|
|
|
|
@@ -0,0 +1,228 @@
|
|
|
|
|
{
|
|
|
|
|
"cells": [
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"id": "f1390152",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"# MRKL Chat\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"This notebook showcases using an agent to replicate the MRKL chain using an agent optimized for chat models."
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"id": "39ea3638",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"This uses the example Chinook database.\n",
|
|
|
|
|
"To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 1,
|
|
|
|
|
"id": "ac561cc4",
|
|
|
|
|
"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, ChatAnthropic"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 5,
|
|
|
|
|
"id": "07e96d99",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stderr",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"/Users/harrisonchase/workplace/langchain/langchain/chains/llm_math/base.py:50: UserWarning: Directly instantiating an LLMMathChain with an llm is deprecated. Please instantiate with llm_chain argument or using the from_llm class method.\n",
|
|
|
|
|
" warnings.warn(\n"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"llm = ChatAnthropic(temperature=0)\n",
|
|
|
|
|
"llm1 = OpenAI(temperature=0)\n",
|
|
|
|
|
"search = SerpAPIWrapper()\n",
|
|
|
|
|
"llm_math_chain = LLMMathChain(llm=llm1, verbose=True)\n",
|
|
|
|
|
"db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
|
|
|
|
|
"db_chain = SQLDatabaseChain.from_llm(llm1, db, verbose=True)\n",
|
|
|
|
|
"tools = [\n",
|
|
|
|
|
" Tool(\n",
|
|
|
|
|
" name=\"Calculator\",\n",
|
|
|
|
|
" func=llm_math_chain.run,\n",
|
|
|
|
|
" description=\"useful for when you need to answer questions about math\"\n",
|
|
|
|
|
" ),\n",
|
|
|
|
|
"]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 6,
|
|
|
|
|
"id": "a069c4b6",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"mrkl = initialize_agent(tools, llm, agent=AgentType.INCEPTION_CHAT_AGENT, verbose=True)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 7,
|
|
|
|
|
"id": "e603cd7d",
|
|
|
|
|
"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: Question: Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\nThought: I need to look up who Leo DiCaprio's current girlfriend is.\nAction: \n{\n \"action\": \"Web Search\",\n \"action_input\": \"Who is Leonardo DiCaprio's current girlfriend?\"\n}\n",
|
|
|
|
|
"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[7], 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? What is her current age raised to the 0.43 power?\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:953\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m 951\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m 952\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--> 953\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 954\u001b[0m \u001b[43m \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 955\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 956\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 957\u001b[0m \u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 958\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 959\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 960\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m 961\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 962\u001b[0m next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m 963\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: Question: Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\nThought: I need to look up who Leo DiCaprio's current girlfriend is.\nAction: \n{\n \"action\": \"Web Search\",\n \"action_input\": \"Who is Leonardo DiCaprio's current girlfriend?\"\n}\n"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"mrkl.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 13,
|
|
|
|
|
"id": "a5c07010",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
|
|
|
|
"\u001b[32;1m\u001b[1;3mQuestion: What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
|
|
|
|
|
"Thought: I should use the Search tool to find the answer to the first part of the question and then use the FooBar DB tool to find the answer to the second part.\n",
|
|
|
|
|
"Action:\n",
|
|
|
|
|
"```\n",
|
|
|
|
|
"{\n",
|
|
|
|
|
" \"action\": \"Search\",\n",
|
|
|
|
|
" \"action_input\": \"Who recently released an album called 'The Storm Before the Calm'\"\n",
|
|
|
|
|
"}\n",
|
|
|
|
|
"```\n",
|
|
|
|
|
"\u001b[0m\n",
|
|
|
|
|
"Observation: \u001b[36;1m\u001b[1;3mAlanis Morissette\u001b[0m\n",
|
|
|
|
|
"Thought:\u001b[32;1m\u001b[1;3mNow that I know the artist's name, I can use the FooBar DB tool to find out if they are in the database and what albums of theirs are in it.\n",
|
|
|
|
|
"Action:\n",
|
|
|
|
|
"```\n",
|
|
|
|
|
"{\n",
|
|
|
|
|
" \"action\": \"FooBar DB\",\n",
|
|
|
|
|
" \"action_input\": \"What albums does Alanis Morissette have in the database?\"\n",
|
|
|
|
|
"}\n",
|
|
|
|
|
"```\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"\u001b[0m\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
|
|
|
|
|
"What albums does Alanis Morissette have in the database?\n",
|
|
|
|
|
"SQLQuery:"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "stderr",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"/Users/harrisonchase/workplace/langchain/langchain/sql_database.py:191: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
|
|
|
|
|
" sample_rows = connection.execute(command)\n"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"\u001b[32;1m\u001b[1;3m SELECT \"Title\" FROM \"Album\" WHERE \"ArtistId\" IN (SELECT \"ArtistId\" FROM \"Artist\" WHERE \"Name\" = 'Alanis Morissette') LIMIT 5;\u001b[0m\n",
|
|
|
|
|
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
|
|
|
|
|
"Answer:\u001b[32;1m\u001b[1;3m Alanis Morissette has the album Jagged Little Pill in the database.\u001b[0m\n",
|
|
|
|
|
"\u001b[1m> Finished chain.\u001b[0m\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"Observation: \u001b[38;5;200m\u001b[1;3m Alanis Morissette has the album Jagged Little Pill in the database.\u001b[0m\n",
|
|
|
|
|
"Thought:\u001b[32;1m\u001b[1;3mThe artist Alanis Morissette is in the FooBar database and has the album Jagged Little Pill in it.\n",
|
|
|
|
|
"Final Answer: Alanis Morissette is in the FooBar database and has the album Jagged Little Pill in it.\u001b[0m\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"'Alanis Morissette is in the FooBar database and has the album Jagged Little Pill in it.'"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"execution_count": 13,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"mrkl.run(\"What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": null,
|
|
|
|
|
"id": "af016a70",
|
|
|
|
|
"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
|
|
|
|
|
}
|
