{ "cells": [ { "cell_type": "markdown", "id": "0c8b472b-f3fb-46c2-841f-930a4692697b", "metadata": {}, "source": [ "# Implementing LLMCompiler using LangGraph\n", "By Kim, et. al [🔗](https://arxiv.org/abs/2312.04511)\n", "\n", "LLMCompiler is an agent architecture intented on speeding up the latency of agentic tasks via fast, parallel tool execution. It has 3 main components:\n", "\n", "1. Planner: generate a DAG of tasks.\n", "2. Task Fetching Unit: schedules and executes the tasks\n", "3. Joiner: Responds to the user or triggers a second plan\n", "\n", "\n", "This notebook walks through each component and shows how to wire them together using LangGraph." ] }, { "cell_type": "markdown", "id": "1abdedbd-d81b-4ee9-b46f-f29439ed1350", "metadata": {}, "source": [ "# Part 1: Planner\n", "\n", "\n", "Largely adapted from [the original source code](https://github.com/SqueezeAILab/LLMCompiler/blob/main/src/llm_compiler/output_parser.py)." ] }, { "cell_type": "markdown", "id": "278f76b0-a2e1-42dc-bd3e-6f624984e3dd", "metadata": {}, "source": [ "#### Output Parser\n", "\n", "Parses task lists in the following form:\n", "\n", "```plaintext\n", "1. tool_1(\"arg1\", 3.5, ...)\n", "Thought: I then want to find out Y by using tool_2\n", "2. tool_2(\"\", ${1})'\n", "3. join()\"\n", "```\n", "\n", "The \"Thought\" lines are optional. The `${#}` placeholders are variables. These are used to route tool (task) outputs to other tools." ] }, { "cell_type": "code", "execution_count": 1, "id": "cc71b6c4-d701-4217-9701-95ac0857e4e1", "metadata": {}, "outputs": [], "source": [ "import json\n", "import re\n", "from typing import Any, Dict, List, Optional, Sequence, Union\n", "\n", "from langchain.agents.agent import AgentOutputParser\n", "from langchain.schema import OutputParserException\n", "from langchain_core.tools import BaseTool\n", "\n", "THOUGHT_PATTERN = r\"Thought: ([^\\n]*)\"\n", "# $1 or ${1} -> 1\n", "ID_PATTERN = r\"\\$\\{?(\\d+)\\}?\"\n", "END_OF_PLAN = \"\"\n", "\n", "\n", "class ActionParserFSM:\n", " def __init__(self):\n", " self.reset()\n", "\n", " def reset(self):\n", " self.state = \"START\"\n", " self.task_index = \"\"\n", " self.action = \"\"\n", " self.comment = \"\"\n", " self.bracket_count = 0\n", " self.actions = []\n", "\n", " def parse(self, text: str):\n", " for char in text:\n", " action = self.process_char(char)\n", " if action:\n", " yield action\n", " action = self.save_action()\n", " if action:\n", " yield action\n", "\n", " def process_char(self, char: str) -> Optional[dict]:\n", " action = None\n", " if self.state == \"START\":\n", " if char.isdigit():\n", " self.state = \"NUMBER\"\n", " self.task_index += char\n", " elif char == \"\\n\":\n", " self.reset()\n", " elif self.state == \"NUMBER\":\n", " if char == \".\":\n", " self.state = \"ACTION\"\n", " elif char.isdigit():\n", " self.task_index += char\n", " else:\n", " self.reset()\n", " elif self.state == \"ACTION\":\n", " if char == \"{\":\n", " self.bracket_count += 1\n", " elif char == \"}\":\n", " self.bracket_count -= 1\n", " if self.bracket_count == 0:\n", " self.state = \"COMMENT\"\n", " self.action += char\n", " elif self.state == \"COMMENT\":\n", " if char == \"\\n\":\n", " action = self.save_action()\n", " self.reset()\n", " else:\n", " self.comment += char\n", " return action\n", "\n", " def save_action(self):\n", " if self.task_index and self.action:\n", " parsed_action = json.loads(self.action.strip())\n", " tool_name, args = next(iter(parsed_action.items()))\n", " return {\n", " \"task_index\": int(self.task_index),\n", " \"tool_name\": tool_name,\n", " \"args\": args,\n", " }\n", "\n", "\n", "class LLMCompilerPlanParser(AgentOutputParser, extra=\"allow\"):\n", " \"\"\"Planning output parser.\"\"\"\n", "\n", " def __init__(self, tools: Sequence[BaseTool], **kwargs):\n", " super().__init__(**kwargs)\n", " self.tools = tools\n", "\n", " def parse(self, text: str) -> list[str]:\n", " parser = ActionParserFSM()\n", " graph_dict = {}\n", " for task in parser.parse(text):\n", " idx = int(task[\"task_index\"])\n", "\n", " task = instantiate_task(\n", " tools=self.tools,\n", " idx=idx,\n", " tool_name=task[\"tool_name\"],\n", " args=task[\"args\"],\n", " )\n", "\n", " graph_dict[idx] = task\n", " if task[\"tool\"] == \"join\":\n", " break\n", "\n", " return graph_dict\n", "\n", "\n", "### Helper functions\n", "\n", "\n", "def default_dependency_rule(idx, args: str):\n", " matches = re.findall(ID_PATTERN, args)\n", " numbers = [int(match) for match in matches]\n", " return idx in numbers\n", "\n", "\n", "def _get_dependencies_from_graph(\n", " idx: int, tool_name: str, args: Sequence[Any]\n", ") -> dict[str, list[str]]:\n", " \"\"\"Get dependencies from a graph.\"\"\"\n", " if tool_name == \"join\":\n", " return list(range(1, idx))\n", " return [i for i in range(1, idx) if default_dependency_rule(i, str(args))]\n", "\n", "\n", "def instantiate_task(\n", " tools: Sequence[BaseTool],\n", " idx: int,\n", " tool_name: str,\n", " args: Union[dict, str, bool, None],\n", ") -> dict:\n", " dependencies = _get_dependencies_from_graph(idx, tool_name, args)\n", " if tool_name == \"join\":\n", " tool = \"join\"\n", " else:\n", " try:\n", " tool = tools[[tool.name for tool in tools].index(tool_name)]\n", " except ValueError as e:\n", " raise OutputParserException(f\"Tool {tool_name} not found.\")\n", " return dict(\n", " tool=tool,\n", " args=args,\n", " dependencies=dependencies,\n", " )" ] }, { "cell_type": "markdown", "id": "228a2f75-68b1-4dbf-95dc-4bfc738c3b3b", "metadata": {}, "source": [ "#### Planner Code\n", "\n", "This takes the input and outputs a plan." ] }, { "cell_type": "code", "execution_count": 141, "id": "58af9746-1011-41e9-a77a-be9cef202aea", "metadata": {}, "outputs": [], "source": [ "from langchain.chat_models.base import BaseChatModel\n", "from langchain_core.prompts import ChatPromptTemplate\n", "from langchain_core.runnables import RunnableBranch\n", "from langchain_core.tools import BaseTool\n", "\n", "END_OF_PLAN = \"\"\n", "\n", "JOINER_FINISH = \"Finish\"\n", "JOINER_REPLAN = \"Replan\"\n", "\n", "\n", "JOIN_DESCRIPTION = (\n", " \"join():\\n\"\n", " \" - Collects and combines results from prior actions.\\n\"\n", " \" - A LLM agent is called upon invoking join to either finalize the user query or wait until the plans are executed.\\n\"\n", " \" - join should always be the last action in the plan, and will be called in two scenarios:\\n\"\n", " \" (a) if the answer can be determined by gathering the outputs from tasks to generate the final response.\\n\"\n", " \" (b) if the answer cannot be determined in the planning phase before you execute the plans. \"\n", ")\n", "\n", "planner_prompt_tmpl_str = (\n", " \"Given a user query, create a plan to solve it with the utmost parallelizability. \"\n", " \"Each plan should comprise an action from the following {num_tools} types:\\n\"\n", " \"{tool_descriptions}\"\n", " f\"\\n{{num_toolsp1}}. {JOIN_DESCRIPTION}\"\n", " \"Guidelines:\\n\"\n", " \" - Each action described above contains input/output types and description.\\n\"\n", " \" - You must strictly adhere to the input and output types for each action.\\n\"\n", " \" - The action descriptions contain the guidelines. You MUST strictly follow those guidelines when you use the actions.\\n\"\n", " \" - Each action in the plan should strictly be one of the above types.\\n\"\n", " \" - Provide actions ONLY in json form, with the single key being the action name and the value being its arguments. Do not write python code. \\n\"\n", " \" - Each action line must start with a unique ID, which is strictly increasing.\\n\"\n", " \" - Inputs for actions can either be constants or outputs from preceding actions. \"\n", " \"In the latter case, use the format $id to denote the ID of the previous action whose output will be the input.\\n\"\n", " f\" - Always call join as the last action in the plan. Say '{END_OF_PLAN}' after you call join\\n\"\n", " \" - Ensure the plan maximizes parallelizability.