environment for new restaurant ventures. The range of ratings suggests that while there are many successful establishments, there is also room for improvement and differentiation in the market. \n",
      "\n",
      "Overall, opening a restaurant near Siam Paragon could be a lucrative opportunity, provided that the concept aligns with the preferences of the local and tourist demographics.\n"
     ]
    }
   ],
   "source": [
    "question = \"วิเคราะห์การเปิดร้านอาหารใกล้สยามพารากอน\"\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": 12,
   "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(\"FINAL ANSWER\", \"\")\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
}