From 9165267f8a63a3ff5c2bc92ca4224f4f26db3b55 Mon Sep 17 00:00:00 2001 From: Harrison Chase Date: Wed, 17 May 2023 21:41:01 -0700 Subject: [PATCH] Harrison/improved retry tool (#4842) --- .../examples/handle_parsing_errors.ipynb | 329 ++++++++++++++++++ langchain/agents/agent.py | 49 ++- 2 files changed, 366 insertions(+), 12 deletions(-) create mode 100644 docs/modules/agents/agent_executors/examples/handle_parsing_errors.ipynb diff --git a/docs/modules/agents/agent_executors/examples/handle_parsing_errors.ipynb b/docs/modules/agents/agent_executors/examples/handle_parsing_errors.ipynb new file mode 100644 index 00000000..dd97f24d --- /dev/null +++ b/docs/modules/agents/agent_executors/examples/handle_parsing_errors.ipynb @@ -0,0 +1,329 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "6317727b", + "metadata": {}, + "source": [ + "# Handle Parsing Errors\n", + "\n", + "Occasionally the LLM cannot determine what step to take because it outputs format in incorrect form to be handled by the output parser. In this case, by default the agent errors. But you can easily control this functionality with `handle_parsing_errors`! Let's explore how." + ] + }, + { + "cell_type": "markdown", + "id": "39cc1a7b", + "metadata": {}, + "source": [ + "## Setup" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "33c7f220", + "metadata": {}, + "outputs": [], + "source": [ + "from langchain import OpenAI, LLMMathChain, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain\n", + "from langchain.agents import initialize_agent, Tool\n", + "from langchain.agents import AgentType\n", + "from langchain.chat_models import ChatOpenAI\n", + "from langchain.agents.types import AGENT_TO_CLASS" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "3de22959", + "metadata": {}, + "outputs": [], + "source": [ + "search = SerpAPIWrapper()\n", + "tools = [\n", + " Tool(\n", + " name = \"Search\",\n", + " func=search.run,\n", + " description=\"useful for when you need to answer questions about current events. You should ask targeted questions\"\n", + " ),\n", + "]" + ] + }, + { + "cell_type": "markdown", + "id": "9f1fc58a", + "metadata": {}, + "source": [ + "## Error\n", + "\n", + "In this scenario, the agent will error (because it fails to output an Action string)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "32ad08d1", + "metadata": {}, + "outputs": [], + "source": [ + "mrkl = initialize_agent(\n", + " tools, \n", + " ChatOpenAI(temperature=0), \n", + " agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n", + " verbose=True,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "facb8895", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "\n", + "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n" + ] + }, + { + "ename": "OutputParserException", + "evalue": "Could not parse LLM output: I'm sorry, but I cannot provide an answer without an Action. Please provide a valid Action in the format specified above.", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)", + "File \u001b[0;32m~/workplace/langchain/langchain/agents/chat/output_parser.py:21\u001b[0m, in \u001b[0;36mChatOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 21\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[43mtext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m```\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\n\u001b[1;32m 22\u001b[0m response \u001b[38;5;241m=\u001b[39m json\u001b[38;5;241m.\u001b[39mloads(action\u001b[38;5;241m.\u001b[39mstrip())\n", + "\u001b[0;31mIndexError\u001b[0m: list index out of range", + "\nDuring handling of the above exception, another exception occurred:\n", + "\u001b[0;31mOutputParserException\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[4], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmrkl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mWho is Leo DiCaprio\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43ms girlfriend? No need to add Action\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m~/workplace/langchain/langchain/chains/base.py:236\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, callbacks, *args, **kwargs)\u001b[0m\n\u001b[1;32m 234\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 235\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` supports only one positional argument.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 236\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys[\u001b[38;5;241m0\u001b[39m]]\n\u001b[1;32m 238\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args:\n\u001b[1;32m 239\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs, callbacks\u001b[38;5;241m=\u001b[39mcallbacks)[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys[\u001b[38;5;241m0\u001b[39m]]\n", + "File \u001b[0;32m~/workplace/langchain/langchain/chains/base.py:140\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m 138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 139\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 140\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 141\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m 142\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(inputs, outputs, return_only_outputs)\n", + "File \u001b[0;32m~/workplace/langchain/langchain/chains/base.py:134\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m 128\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m 129\u001b[0m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m},\n\u001b[1;32m 130\u001b[0m inputs,\n\u001b[1;32m 131\u001b[0m )\n\u001b[1;32m 132\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 133\u001b[0m outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 134\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 135\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m 136\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m 137\u001b[0m )\n\u001b[1;32m 138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 