\\n\"\n", " \" - Only use the provided action types. If a query cannot be addressed using these, invoke the join action for the next steps.\\n\"\n", " \" - Never introduce new actions other than the ones provided.\\n\\n\"\n", " \"{replan}\"\n", " \"{examples}\"\n", ")\n", "\n", "\n", "def _generate_planner_prompt(\n", " tools: Sequence[BaseTool],\n", " example_prompt=str,\n", "):\n", " tool_descriptions = \"\\n\".join(\n", " f\"{i+1}. {tool.name}: {tool.description}\\n\\tInput schema: {tool.args}\"\n", " for i, tool in enumerate(tools)\n", " )\n", " planner_prompt_template = ChatPromptTemplate.from_messages(\n", " [(\"system\", planner_prompt_tmpl_str), (\"user\", \"Question: {input}{context}\")]\n", " ).partial(\n", " tool_descriptions=tool_descriptions,\n", " examples=\"Here are some examples:\\n\\n\" + example_prompt\n", " if example_prompt\n", " else \"\",\n", " num_tools=len(tools),\n", " num_toolsp1=len(tools) + 1,\n", " )\n", "\n", " return planner_prompt_template\n", "\n", "\n", "def create_planner(\n", " llm: BaseChatModel,\n", " example_prompt: str,\n", " tools: Sequence[BaseTool],\n", " stop: Optional[list[str]] = None,\n", "):\n", " og_planner_prompt = _generate_planner_prompt(tools, example_prompt).partial(\n", " replan=\"\",\n", " context=\"\",\n", " )\n", " replanner_prompt = _generate_planner_prompt(tools, example_prompt).partial(\n", " replan=' - You are given \"Previous Plan\" which is the plan that the previous agent created along with the execution results '\n", " \"(given as Observation) of each plan and a general thought (given as Thought) about the executed results.\"\n", " 'You MUST use these information to create the next plan under \"Current Plan\".\\n'\n", " ' - When starting the Current Plan, you should start with \"Thought\" that outlines the strategy for the next plan.\\n'\n", " \" - In the Current Plan, you should NEVER repeat the actions that are already executed in the Previous Plan.\\n\"\n", " \" - You must continue the task index from the end of the previous one. Do not repeat task indices.\"\n", " )\n", " bound_llm = llm.bind(stop=stop)\n", " return (\n", " RunnableBranch(\n", " ((lambda x: x.get(\"context\") is not None), replanner_prompt),\n", " og_planner_prompt,\n", " )\n", " | bound_llm\n", " | LLMCompilerPlanParser(tools=tools)\n", " )" ] }, { "cell_type": "markdown", "id": "7feb5c82-b1a9-40ae-863a-0362fe3ce5ea", "metadata": {}, "source": [ "#### Example usage\n", "\n", "Here's an example usage of the planner module" ] }, { "cell_type": "code", "execution_count": 131, "id": "3fe074ea-7314-47a7-9a9f-a8e6191ea1f3", "metadata": {}, "outputs": [], "source": [ "from langchain.tools import tool\n", "from langchain_openai import ChatOpenAI\n", "\n", "\n", "@tool\n", "def get_user_id(first_name: str, last_name: Optional[str] = None):\n", " \"\"\"Query the user IDs of everyone with the provided name.\"\"\"\n", " return 4\n", "\n", "\n", "@tool\n", "def get_scores(class_name: str, user_id: int):\n", " \"\"\"Query the class registry for grades of the provided user ID.\"\"\"\n", " return \"A+\"\n", "\n", "\n", "examples = (\n", " \"Question: What's the user ID for Johnny Drop Tables?\\n\"\n", " '1. {\"get_user_id\": {\"first_name\": \"Johnny\", \"last_name\":\"Drop Tables\"}}\\n'\n", " f'2. {{\"join\": null}}{END_OF_PLAN}\\n'\n", " \"###\\n\"\n", " \"\\n\"\n", " \"Question: What was Eric Zhang's score in Calc?\\n\"\n", " '1. {\"get_user_id\": {\"first_name\": \"Eric\", \"last_name\":\"Zhang\"}}\\n'\n", " '2. {\"get_scores\": {\"class_name\": \"calc\", \"user_id\": \"$1\"}}\\n'\n", " f'3. {{\"join\": null}}{END_OF_PLAN}\\n'\n", " \"###\\n\"\n", " \"\\n\"\n", ")\n", "\n", "planner = create_planner(\n", " ChatOpenAI(model=\"gpt-3.5-turbo\"),\n", " example_prompt=examples,\n", " tools=[get_user_id, get_scores],\n", ")" ] }, { "cell_type": "code", "execution_count": 132, "id": "55fb0f99-4e59-4e5a-b687-a90bb4d06d39", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{1: {'tool': StructuredTool(name='get_user_id', description='get_user_id(first_name: str, last_name: Optional[str] = None) - Query the user IDs of everyone with the provided name.', args_schema=, func=),\n", " 'args': {'first_name': 'Sam', 'last_name': 'Van Damm'},\n", " 'dependencies': []},\n", " 2: {'tool': StructuredTool(name='get_user_id', description='get_user_id(first_name: str, last_name: Optional[str] = None) - Query the user IDs of everyone with the provided name.', args_schema=, func=),\n", " 'args': {'first_name': 'Will', 'last_name': 'Van Damm'},\n", " 'dependencies': []},\n", " 3: {'tool': StructuredTool(name='get_scores', description='get_scores(class_name: str, user_id: int) - Query the class registry for grades of the provided user ID.', args_schema=, func=),\n", " 'args': {'class_name': 'Calc BC', 'user_id': '$1'},\n", " 'dependencies': [1]},\n", " 4: {'tool': StructuredTool(name='get_scores', description='get_scores(class_name: str, user_id: int) - Query the class registry for grades of the provided user ID.', args_schema=, func=),\n", " 'args': {'class_name': 'Calc BC', 'user_id': '$2'},\n", " 'dependencies': [2]},\n", " 5: {'tool': 'join', 'args': None, 'dependencies': [1, 2, 3, 4]}}" ] }, "execution_count": 132, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tasks = planner.invoke(\n", " {\"input\": \"What are the Calc BC grades for Sam and Will Van Damm?\"}\n", ")\n", "tasks" ] }, { "cell_type": "markdown", "id": "5d0e795f-61ff-4553-9823-23e7624ca180", "metadata": {}, "source": [ "## 2. Task Fetching Unit\n", "\n", "This component schedules the tasks. In the paper, it's kept separate from the \"executor\", but here we create a single DAG to be executed by LangGraph.\n", "\n", "Basic idea is that, given a list of dicts of the form:\n", "\n", "```typescript\n", "{\n", " tool: BaseTool,\n", " dependencies: number[],\n", "}\n", "```\n", "\n", "1. Create a topological sort of the tasks\n", "2. Execute them on the previous step's output, ensuring to perform variable substitution where appropriate" ] }, { "cell_type": "code", "execution_count": 184, "id": "c70a0e28-43db-4ea2-af48-8a2f310dce83", "metadata": {}, "outputs": [], "source": [ "import functools\n", "\n", "from langchain_core.runnables import (\n", " RunnableLambda,\n", " RunnableParallel,\n", " RunnablePassthrough,\n", ")\n", "\n", "\n", "def _sort_tasks(data):\n", " if not data:\n", " return []\n", " sorted_tasks = []\n", " # Remove tasks already completed\n", " min_idx = min([int(k) for k in data])\n", " data = {\n", " int(k): {\n", " **v,\n", " \"dependencies\": [dep for dep in v[\"dependencies\"] if dep >= min_idx],\n", " }\n", " for k, v in data.items()\n", " }\n", " while data:\n", " no_deps = {k: v for k, v in data.items() if not v[\"dependencies\"]}\n", " if not no_deps:\n", " raise ValueError(\"We seem to have run into a circular dependency.\")\n", "\n", " sorted_tasks.append(no_deps)\n", " data = {\n", " k: {\n", " **v,\n", " \"dependencies\": [d for d in v[\"dependencies\"] if d not in no_deps],\n", " }\n", " for k, v in data.items()\n", " if k not in no_deps\n", " }\n", " return sorted_tasks\n", "\n", "\n", "def _resolve_arg(x: dict, arg: Union[str, Any]):\n", " if isinstance(arg, str) and arg.startswith(\"$\"):\n", " try:\n", " return x[f\"task_{arg[1:]}\"]\n", " except:\n", " if arg.endswith(\".output\"):\n", " return x[f\"task_{arg[1:-7]}\"]\n", " raise\n", "\n", " else:\n", " return arg\n", "\n", "\n", "def _execute_task(x, task):\n", " tool_to_use = task[\"tool\"]\n", " args = task[\"args\"]\n", " if isinstance(args, str):\n", " resolved_args = _resolve_arg(x, args)\n", " elif isinstance(args, dict):\n", " resolved_args = {key: _resolve_arg(x, val) for key, val in args.items()}\n", " else:\n", " # This will likely fail\n", " resolved_args = args\n", " try:\n", " return tool_to_use.invoke(resolved_args)\n", " except Exception as e:\n", " return (\n", " f\"ERROR(Failed to call tool {tool_to_use} with args {tool_to_use}.