{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "124c8be0-1c20-4ea1-aeee-106d3fb7143f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_huggingface import HuggingFacePipeline, ChatHuggingFace\n",
    "from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForCausalLM, pipeline\n",
    "import torch\n",
    "from langchain_core.messages import (\n",
    "    HumanMessage,\n",
    "    SystemMessage,\n",
    "    BaseMessage\n",
    ")\n",
    "from typing import (\n",
    "    Any,\n",
    "    Callable,\n",
    "    Dict,\n",
    "    List,\n",
    "    Literal,\n",
    "    Optional,\n",
    "    Sequence,\n",
    "    Type,\n",
    "    Union,\n",
    "    cast,\n",
    ")\n",
    "\n",
    "class HuggingFaceAI(ChatHuggingFace):\n",
    "    \n",
    "    def _to_chat_prompt(\n",
    "        self,\n",
    "        messages: List[BaseMessage],\n",
    "    ) -> str:\n",
    "        \"\"\"Convert a list of messages into a prompt format expected by wrapped LLM.\"\"\"\n",
    "        if not messages:\n",
    "            raise ValueError(\"At least one HumanMessage must be provided!\")\n",
    "\n",
    "        if not isinstance(messages[-1], HumanMessage) and not isinstance(messages[-1], SystemMessage) :\n",
    "            raise ValueError(\"Last message must be a HumanMessage or SystemMessage!!!\")\n",
    "\n",
    "        messages_dicts = [self._to_chatml_format(m) for m in messages]\n",
    "\n",
    "        return self.tokenizer.apply_chat_template(\n",
    "            messages_dicts, tokenize=False, add_generation_prompt=True\n",
    "        )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "3ab4c82b-4268-4ffa-b814-967cf5e347d2",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bb1698c756e946beb49a2afcfde2e51e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer_config.json:   0%|          | 0.00/137k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2fe3d3847e4e4cfa8b124211c679597c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer.model:   0%|          | 0.00/587k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8dc27068bab14901a3595e921a34c4ef",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer.json:   0%|          | 0.00/1.96M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bc109fc9216449f19e610b30a9879b27",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "special_tokens_map.json:   0%|          | 0.00/414 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c3180e986f4d411d8511e361e4f3cd8f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "config.json:   0%|          | 0.00/601 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4c3c52d9f0c04b1eb3eb0c5ebd3e14c8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model.safetensors.index.json:   0%|          | 0.00/23.9k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "824ba11de3ba4cc7aa713779f3971025",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading shards:   0%|          | 0/3 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8c9b9325e7584ccf93733ab371493b1a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model-00001-of-00003.safetensors:   0%|          | 0.00/4.95G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2a5cfc651b7f4b6793305c507bb4f1ca",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model-00002-of-00003.safetensors:   0%|          | 0.00/5.00G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1aefc575e0c34cea950ca2e660024cc2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model-00003-of-00003.safetensors:   0%|          | 0.00/4.55G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "511d965c616345eaaa447a3f6ae3d8b8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a222b677f36e430383e9470d87a143c0",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "generation_config.json:   0%|          | 0.00/116 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "AIMessage(content='<s>[INST] Hugging Face is [/INST] Hugging Face is a technology company that specializes in natural language processing (NLP). They are best known for their transformers library, which is a state-of-the-art machine learning framework for NLP tasks. The transformers library includes pre-trained models for a wide range of NLP tasks such as language translation, text classification, and question answering. Hugging Face also provides a platform for training, sharing, and using NLP models, called the Hugging Face Model Hub', id='run-9b0b07cc-2121-4c78-8ebf-61df58694193-0')"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_huggingface import ChatHuggingFace, HuggingFacePipeline\n",
    "\n",
    "llm = HuggingFacePipeline.from_model_id(\n",
    "    model_id=\"mistralai/Mistral-7B-Instruct-v0.3\",\n",
    "    device_map=\"auto\",\n",
    "    task=\"text-generation\",\n",
    "    pipeline_kwargs={\n",
    "        \"max_new_tokens\": 100,\n",
    "        \"top_k\": 50,\n",
    "    },\n",
    ")\n",
    "\n",
    "llm_engine_hf = HuggingFaceAI(llm=llm)\n",
    "llm_engine_hf.invoke(\"Hugging Face is\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8cf48c8f-27c2-4c22-a219-965ad3621bc2",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.agents import AgentExecutor, create_openai_tools_agent\n",