139\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n", + "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:947\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m 945\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m 946\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m--> 947\u001b[0m next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 948\u001b[0m \u001b[43m \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 949\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 950\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 951\u001b[0m \u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 952\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 953\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 954\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m 955\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m 956\u001b[0m next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m 957\u001b[0m )\n", + "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:773\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m 771\u001b[0m raise_error \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m 772\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m raise_error:\n\u001b[0;32m--> 773\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 774\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(e)\n\u001b[1;32m 775\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n", + "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:762\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m 756\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Take a single step in the thought-action-observation loop.\u001b[39;00m\n\u001b[1;32m 757\u001b[0m \n\u001b[1;32m 758\u001b[0m \u001b[38;5;124;03mOverride this to take control of how the agent makes and acts on choices.\u001b[39;00m\n\u001b[1;32m 759\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 760\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 761\u001b[0m \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m--> 762\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplan\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 763\u001b[0m \u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 764\u001b[0m \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[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 765\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 766\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 767\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m OutputParserException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 768\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n", + "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:444\u001b[0m, in \u001b[0;36mAgent.plan\u001b[0;34m(self, intermediate_steps, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m 442\u001b[0m full_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_full_inputs(intermediate_steps, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 443\u001b[0m full_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_chain\u001b[38;5;241m.\u001b[39mpredict(callbacks\u001b[38;5;241m=\u001b[39mcallbacks, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfull_inputs)\n\u001b[0;32m--> 444\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[43moutput_parser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfull_output\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m~/workplace/langchain/langchain/agents/chat/output_parser.py:26\u001b[0m, in \u001b[0;36mChatOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 23\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m AgentAction(response[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maction\u001b[39m\u001b[38;5;124m\"\u001b[39m], response[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maction_input\u001b[39m\u001b[38;5;124m\"\u001b[39m], text)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m---> 26\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m OutputParserException(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCould not parse LLM output: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n", + "\u001b[0;31mOutputParserException\u001b[0m: Could not parse LLM output: I'm sorry, but I cannot provide an answer without an Action. Please provide a valid Action in the format specified above." + ] + } + ], + "source": [ + "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")" + ] + }, + { + "cell_type": "markdown", + "id": "72687d56", + "metadata": {}, + "source": [ + "## Default error handling\n", + "\n", + "Handle errors with `Invalid or incomplete response`" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "6bfc21ef", + "metadata": {}, + "outputs": [], + "source": [ + "mrkl = initialize_agent(\n", + " tools, \n", + " ChatOpenAI(temperature=0), \n", + " agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n", + " verbose=True,\n", + " handle_parsing_errors=True\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "9c181f33", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "\n", + "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n", + "\n", + "Observation: Invalid or incomplete response\n", + "Thought:\n", + "Observation: Invalid or incomplete response\n", + "Thought:\u001b[32;1m\u001b[1;3mSearch for Leo DiCaprio's current girlfriend\n", + "Action:\n", + "```\n", + "{\n", + " \"action\": \"Search\",\n", + " \"action_input\": \"Leo DiCaprio current girlfriend\"\n", + "}\n", + "```\n", + "\u001b[0m\n", + "Observation: \u001b[36;1m\u001b[1;3mJust Jared on Instagram: “Leonardo DiCaprio & girlfriend Camila Morrone couple up for a lunch date!\u001b[0m\n", + "Thought:\u001b[32;1m\u001b[1;3mCamila Morrone is currently Leo DiCaprio's girlfriend\n", + "Final Answer: Camila Morrone\u001b[0m\n", + "\n", + "\u001b[1m> Finished chain.