\"\n", " + f\" Args resolved to {resolved_args}. Error: {repr(e)})\"\n", " )\n", "\n", "\n", "def construct_dag(tasks):\n", " sorted_tasks = _sort_tasks(tasks)\n", " chain = None\n", " for idx, task_group in enumerate(sorted_tasks):\n", " if len(task_group) == 1 and next(iter(task_group.values()))[\"tool\"] == \"join\":\n", " # TODO: actually join the values\n", " step = lambda x: {\"join\": x}\n", " else:\n", " # Cascade all results forward\n", " constructor = (\n", " RunnableParallel if chain is None else RunnablePassthrough.assign\n", " )\n", " task_dict = {}\n", " for idx, task in task_group.items():\n", " task_dict[f\"task_{idx}\"] = RunnableLambda(\n", " functools.partial(_execute_task, task=task)\n", " ).with_config(run_name=f\"task_{idx}\")\n", "\n", " step = constructor(**task_dict).with_config(run_name=f\"TaskGroup{idx}\")\n", " if chain is None:\n", " chain = step\n", " else:\n", " chain |= step\n", "\n", " if chain is not None:\n", " return chain | RunnablePassthrough.assign(tasks=lambda _: tasks)\n", " return chain" ] }, { "cell_type": "code", "execution_count": 185, "id": "87f11cea-3a8d-479c-8a9e-81223dbbc1f5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " +------------------------------+ \n", " | ParallelInput | \n", " +------------------------------+ \n", " *** *** \n", " ** ** \n", " ** ** \n", " +-------------+ +-------------+ \n", " | Lambda(...) | | Lambda(...) | \n", " +-------------+ +-------------+ \n", " *** *** \n", " ** ** \n", " ** ** \n", " +-------------------------------+ \n", " | ParallelOutput | \n", " +-------------------------------+ \n", " * \n", " * \n", " * \n", " +------------------------------+ \n", " | ParallelInput | \n", " +------------------------------+ \n", " ***** * ***** \n", " ***** * ***** \n", " *** * *** \n", "+-------------+ +-------------+ +-------------+ \n", "| Lambda(...) | | Lambda(...) | | Passthrough | \n", "+-------------+***** +-------------+ *****+-------------+ \n", " ***** * ***** \n", " ***** * ***** \n", " *** * *** \n", " +-------------------------------+ \n", " | ParallelOutput | \n", " +-------------------------------+ \n", " * \n", " * \n", " * \n", " +-------------------------------+ \n", " | Lambda(lambda x: {'join': x}) | \n", " +-------------------------------+ \n", " * \n", " * \n", " * \n", " +----------------------+ \n", " | ParallelInput | \n", " +----------------------+ \n", " *** *** \n", " *** *** \n", " ** ** \n", " +-------------------------+ +-------------+ \n", " | Lambda(lambda _: tasks) | | Passthrough | \n", " +-------------------------+ +-------------+ \n", " *** *** \n", " *** *** \n", " ** ** \n", " +-----------------------+ \n", " | ParallelOutput | \n", " +-----------------------+ \n" ] } ], "source": [ "graph = construct_dag(tasks)\n", "graph.get_graph().print_ascii()" ] }, { "cell_type": "markdown", "id": "9efa15ae-817a-48c6-86ed-16bc112fedc5", "metadata": {}, "source": [ "#### Example Plan\n", "\n", "We still haven't introduced any cycles in our computation graph, so this is all easily expressed in LCEL." ] }, { "cell_type": "code", "execution_count": 135, "id": "133d124a-0d41-4c6d-a86a-34fa4cb1430f", "metadata": {}, "outputs": [], "source": [ "chain = planner | construct_dag" ] }, { "cell_type": "code", "execution_count": 136, "id": "55142257-2674-4a47-988e-0d2810917329", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'task_1': 4, 'task_2': 4, 'task_3': 'A+', 'task_4': 'A+'}" ] }, "execution_count": 136, "metadata": {}, "output_type": "execute_result" } ], "source": [ "example_question = \"Did Aliya get a better score than Roger in Geology?\"\n", "task_results = chain.invoke({\"input\": example_question})\n", "task_results[\"join\"]" ] }, { "cell_type": "markdown", "id": "563d5311-55f0-4ca1-afbd-01fd970cf3e3", "metadata": {}, "source": [ "## Agent Logic\n", "\n", "So now we have the planning and initial execution done. We need a component to process these outputs and either:\n", "1. Respond with the correct answer.\n", "2. Loop with a new plan.\n", "\n", "The paper calls this the \"joiner\"." ] }, { "cell_type": "code", "execution_count": 216, "id": "2978991e-45a4-44e6-9deb-f941f44fe93a", "metadata": {}, "outputs": [], "source": [ "from langchain_core.output_parsers import StrOutputParser\n", "from typing_extensions import TypedDict\n", "\n", "\n", "def format_task(task, idx):\n", " tool = task[\"tool\"]\n", " tool_name = tool if isinstance(tool, str) else tool.name # Handle join()\n", " return f\"{idx}. {{{tool_name}: {task['args']}}}\"\n", "\n", "\n", "def format_tasks(executor_output: dict):\n", " tasks = executor_output[\"tasks\"]\n", " prior_observations = executor_output.get(\"observations\")\n", " formatted_plan = \"\\n\".join(format_task(task, idx) for idx, task in tasks.items())\n", " observations = \"\\n\".join(f\"{k}: {v}\" for k, v in executor_output[\"join\"].items())\n", " result = f\"Original Plan:\\n{formatted_plan}\\nExecuted plan results:\\n{observations}\"\n", " if prior_observations:\n", " result += f\"\\nPrevious Results:\\n{prior_observations}\"\n", " return result\n", "\n", "\n", "def _parse_joiner_output(raw_answer: str) -> str:\n", " thought, answer, is_replan = \"\", \"\", False # default values\n", " raw_answers = raw_answer.split(\"\\n\")\n", " for ans in raw_answers:\n", " if ans.startswith(\"Action:\"):\n", " answer = ans[ans.find(\"(\") + 1 : ans.find(\")\")]\n", " is_replan = JOINER_REPLAN in ans\n", " elif ans.startswith(\"Thought:\"):\n", " thought = ans.split(\"Thought:\")[1].strip()\n", " if is_replan:\n", " return {\"thought\": thought, \"context\": answer}\n", " else:\n", " return {\"thought\": thought, \"answer\": answer}" ] }, { "cell_type": "code", "execution_count": 217, "id": "b2feea5a-e0e4-4cff-8cb5-fdbfec95ba57", "metadata": {}, "outputs": [], "source": [ "def create_joiner(prompt, llm):\n", " return (\n", " (\n", " lambda x: {\n", " **x[\"plan\"],\n", " \"input\": x[\"input\"],\n", " \"context\": x.get(\"context\"),\n", " \"observations\": x.get(\"observations\"),\n", " }\n", " )\n", " | RunnablePassthrough.assign(scratchpad=format_tasks)\n", " | ChatPromptTemplate.from_messages([(\"system\", prompt), (\"user\", \"{input}\")])\n", " | llm\n", " | StrOutputParser()\n", " | _parse_joiner_output\n", " )" ] }, { "cell_type": "code", "execution_count": 218, "id": "942dab42-ad42-4ba2-90d5-49edbe4fae68", "metadata": {}, "outputs": [], "source": [ "system_prompt = (\n", " \"Solve a question answering task. Here are some guidelines:\\n\"\n", " \" - In the Assistant Scratchpad, you will be given results of a plan you have executed to answer the user's question.\\n\"\n", " \" - Thought needs to reason about the question based on the Observations in 1-2 sentences.\\n\"\n", " \" - Ignore irrelevant action results.\\n\"\n", " \" - If the required information is present, give a concise but complete and helpful answer to the user's question.\\n\"\n", " \" - If you are unable to give a satisfactory finishing answer, replan to get the required information.\"\n", " \" Respond in the following format:\\n\\n\"\n", " \"Thought: \\n\"\n", " \"Action: \\n\"\n", " \"Available actions:\\n\"\n", " f\" (1) {JOINER_FINISH}(the final answer to return to the user): returns the answer and finishes the task.\\n\"\n", " f\" (2) {JOINER_REPLAN}(the reasoning and other information that will help you plan again. Can be a line of any length): instructs why we must replan\\n\\n\"\n", " \" Examples:\\n\"\n", " \"Question: How many users are currently using the new product?\\n\"\n", " \"...task returns the number 32,000\\n\"\n", " \"Thought: I find no issue with the original plan, and the results satisfy everything in the user question.\\n\"\n", " f\"Action: {JOINER_FINISH}(32,000 users currently use the new product)\\n###\\n\"\n", " \"Question: How much cooler is it in NY than SF?