    "from langchain_core.messages import BaseMessage, HumanMessage, SystemMessage, AIMessage\n",
    "from langchain_openai import ChatOpenAI\n",
    "\n",
    "\n",
    "def create_agent(llm: ChatHuggingFace, tools: list, system_prompt: str):\n",
    "    # Each worker node will be given a name and some tools.\n",
    "    prompt = ChatPromptTemplate.from_messages(\n",
    "        [\n",
    "            (\n",
    "                \"system\",\n",
    "                system_prompt,\n",
    "            ),\n",
    "            MessagesPlaceholder(variable_name=\"messages\"),\n",
    "            MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
    "        ]\n",
    "    )\n",
    "    agent = create_openai_tools_agent(llm, tools, prompt)\n",
    "    executor = AgentExecutor(agent=agent, tools=tools)\n",
    "    return executor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b2968526-9c48-45fe-b783-707873af7436",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from typing import Annotated, List, Tuple, Union\n",
    "\n",
    "from langchain_core.tools import tool\n",
    "from langchain_experimental.tools import PythonREPLTool\n",
    "\n",
    "\n",
    "# This executes code locally, which can be unsafe\n",
    "python_repl_tool = PythonREPLTool()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fd6d6e2f-d327-4a03-8693-9b6e20170826",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "chat_model = llm_engine_hf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "5cf6d454-81fb-43cd-a472-519df681ca32",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def agent_node(state, agent, name):\n",
    "    result = agent.invoke(state)\n",
    "    return {\"messages\": [HumanMessage(content=result[\"output\"], name=name)]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d35ca09b-1310-466d-924a-31f761a1f700",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_core.tools import tool\n",
    "\n",
    "@tool\n",
    "def multiply(a: int, b: int) -> int:\n",
    "    \"\"\"Multiply two numbers.\"\"\"\n",
    "    print(\"Multiply used\")\n",
    "    return a * b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "1579a0b5-bc37-45d4-aba4-244c3891f0f6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain_core.output_parsers import StrOutputParser\n",
    "from langchain_core.prompts import PromptTemplate, ChatPromptTemplate, MessagesPlaceholder\n",
    "from langchain_core.runnables import RunnableLambda    \n",
    "\n",
    "def stripPrompt(info):\n",
    "    print(info)\n",
    "    eot_token = \"[/INST] \"\n",
    "    i = info.content.rfind(eot_token)\n",
    "    if i == -1:\n",
    "        return info\n",
    "    \n",
    "    info.content = info.content[i + len(eot_token):]\n",
    "    \n",
    "    return info.content\n",
    "   \n",
    "members = [\"Multiplier\", \"Coder\"]\n",
    "# Our team supervisor is an LLM node. It just picks the next agent to process\n",
    "# and decides when the work is completed\n",
    "options = [\"FINISH\"] + members\n",
    "system_prompt = (\n",
    "    \"You are a supervisor tasked with managing a conversation between the\"\n",
    "    \" following workers:  {members}. Given the following user request,\"\n",
    "    \" respond with the worker to act next. Each worker will perform a\"\n",
    "    \" task and respond with their results and status. When finished,\"\n",
    "    \" respond with FINISH.\"\n",
    ")\n",
    "\n",
    "\n",
    "prompt = ChatPromptTemplate.from_messages(\n",
    "    [\n",
    "        (\"human\", system_prompt),\n",
    "        (\"assistant\", \"ok\"),\n",
    "        MessagesPlaceholder(variable_name=\"messages\"),\n",
    "        (\"assistant\", \"ok\"),\n",
    "        (\n",
    "            \"human\",\n",
    "            \"Given the conversation above, who should act next?\"\n",
    "            \" Or should we FINISH? Select one of: {options}\",\n",
    "        ),\n",
    "    ]\n",
    ").partial(options=str(options), members=\", \".join(members))\n",
    "\n",
    "chain = ( prompt | chat_model | RunnableLambda(stripPrompt))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "dbe4efe7-220a-42f9-badc-0e27329c8225",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import operator\n",
    "from typing import Annotated, Any, Dict, List, Optional, Sequence, TypedDict\n",
    "import functools\n",
    "\n",
    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
    "from langgraph.graph import StateGraph, END\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "multiply_agent = create_agent(chat_model, [multiply], \"You multiply numbers\")\n",
    "multiply_node = functools.partial(agent_node, agent=multiply_agent, name=\"Multiplier\")\n",
    "#research_node = functools.partial(agent_node, agent=research_agent, name=\"Researcher\")\n",
    "\n",
    "# NOTE: THIS PERFORMS ARBITRARY CODE EXECUTION. PROCEED WITH CAUTION\n",
    "code_agent = create_agent(\n",
    "    chat_model,\n",
    "    [python_repl_tool],\n",
    "    \"You may generate safe python code to analyze data and generate charts using matplotlib.\",\n",