\u001b[0m\n" + ] + }, + { + "data": { + "text/plain": [ + "'Camila Morrone'" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")" + ] + }, + { + "cell_type": "markdown", + "id": "6613cc9c", + "metadata": {}, + "source": [ + "## Custom Error Message\n", + "\n", + "You can easily customize the message to use when there are parsing errors" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "2b23b0af", + "metadata": {}, + "outputs": [], + "source": [ + "mrkl = initialize_agent(\n", + " tools, \n", + " ChatOpenAI(temperature=0), \n", + " agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n", + " verbose=True,\n", + " handle_parsing_errors=\"Check your output and make sure it conforms!\"\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5d5a3e47", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "\n", + "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n", + "\n", + "Observation: Check your output and make sure it conforms!\n", + "Thought:\n", + "Observation: Check your output and make sure it conforms!\n", + "Thought:\u001b[32;1m\u001b[1;3mI'm sorry for the confusion. However, as the question is about a current event, I can use the Search tool to find the answer.\n", + "Action:\n", + "```\n", + "{\n", + " \"action\": \"Search\",\n", + " \"action_input\": \"Leo DiCaprio girlfriend\"\n", + "}\n", + "```\n", + "\u001b[0m\n", + "Observation: \u001b[36;1m\u001b[1;3mHe went on to date Gisele Bündchen, Bar Refaeli, Blake Lively, Toni Garrn and Nina Agdal, among others, before finally settling down with current girlfriend Camila Morrone, who is 23 years his junior.\u001b[0m\n", + "Thought:\u001b[32;1m\u001b[1;3mThe answer to the question is Camila Morrone. \n", + "Final Answer: Camila Morrone.\u001b[0m\n", + "\n", + "\u001b[1m> Finished chain.\u001b[0m\n" + ] + } + ], + "source": [ + "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "65de0bed", + "metadata": {}, + "outputs": [], + "source": [ + "## Custom Error Function\n", + "\n", + "You can also customize the error to be a fun" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "22772981", + "metadata": {}, + "outputs": [], + "source": [ + "def _handle_error(error) -> str:\n", + " return str(error)[:50]\n", + "\n", + "mrkl = initialize_agent(\n", + " tools, \n", + " ChatOpenAI(temperature=0), \n", + " agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n", + " verbose=True,\n", + " handle_parsing_errors=_handle_error\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "151eb820", + "metadata": {}, + "outputs": [], + "source": [ + "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4aaef878", + "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": "3.9.1" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/langchain/agents/agent.py b/langchain/agents/agent.py index f73b5f26..1e2e6495 100644 --- a/langchain/agents/agent.py +++ b/langchain/agents/agent.py @@ -7,7 +7,7 @@ import logging import time from abc import abstractmethod from pathlib import Path -from typing import Any, Dict, List, Optional, Sequence, Tuple, Union +from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple, Union import yaml from pydantic import BaseModel, root_validator @@ -34,6 +34,7 @@ from langchain.schema import ( AgentFinish, BaseMessage, BaseOutputParser, + OutputParserException, ) from langchain.tools.base import BaseTool from langchain.utilities.asyncio import asyncio_timeout @@ -625,7 +626,9 @@ class AgentExecutor(Chain): max_iterations: Optional[int] = 15 max_execution_time: Optional[float] = None early_stopping_method: str = "force" - handle_parsing_errors: bool = False + handle_parsing_errors: Union[ + bool, str, Callable[[OutputParserException], str] + ] = False @classmethod def from_agent_and_tools( @@ -761,15 +764,26 @@ class AgentExecutor(Chain): callbacks=run_manager.get_child() if run_manager else None, **inputs, ) - except Exception as e: - if not self.handle_parsing_errors: + except OutputParserException as e: + if isinstance(self.handle_parsing_errors, bool): + raise_error = not self.handle_parsing_errors + else: + raise_error = False + if raise_error: raise e - text = str(e).split("`")[1] - observation = "Invalid or incomplete response" + text = str(e) + if isinstance(self.handle_parsing_errors, bool): + observation = "Invalid or incomplete response" + elif isinstance(self.handle_parsing_errors, str): + observation = self.handle_parsing_errors + elif callable(self.handle_parsing_errors): + observation = self.handle_parsing_errors(e) + else: + raise ValueError("Got unexpected type of `handle_parsing_errors`") output = AgentAction("_Exception", observation, text) tool_run_kwargs = self.agent.tool_run_logging_kwargs() observation = ExceptionTool().run( - output.tool, + output.tool_input, verbose=self.verbose, color=None, callbacks=run_manager.get_child() if run_manager else None, @@ -835,15 +849,26 @@ class AgentExecutor(Chain): callbacks=run_manager.get_child() if run_manager else None, **inputs, ) - except Exception as e: - if not self.handle_parsing_errors: + except OutputParserException as e: + if isinstance(self.handle_parsing_errors, bool): + raise_error = not self.handle_parsing_errors + else: + raise_error = False + if raise_error: raise e - text = str(e).split("`")[1] - observation = "Invalid or incomplete response" + text = str(e) + if isinstance(self.handle_parsing_errors, bool): + observation = "Invalid or incomplete response" + elif isinstance(self.handle_parsing_errors, str): + observation = self.handle_parsing_errors + elif callable(self.handle_parsing_errors): + observation = self.handle_parsing_errors(e) + else: + raise ValueError("Got unexpected type of `handle_parsing_errors`") output = AgentAction("_Exception", observation, text) tool_run_kwargs = self.agent.tool_run_logging_kwargs() observation = await ExceptionTool().arun( - output.tool, + output.tool_input, verbose=self.verbose, color=None, callbacks=run_manager.get_child() if run_manager else None,