\\n\"\n", " \"...task results show SF is 57 degrees fahrenheit today, and they show in NY it has a high of 32 degrees fahrenheit \\n\"\n", " \"Thought: I can answer by synthesizing the results.\\n\"\n", " f\"Action: {JOINER_FINISH}(NY is 25 degrees cooler than SF today, as it has a high of 32 degrees Fahrenheit today, whereas in SF, it is 57 degrees Fahrenheit.)\\n###\\n\"\n", " \"Question: Are the gophers beating the rabbits??\\n\"\n", " \"...task returns the a score of 7 for rabbits but no other value...\\n\"\n", " \"Thought: I need the gophers' score to make a final decision.\\n\"\n", " f\"Action: {JOINER_REPLAN}(The rabbits have a score of 7, but I need the gophers' score.)\"\n", " \"\\nAssistant Scratchpad:\\n{scratchpad}\"\n", ")" ] }, { "cell_type": "code", "execution_count": 219, "id": "a07d0804-2ce5-4462-98eb-4473f36ef704", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'thought': 'The plan has been executed successfully and returned the scores for both Aliya and Roger in Geology. We can compare their scores to determine if Aliya got a better score than Roger.',\n", " 'answer': 'Aliya got an A+ in Geology, while Roger also got an A+. Therefore, they both got the same score in Geology.'}" ] }, "execution_count": 219, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joiner = create_joiner(system_prompt, ChatOpenAI(model=\"gpt-3.5-turbo\"))\n", "joiner.invoke({\"plan\": task_results, \"input\": example_question})" ] }, { "cell_type": "markdown", "id": "b099e5ee-2c23-47d9-9387-0f64e02627d3", "metadata": {}, "source": [ "### Construct Agent\n", "\n", "Now we have all the required pieces! Let's construct our agent with its tools." ] }, { "cell_type": "code", "execution_count": 220, "id": "565b08d2-d19c-4125-97f7-996fc01bc631", "metadata": {}, "outputs": [], "source": [ "import getpass\n", "import os\n", "\n", "os.environ[\"TAVILY_API_KEY\"] = (\n", " os.environ.get(\"TAVILY_API_KEY\")\n", " if \"TAVILY_API_KEY\" in os.environ\n", " else getpass.getpass(\"Tavily API Key:\")\n", ")\n", "# Then fetch a credentials.json file\n", "# https://developers.google.com/gmail/api/quickstart/python#authorize_credentials_for_a_desktop_application" ] }, { "cell_type": "code", "execution_count": 221, "id": "bd84ca4b-eacb-471d-9975-5449047b5bed", "metadata": {}, "outputs": [], "source": [ "from operator import add, mul, sub, truediv\n", "from typing import Literal\n", "\n", "from langchain_community.agent_toolkits import GmailToolkit\n", "from langchain_community.tools.tavily_search import TavilySearchResults\n", "from langchain_core.tools import tool\n", "\n", "\n", "@tool\n", "def calculate(\n", " arg1: float,\n", " arg2: float,\n", " op: Union[Literal[\"+\"], Literal[\"-\"], Literal[\"*\"], Literal[\"/\"]],\n", "):\n", " \"\"\"Calculate a mathematical operation on two arguments.\"\"\"\n", " resolved_op = {\"+\": add, \"-\": sub, \"*\": mul, \"/\": truediv}\n", " return resolved_op[op](arg1, arg2)\n", "\n", "\n", "tools = [TavilySearchResults(max_results=1), calculate]" ] }, { "cell_type": "code", "execution_count": 224, "id": "768b5f11-e3d2-47be-8143-a7dcd8765243", "metadata": {}, "outputs": [], "source": [ "from langgraph.graph import END, StateGraph\n", "\n", "\n", "class GraphState(TypedDict):\n", " input: str\n", " plan: Dict\n", " agent_output: Dict\n", " observations: Dict\n", " num_iterations: int\n", " context: str\n", " stop_reason: str\n", "\n", "\n", "MAX_ITERATIONS = 5\n", "workflow = StateGraph(GraphState)\n", "\n", "# 1. Define vertices\n", "\n", "planner = create_planner(\n", " llm=ChatOpenAI(model=\"gpt-4-1106-preview\"),\n", " # Add more examples to improve reliability\n", " example_prompt=(\n", " \"Question: What's the capital of Myanmar?\\n\"\n", " '1. {\"tavily_search_results_json\": {\"query\": \"Capital of Myanmar\"}}\\n'\n", " f'2. {{\"join\": null}}{END_OF_PLAN}\\n'\n", " \"###\\n\"\n", " \"\\n\"\n", " ),\n", " tools=tools,\n", ")\n", "\n", "plan_and_execute = planner | construct_dag\n", "joiner = create_joiner(system_prompt, ChatOpenAI(model=\"gpt-4-1106-preview\"))\n", "\n", "\n", "def _reformat_task(idx, task: Union[BaseTool, str]):\n", " tool = task[\"tool\"]\n", " tool_name = tool if isinstance(tool, str) else tool.name\n", " called = {tool_name: task[\"args\"]}\n", " return f\"{idx}. {json.dumps(called)}\"\n", "\n", "\n", "def provide_context(state):\n", " # Insert a context string for the re-planner.\n", " # This could alternatively call an LLM to provide additional logic\n", " context = state[\"agent_output\"][\"context\"]\n", " num_iterations = int(state.get(\"num_iterations\") or 1) + 1\n", " previous_plan = \"\\n\".join(\n", " [\n", " _reformat_task(idx, task)\n", " for idx, task in sorted(state[\"plan\"][\"tasks\"].items())\n", " ]\n", " )\n", " context_str = (\n", " f\"\\n\\nPrevious Plan:\\n{previous_plan}\\n\"\n", " f\"{context}\\nYou have made {num_iterations}/{MAX_ITERATIONS} attempts thus far.\"\n", " )\n", " observations = state[\"observations\"] or {}\n", " for task, observation in state[\"plan\"][\"join\"].items():\n", " observations[task] = observation\n", " return {\n", " \"context\": context_str,\n", " \"num_iterations\": num_iterations,\n", " \"observations\": observations,\n", " }\n", "\n", "\n", "def add_stop_reason(state):\n", " num_iterations = int(state.get(\"num_iterations\") or 0)\n", " if num_iterations >= MAX_ITERATIONS:\n", " return {\"stop_reason\": \"end_max_iter\"}\n", " if state[\"agent_output\"].get(\"answer\"):\n", " return {\"stop_reason\": \"answer\"}\n", " return {\"stop_reason\": None}\n", "\n", "\n", "# Assign each node to a state variable to update\n", "workflow.add_node(\"plan_and_execute\", RunnablePassthrough.assign(plan=plan_and_execute))\n", "workflow.add_node(\"join\", RunnablePassthrough.assign(agent_output=joiner))\n", "workflow.add_node(\"provide_context\", provide_context)\n", "workflow.add_node(\"provide_stop_reason\", add_stop_reason)\n", "\n", "\n", "## Define edges\n", "\n", "workflow.add_edge(\"plan_and_execute\", \"join\")\n", "workflow.add_edge(\"provide_context\", \"plan_and_execute\")\n", "workflow.add_edge(\"join\", \"provide_stop_reason\")\n", "\n", "### This condition determines looping logic\n", "\n", "\n", "def should_continue(state):\n", " if state[\"stop_reason\"] is None:\n", " return \"continue\"\n", " return \"end\"\n", "\n", "\n", "workflow.add_conditional_edges(\n", " start_key=\"provide_stop_reason\",\n", " # Next, we pass in the function that will determine which node is called next.\n", " condition=should_continue,\n", " conditional_edge_mapping={\n", " # If it generates context, we must replan\n", " \"continue\": \"provide_context\",\n", " # Otherwise we finish.\n", " \"end\": END,\n", " },\n", ")\n", "workflow.set_entry_point(\"plan_and_execute\")\n", "chain = workflow.compile()" ] }, { "cell_type": "markdown", "id": "9f8c9849-8531-463d-a0ef-dcc3d9888b2d", "metadata": {}, "source": [ "## Simple question\n", "\n", "Let's ask a simple question of the agent." ] }, { "cell_type": "code", "execution_count": 225, "id": "5bc4584a-e31c-4065-805e-76a6db30676a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "The GDP of New York in 2022 was about 1.56 trillion U.S. dollars.\n" ] } ], "source": [ "result = chain.invoke({\"input\": \"What's the GDP of New York?\"})\n", "print(result[\"agent_output\"][\"answer\"])" ] }, { "cell_type": "markdown", "id": "33c65ef5-b4b2-4ab2-8c78-a551da7819b9", "metadata": {}, "source": [ "## Multi-hop question" ] }, { "cell_type": "code", "execution_count": 227, "id": "0b3a0916-d8ca-4092-b91c-d9e2b05259d8", "metadata": {}, "outputs": [ { "ename": "JSONDecodeError", "evalue": "Expecting value: line 1 column 1 (char 0)", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mJSONDecodeError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[227], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43mchain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 2\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43minput\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mHow much larger is the GDP of the UK than that of New York?