    ")\n",
    "code_node = functools.partial(agent_node, agent=code_agent, name=\"Coder\")\n",
    "\n",
    "workflow = StateGraph(AgentState)\n",
    "workflow.add_node(\"Multiplier\", multiply_node)\n",
    "workflow.add_node(\"Coder\", code_node)\n",
    "workflow.add_node(\"supervisor\", chain)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "74714d27-60b1-4ae3-9993-d0c10b77e417",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "for member in members:\n",
    "    # We want our workers to ALWAYS \"report back\" to the supervisor when done\n",
    "    workflow.add_edge(member, \"supervisor\")\n",
    "# The supervisor populates the \"next\" field in the graph state\n",
    "# which routes to a node or finishes\n",
    "conditional_map = {k: k for k in members}\n",
    "conditional_map[\"FINISH\"] = END\n",
    "workflow.add_conditional_edges(\"supervisor\", lambda x: x[\"next\"], conditional_map)\n",
    "# Finally, add entrypoint\n",
    "workflow.set_entry_point(\"supervisor\")\n",
    "\n",
    "graph = workflow.compile()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "e6dc680d-15ec-484b-9a72-dc8af0f04234",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "content=\"<s>[INST] You are a supervisor tasked with managing a conversation between the following workers:  Multiplier, Coder. Given the following user request, respond with the worker to act next. Each worker will perform a task and respond with their results and status. When finished, respond with FINISH. [/INST]ok</s>[INST] What is 4 multiplied by 35 [/INST]ok</s>[INST] Given the conversation above, who should act next? Or should we FINISH? Select one of: ['FINISH', 'Multiplier', 'Coder'] [/INST] Multiplier (since they provided the result of the multiplication)\" id='run-8c0df905-9902-4ac2-8327-f4e4fb612cc2-0'\n"
     ]
    },
    {
     "ename": "InvalidUpdateError",
     "evalue": "Expected dict, got Multiplier (since they provided the result of the multiplication)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mInvalidUpdateError\u001b[0m                        Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[25], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m graph\u001b[38;5;241m.\u001b[39mstream(\n\u001b[1;32m      2\u001b[0m     {\n\u001b[1;32m      3\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m: [\n\u001b[1;32m      4\u001b[0m             HumanMessage(content\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWhat is 4 multiplied by 35\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      5\u001b[0m         ]\n\u001b[1;32m      6\u001b[0m     }\n\u001b[1;32m      7\u001b[0m ):\n\u001b[1;32m      8\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m__end__\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m s:\n\u001b[1;32m      9\u001b[0m         \u001b[38;5;28mprint\u001b[39m(s)\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/pregel/__init__.py:963\u001b[0m, in \u001b[0;36mPregel.stream\u001b[0;34m(self, input, config, stream_mode, output_keys, input_keys, interrupt_before, interrupt_after, debug)\u001b[0m\n\u001b[1;32m    960\u001b[0m         \u001b[38;5;28;01mdel\u001b[39;00m fut, task\n\u001b[1;32m    962\u001b[0m \u001b[38;5;66;03m# panic on failure or timeout\u001b[39;00m\n\u001b[0;32m--> 963\u001b[0m \u001b[43m_panic_or_proceed\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdone\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minflight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstep\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    964\u001b[0m \u001b[38;5;66;03m# don't keep futures around in memory longer than needed\u001b[39;00m\n\u001b[1;32m    965\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m done, inflight, futures\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/pregel/__init__.py:1489\u001b[0m, in \u001b[0;36m_panic_or_proceed\u001b[0;34m(done, inflight, step)\u001b[0m\n\u001b[1;32m   1487\u001b[0m             inflight\u001b[38;5;241m.\u001b[39mpop()\u001b[38;5;241m.\u001b[39mcancel()\n\u001b[1;32m   1488\u001b[0m         \u001b[38;5;66;03m# raise the exception\u001b[39;00m\n\u001b[0;32m-> 1489\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m exc\n\u001b[1;32m   1491\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inflight:\n\u001b[1;32m   1492\u001b[0m     \u001b[38;5;66;03m# if we got here means we timed out\u001b[39;00m\n\u001b[1;32m   1493\u001b[0m     \u001b[38;5;28;01mwhile\u001b[39;00m inflight:\n\u001b[1;32m   1494\u001b[0m         \u001b[38;5;66;03m# cancel all pending tasks\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/concurrent/futures/thread.py:52\u001b[0m, in \u001b[0;36m_WorkItem.run\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     49\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[1;32m     51\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 52\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     53\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m     54\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfuture\u001b[38;5;241m.