\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m}\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/code/lc/langgraph/langgraph/pregel/__init__.py:492\u001b[0m, in \u001b[0;36mPregel.invoke\u001b[0;34m(self, input, config, output_keys, input_keys, **kwargs)\u001b[0m\n\u001b[1;32m 482\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m 483\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 484\u001b[0m \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Any], Any],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 489\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 490\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[\u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Any], Any]:\n\u001b[1;32m 491\u001b[0m latest: Union[\u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Any], Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 492\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 493\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 494\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 495\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_keys\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43moutput_keys\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moutput\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 496\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minput_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 497\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 498\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 499\u001b[0m \u001b[43m \u001b[49m\u001b[43mlatest\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\n\u001b[1;32m 500\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m latest\n", "File \u001b[0;32m~/code/lc/langgraph/langgraph/pregel/__init__.py:528\u001b[0m, in \u001b[0;36mPregel.transform\u001b[0;34m(self, input, config, output_keys, input_keys, **kwargs)\u001b[0m\n\u001b[1;32m 519\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mtransform\u001b[39m(\n\u001b[1;32m 520\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 521\u001b[0m \u001b[38;5;28minput\u001b[39m: Iterator[Union[\u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Any], Any]],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 526\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 527\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Iterator[Union[\u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Any], Any]]:\n\u001b[0;32m--> 528\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_transform_stream_with_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 529\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 530\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_transform\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 531\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 532\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 533\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minput_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 534\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 535\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 536\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:1226\u001b[0m, in \u001b[0;36mRunnable._transform_stream_with_config\u001b[0;34m(self, input, transformer, config, run_type, **kwargs)\u001b[0m\n\u001b[1;32m 1224\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1225\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m-> 1226\u001b[0m chunk: Output \u001b[38;5;241m=\u001b[39m context\u001b[38;5;241m.\u001b[39mrun(\u001b[38;5;28mnext\u001b[39m, iterator) \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[1;32m 1227\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m chunk\n\u001b[1;32m 1228\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m final_output_supported:\n", "File \u001b[0;32m~/code/lc/langgraph/langgraph/pregel/__init__.py:313\u001b[0m, in \u001b[0;36mPregel._transform\u001b[0;34m(self, input, run_manager, config, input_keys, output_keys)\u001b[0m\n\u001b[1;32m 303\u001b[0m done, inflight \u001b[38;5;241m=\u001b[39m concurrent\u001b[38;5;241m.\u001b[39mfutures\u001b[38;5;241m.\u001b[39mwait(\n\u001b[1;32m 304\u001b[0m [\n\u001b[1;32m 305\u001b[0m executor\u001b[38;5;241m.\u001b[39msubmit(proc\u001b[38;5;241m.\u001b[39minvoke, \u001b[38;5;28minput\u001b[39m, config)\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 309\u001b[0m timeout\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstep_timeout,\n\u001b[1;32m 310\u001b[0m )\n\u001b[1;32m 312\u001b[0m \u001b[38;5;66;03m# interrupt on failure or timeout\u001b[39;00m\n\u001b[0;32m--> 313\u001b[0m \u001b[43m_interrupt_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 315\u001b[0m \u001b[38;5;66;03m# apply writes to channels\u001b[39;00m\n\u001b[1;32m 316\u001b[0m _apply_writes(checkpoint, channels, pending_writes, config, step \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m)\n", "File \u001b[0;32m~/code/lc/langgraph/langgraph/pregel/__init__.py:611\u001b[0m, in \u001b[0;36m_interrupt_or_proceed\u001b[0;34m(done, inflight, step)\u001b[0m\n\u001b[1;32m 609\u001b[0m inflight\u001b[38;5;241m.\u001b[39mpop()\u001b[38;5;241m.\u001b[39mcancel()\n\u001b[1;32m 610\u001b[0m \u001b[38;5;66;03m# raise the exception\u001b[39;00m\n\u001b[0;32m--> 611\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exc\n\u001b[1;32m 612\u001b[0m \u001b[38;5;66;03m# TODO this is where retry of an entire step would happen\u001b[39;00m\n\u001b[1;32m 614\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inflight:\n\u001b[1;32m 615\u001b[0m \u001b[38;5;66;03m# if we got here means we timed out\u001b[39;00m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/concurrent/futures/thread.py:58\u001b[0m, in \u001b[0;36m_WorkItem.run\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 55\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[1;32m 57\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 58\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 59\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 60\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~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:3596\u001b[0m, in \u001b[0;36mRunnableBindingBase.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 3590\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m 3591\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 3592\u001b[0m \u001b[38;5;28minput\u001b[39m: Input,\n\u001b[1;32m 3593\u001b[0m config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 3594\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Optional[Any],\n\u001b[1;32m 3595\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Output:\n\u001b[0;32m-> 3596\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbound\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3597\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3598\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_merge_configs\u001b[49m\u001b[43m(\u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3599\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;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\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\u001b[43m,\u001b[49m\n\u001b[1;32m 3600\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:1774\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m 1772\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1773\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, step \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msteps):\n\u001b[0;32m-> 1774\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\n\u001b[1;32m 1775\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1776\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# mark each step as a child run\u001b[39;49;00m\n\u001b[1;32m 1777\u001b[0m \u001b[43m \u001b[49m\u001b[43mpatch_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1778\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseq:step:\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mi\u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1779\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1780\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1781\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m 1782\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~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/passthrough.py:415\u001b[0m, in \u001b[0;36mRunnableAssign.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 409\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m 410\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 411\u001b[0m \u001b[38;5;28minput\u001b[39m: Dict[\u001b[38;5;28mstr\u001b[39m, Any],\n\u001b[1;32m 412\u001b[0m config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 413\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 414\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Dict[\u001b[38;5;28mstr\u001b[39m, Any]:\n\u001b[0;32m--> 415\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \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\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_invoke\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[43mconfig\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\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:975\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 971\u001b[0m context \u001b[38;5;241m=\u001b[39m copy_context()\n\u001b[1;32m 972\u001b[0m context\u001b[38;5;241m.\u001b[39mrun(var_child_runnable_config\u001b[38;5;241m.\u001b[39mset, child_config)\n\u001b[1;32m 973\u001b[0m output \u001b[38;5;241m=\u001b[39m cast(\n\u001b[1;32m 974\u001b[0m Output,\n\u001b[0;32m--> 975\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 976\u001b[0m \u001b[43m \u001b[49m\u001b[43mcall_func_with_variable_args\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 977\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 978\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 979\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 980\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 981\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 982\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m 983\u001b[0m )\n\u001b[1;32m 984\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 985\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/config.py:323\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 321\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 322\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--> 323\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~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/passthrough.py:402\u001b[0m, in \u001b[0;36mRunnableAssign._invoke\u001b[0;34m(self, input, run_manager, config, **kwargs)\u001b[0m\n\u001b[1;32m 389\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_invoke\u001b[39m(\n\u001b[1;32m 390\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 391\u001b[0m \u001b[38;5;28minput\u001b[39m: Dict[\u001b[38;5;28mstr\u001b[39m, Any],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 394\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 395\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Dict[\u001b[38;5;28mstr\u001b[39m, Any]:\n\u001b[1;32m 396\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\n\u001b[1;32m 397\u001b[0m \u001b[38;5;28minput\u001b[39m, \u001b[38;5;28mdict\u001b[39m\n\u001b[1;32m 398\u001b[0m ), \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe input to RunnablePassthrough.assign() must be a dict.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 400\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m 401\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28minput\u001b[39m,\n\u001b[0;32m--> 402\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28;43mself\u001b[39;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\n\u001b[1;32m 403\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 404\u001b[0m \u001b[43m \u001b[49m\u001b[43mpatch_config\u001b[49m\u001b[43m(\u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 405\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 406\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m 407\u001b[0m }\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:2339\u001b[0m, in \u001b[0;36mRunnableParallel.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m 2326\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m get_executor_for_config(config) \u001b[38;5;28;01mas\u001b[39;00m executor:\n\u001b[1;32m 2327\u001b[0m futures \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m 2328\u001b[0m executor\u001b[38;5;241m.\u001b[39msubmit(\n\u001b[1;32m 2329\u001b[0m step\u001b[38;5;241m.\u001b[39minvoke,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 2337\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, step \u001b[38;5;129;01min\u001b[39;00m steps\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m 2338\u001b[0m ]\n\u001b[0;32m-> 2339\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43m{\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfuture\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfuture\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mzip\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msteps\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfutures\u001b[49m\u001b[43m)\u001b[49m\u001b[43m}\u001b[49m\n\u001b[1;32m 2340\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m 2341\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~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:2339\u001b[0m, in \u001b[0;36m\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 2326\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m get_executor_for_config(config) \u001b[38;5;28;01mas\u001b[39;00m executor:\n\u001b[1;32m 2327\u001b[0m futures \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m 2328\u001b[0m executor\u001b[38;5;241m.\u001b[39msubmit(\n\u001b[1;32m 2329\u001b[0m step\u001b[38;5;241m.\u001b[39minvoke,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 2337\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, step \u001b[38;5;129;01min\u001b[39;00m steps\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m 2338\u001b[0m ]\n\u001b[0;32m-> 2339\u001b[0m output \u001b[38;5;241m=\u001b[39m {key: \u001b[43mfuture\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m key, future \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(steps, futures)}\n\u001b[1;32m 2340\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m 2341\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~/.pyenv/versions/3.11.2/lib/python3.11/concurrent/futures/_base.py:456\u001b[0m, in \u001b[0;36mFuture.result\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 454\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m CancelledError()\n\u001b[1;32m 455\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;241m==\u001b[39m FINISHED:\n\u001b[0;32m--> 456\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__get_result\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 457\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 458\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTimeoutError\u001b[39;00m()\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/concurrent/futures/_base.py:401\u001b[0m, in \u001b[0;36mFuture.