\u001b[39mset_exception(exc)\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/pregel/retry.py:66\u001b[0m, in \u001b[0;36mrun_with_retry\u001b[0;34m(task, retry_policy)\u001b[0m\n\u001b[1;32m     64\u001b[0m task\u001b[38;5;241m.\u001b[39mwrites\u001b[38;5;241m.\u001b[39mclear()\n\u001b[1;32m     65\u001b[0m \u001b[38;5;66;03m# run the task\u001b[39;00m\n\u001b[0;32m---> 66\u001b[0m \u001b[43mtask\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mproc\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtask\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minput\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtask\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     67\u001b[0m \u001b[38;5;66;03m# if successful, end\u001b[39;00m\n\u001b[1;32m     68\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langchain_core/runnables/base.py:2495\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m   2493\u001b[0m             \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m step\u001b[38;5;241m.\u001b[39minvoke(\u001b[38;5;28minput\u001b[39m, config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m   2494\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 2495\u001b[0m             \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mstep\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2496\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m   2497\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/utils.py:86\u001b[0m, in \u001b[0;36mRunnableCallable.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m     84\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m {\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkwargs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs}\n\u001b[1;32m     85\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrace:\n\u001b[0;32m---> 86\u001b[0m     ret \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_with_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     87\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmerge_configs\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m     88\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     89\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m     90\u001b[0m     config \u001b[38;5;241m=\u001b[39m merge_configs(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig, config)\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langchain_core/runnables/base.py:1596\u001b[0m, in \u001b[0;36mRunnable._call_with_config\u001b[0;34m(self, func, input, config, run_type, **kwargs)\u001b[0m\n\u001b[1;32m   1592\u001b[0m     context \u001b[38;5;241m=\u001b[39m copy_context()\n\u001b[1;32m   1593\u001b[0m     context\u001b[38;5;241m.\u001b[39mrun(_set_config_context, child_config)\n\u001b[1;32m   1594\u001b[0m     output \u001b[38;5;241m=\u001b[39m cast(\n\u001b[1;32m   1595\u001b[0m         Output,\n\u001b[0;32m-> 1596\u001b[0m         \u001b[43mcontext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1597\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcall_func_with_variable_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[arg-type]\u001b[39;49;00m\n\u001b[1;32m   1598\u001b[0m \u001b[43m            \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[arg-type]\u001b[39;49;00m\n\u001b[1;32m   1599\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[arg-type]\u001b[39;49;00m\n\u001b[1;32m   1600\u001b[0m \u001b[43m            \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1601\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1602\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1603\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m   1604\u001b[0m     )\n\u001b[1;32m   1605\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m   1606\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langchain_core/runnables/config.py:380\u001b[0m, in \u001b[0;36mcall_func_with_variable_args\u001b[0;34m(func, input, config, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    378\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m run_manager \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m accepts_run_manager(func):\n\u001b[1;32m    379\u001b[0m     kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m run_manager\n\u001b[0;32m--> 380\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/pregel/write.py:97\u001b[0m, in \u001b[0;36mChannelWrite._write\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m     93\u001b[0m \u001b[38;5;66;03m# process entries into values\u001b[39;00m\n\u001b[1;32m     94\u001b[0m values \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m     95\u001b[0m     \u001b[38;5;28minput\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m write\u001b[38;5;241m.\u001b[39mvalue \u001b[38;5;129;01mis\u001b[39;00m PASSTHROUGH \u001b[38;5;28;01melse\u001b[39;00m write\u001b[38;5;241m.\u001b[39mvalue \u001b[38;5;28;01mfor\u001b[39;00m write \u001b[38;5;129;01min\u001b[39;00m entries\n\u001b[1;32m     96\u001b[0m ]\n\u001b[0;32m---> 97\u001b[0m values \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m     98\u001b[0m     val \u001b[38;5;28;01mif\u001b[39;00m write\u001b[38;5;241m.\u001b[39mmapper \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m write\u001b[38;5;241m.