__get_result\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 399\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception:\n\u001b[1;32m 400\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 401\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception\n\u001b[1;32m 402\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m 403\u001b[0m \u001b[38;5;66;03m# Break a reference cycle with the exception in self._exception\u001b[39;00m\n\u001b[1;32m 404\u001b[0m \u001b[38;5;28mself\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/concurrent/futures/thread.py:58\u001b[0m, in \u001b[0;36m_WorkItem.run\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 55\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[1;32m 57\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 58\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 59\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 60\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~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:1774\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m 1772\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1773\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, step \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msteps):\n\u001b[0;32m-> 1774\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\n\u001b[1;32m 1775\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1776\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# mark each step as a child run\u001b[39;49;00m\n\u001b[1;32m 1777\u001b[0m \u001b[43m \u001b[49m\u001b[43mpatch_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1778\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseq:step:\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mi\u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1779\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1780\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1781\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m 1782\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~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/output_parsers/base.py:167\u001b[0m, in \u001b[0;36mBaseOutputParser.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m 164\u001b[0m \u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, BaseMessage], config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 165\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T:\n\u001b[1;32m 166\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28minput\u001b[39m, BaseMessage):\n\u001b[0;32m--> 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \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 168\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43minner_input\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_result\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 169\u001b[0m \u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatGeneration\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmessage\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minner_input\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m 170\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 171\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 172\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 173\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 174\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 175\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 176\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_with_config(\n\u001b[1;32m 177\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m inner_input: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparse_result([Generation(text\u001b[38;5;241m=\u001b[39minner_input)]),\n\u001b[1;32m 178\u001b[0m \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m 179\u001b[0m config,\n\u001b[1;32m 180\u001b[0m run_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparser\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 181\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/base.py:975\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 971\u001b[0m context \u001b[38;5;241m=\u001b[39m copy_context()\n\u001b[1;32m 972\u001b[0m context\u001b[38;5;241m.\u001b[39mrun(var_child_runnable_config\u001b[38;5;241m.\u001b[39mset, child_config)\n\u001b[1;32m 973\u001b[0m output \u001b[38;5;241m=\u001b[39m cast(\n\u001b[1;32m 974\u001b[0m Output,\n\u001b[0;32m--> 975\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 976\u001b[0m \u001b[43m \u001b[49m\u001b[43mcall_func_with_variable_args\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 977\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 978\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 979\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 980\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 981\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 982\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m 983\u001b[0m )\n\u001b[1;32m 984\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 985\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/runnables/config.py:323\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 321\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 322\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--> 323\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~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/output_parsers/base.py:168\u001b[0m, in \u001b[0;36mBaseOutputParser.invoke..\u001b[0;34m(inner_input)\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m 164\u001b[0m \u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, BaseMessage], config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 165\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T:\n\u001b[1;32m 166\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28minput\u001b[39m, BaseMessage):\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_with_config(\n\u001b[0;32m--> 168\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m inner_input: \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_result\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 169\u001b[0m \u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatGeneration\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmessage\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minner_input\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m 170\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m 171\u001b[0m \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m 172\u001b[0m config,\n\u001b[1;32m 173\u001b[0m run_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparser\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 174\u001b[0m )\n\u001b[1;32m 175\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 176\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_with_config(\n\u001b[1;32m 177\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m inner_input: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparse_result([Generation(text\u001b[38;5;241m=\u001b[39minner_input)]),\n\u001b[1;32m 178\u001b[0m \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m 179\u001b[0m config,\n\u001b[1;32m 180\u001b[0m run_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparser\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 181\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/site-packages/langchain_core/output_parsers/base.py:219\u001b[0m, in \u001b[0;36mBaseOutputParser.parse_result\u001b[0;34m(self, result, partial)\u001b[0m\n\u001b[1;32m 206\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mparse_result\u001b[39m(\u001b[38;5;28mself\u001b[39m, result: List[Generation], \u001b[38;5;241m*\u001b[39m, partial: \u001b[38;5;28mbool\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T:\n\u001b[1;32m 207\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Parse a list of candidate model Generations into a specific format.\u001b[39;00m\n\u001b[1;32m 208\u001b[0m \n\u001b[1;32m 209\u001b[0m \u001b[38;5;124;03m The return value is parsed from only the first Generation in the result, which\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 217\u001b[0m \u001b[38;5;124;03m Structured output.