\u001b[39mmapper\u001b[38;5;241m.\u001b[39minvoke(val, config)\n\u001b[1;32m     99\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m val, write \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(values, entries)\n\u001b[1;32m    100\u001b[0m ]\n\u001b[1;32m    101\u001b[0m values \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m    102\u001b[0m     (write\u001b[38;5;241m.\u001b[39mchannel, val)\n\u001b[1;32m    103\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m val, write \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(values, entries)\n\u001b[1;32m    104\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m write\u001b[38;5;241m.\u001b[39mskip_none \u001b[38;5;129;01mor\u001b[39;00m val \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    105\u001b[0m ]\n\u001b[1;32m    106\u001b[0m \u001b[38;5;66;03m# write packets and values\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/pregel/write.py:98\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     93\u001b[0m \u001b[38;5;66;03m# process entries into values\u001b[39;00m\n\u001b[1;32m     94\u001b[0m values \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m     95\u001b[0m     \u001b[38;5;28minput\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m write\u001b[38;5;241m.\u001b[39mvalue \u001b[38;5;129;01mis\u001b[39;00m PASSTHROUGH \u001b[38;5;28;01melse\u001b[39;00m write\u001b[38;5;241m.\u001b[39mvalue \u001b[38;5;28;01mfor\u001b[39;00m write \u001b[38;5;129;01min\u001b[39;00m entries\n\u001b[1;32m     96\u001b[0m ]\n\u001b[1;32m     97\u001b[0m values \u001b[38;5;241m=\u001b[39m [\n\u001b[0;32m---> 98\u001b[0m     val \u001b[38;5;28;01mif\u001b[39;00m write\u001b[38;5;241m.\u001b[39mmapper \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[43mwrite\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmapper\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[43mval\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     99\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m val, write \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(values, entries)\n\u001b[1;32m    100\u001b[0m ]\n\u001b[1;32m    101\u001b[0m values \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m    102\u001b[0m     (write\u001b[38;5;241m.\u001b[39mchannel, val)\n\u001b[1;32m    103\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m val, write \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(values, entries)\n\u001b[1;32m    104\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m write\u001b[38;5;241m.\u001b[39mskip_none \u001b[38;5;129;01mor\u001b[39;00m val \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    105\u001b[0m ]\n\u001b[1;32m    106\u001b[0m \u001b[38;5;66;03m# write packets and values\u001b[39;00m\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/utils.py:95\u001b[0m, in \u001b[0;36mRunnableCallable.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m     93\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m accepts_config(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunc):\n\u001b[1;32m     94\u001b[0m         kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mconfig\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m config\n\u001b[0;32m---> 95\u001b[0m     ret \u001b[38;5;241m=\u001b[39m \u001b[43mcontext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     96\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(ret, Runnable) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrecurse:\n\u001b[1;32m     97\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m ret\u001b[38;5;241m.\u001b[39minvoke(\u001b[38;5;28minput\u001b[39m, config)\n",
      "File \u001b[0;32m~/miniconda/lib/python3.9/site-packages/langgraph/graph/state.py:300\u001b[0m, in \u001b[0;36mCompiledStateGraph.attach_node.<locals>._get_state_key\u001b[0;34m(input, config, key)\u001b[0m\n\u001b[1;32m    298\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m value \u001b[38;5;28;01mif\u001b[39;00m value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m SKIP_WRITE\n\u001b[1;32m    299\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 300\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m InvalidUpdateError(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExpected dict, got \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28minput\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
      "\u001b[0;31mInvalidUpdateError\u001b[0m: Expected dict, got Multiplier (since they provided the result of the multiplication)"
     ]
    }
   ],
   "source": [
    "for s in graph.stream(\n",
    "    {\n",
    "        \"messages\": [\n",
    "            HumanMessage(content=\"What is 4 multiplied by 35\")\n",
    "        ]\n",
    "    }\n",
    "):\n",
    "    if \"__end__\" not in s:\n",
    "        print(s)\n",
    "        print(\"----\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6ff7b4d7-189a-4c31-9366-c42e3a0a7d47",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2d14d9f3-bcc8-476a-b5f9-34987183636c",
   "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": "3.9.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}