\u001b[39;00m\n\u001b[1;32m 218\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 219\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n", "Cell \u001b[0;32mIn[1], line 88\u001b[0m, in \u001b[0;36mLLMCompilerPlanParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 86\u001b[0m parser \u001b[38;5;241m=\u001b[39m ActionParserFSM()\n\u001b[1;32m 87\u001b[0m graph_dict \u001b[38;5;241m=\u001b[39m {}\n\u001b[0;32m---> 88\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mtask\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 89\u001b[0m \u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43mint\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mtask\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtask_index\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 91\u001b[0m \u001b[43m \u001b[49m\u001b[43mtask\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43minstantiate_task\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 92\u001b[0m \u001b[43m \u001b[49m\u001b[43mtools\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[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 93\u001b[0m \u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43midx\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 94\u001b[0m \u001b[43m \u001b[49m\u001b[43mtool_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtask\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtool_name\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 95\u001b[0m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtask\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43margs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 96\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n", "Cell \u001b[0;32mIn[1], line 29\u001b[0m, in \u001b[0;36mActionParserFSM.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mparse\u001b[39m(\u001b[38;5;28mself\u001b[39m, text: \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 28\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m char \u001b[38;5;129;01min\u001b[39;00m text:\n\u001b[0;32m---> 29\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mprocess_char\u001b[49m\u001b[43m(\u001b[49m\u001b[43mchar\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 30\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m action:\n\u001b[1;32m 31\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m action\n", "Cell \u001b[0;32mIn[1], line 61\u001b[0m, in \u001b[0;36mActionParserFSM.process_char\u001b[0;34m(self, char)\u001b[0m\n\u001b[1;32m 59\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCOMMENT\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 60\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m char \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m---> 61\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave_action\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 62\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreset()\n\u001b[1;32m 63\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", "Cell \u001b[0;32mIn[1], line 69\u001b[0m, in \u001b[0;36mActionParserFSM.save_action\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 67\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21msave_action\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 68\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtask_index \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maction:\n\u001b[0;32m---> 69\u001b[0m parsed_action \u001b[38;5;241m=\u001b[39m \u001b[43mjson\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloads\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43maction\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstrip\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 70\u001b[0m tool_name, args \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mnext\u001b[39m(\u001b[38;5;28miter\u001b[39m(parsed_action\u001b[38;5;241m.\u001b[39mitems()))\n\u001b[1;32m 71\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m 72\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtask_index\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mint\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtask_index),\n\u001b[1;32m 73\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtool_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: tool_name,\n\u001b[1;32m 74\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124margs\u001b[39m\u001b[38;5;124m\"\u001b[39m: args,\n\u001b[1;32m 75\u001b[0m }\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/json/__init__.py:346\u001b[0m, in \u001b[0;36mloads\u001b[0;34m(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)\u001b[0m\n\u001b[1;32m 341\u001b[0m s \u001b[38;5;241m=\u001b[39m s\u001b[38;5;241m.\u001b[39mdecode(detect_encoding(s), \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msurrogatepass\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 343\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m object_hook \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m 344\u001b[0m parse_int \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m parse_float \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m 345\u001b[0m parse_constant \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m object_pairs_hook \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m kw):\n\u001b[0;32m--> 346\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_default_decoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 347\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 348\u001b[0m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;241m=\u001b[39m JSONDecoder\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/json/decoder.py:337\u001b[0m, in \u001b[0;36mJSONDecoder.decode\u001b[0;34m(self, s, _w)\u001b[0m\n\u001b[1;32m 332\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecode\u001b[39m(\u001b[38;5;28mself\u001b[39m, s, _w\u001b[38;5;241m=\u001b[39mWHITESPACE\u001b[38;5;241m.\u001b[39mmatch):\n\u001b[1;32m 333\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Return the Python representation of ``s`` (a ``str`` instance\u001b[39;00m\n\u001b[1;32m 334\u001b[0m \u001b[38;5;124;03m containing a JSON document).\u001b[39;00m\n\u001b[1;32m 335\u001b[0m \n\u001b[1;32m 336\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 337\u001b[0m obj, end \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraw_decode\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_w\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mend\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 338\u001b[0m end \u001b[38;5;241m=\u001b[39m _w(s, end)\u001b[38;5;241m.\u001b[39mend()\n\u001b[1;32m 339\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m end \u001b[38;5;241m!=\u001b[39m \u001b[38;5;28mlen\u001b[39m(s):\n", "File \u001b[0;32m~/.pyenv/versions/3.11.2/lib/python3.11/json/decoder.py:355\u001b[0m, in \u001b[0;36mJSONDecoder.raw_decode\u001b[0;34m(self, s, idx)\u001b[0m\n\u001b[1;32m 353\u001b[0m obj, end \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscan_once(s, idx)\n\u001b[1;32m 354\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[0;32m--> 355\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m JSONDecodeError(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExpecting value\u001b[39m\u001b[38;5;124m\"\u001b[39m, s, err\u001b[38;5;241m.\u001b[39mvalue) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 356\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m obj, end\n", "\u001b[0;31mJSONDecodeError\u001b[0m: Expecting value: line 1 column 1 (char 0)" ] } ], "source": [ "result = chain.invoke(\n", " {\"input\": \"How much larger is the GDP of the UK than that of New York?\"}\n", ")" ] }, { "cell_type": "code", "execution_count": null, "id": "a157cd88-2e54-4525-8126-6d22affa31d7", "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": "3.11.2" } }, "nbformat": 4, "nbformat_minor": 5 }