mirror of
https://github.com/hwchase17/langchain.git
synced 2025-07-05 12:48:12 +00:00
add xml agent notebook
This commit is contained in:
Harrison Chase
parent
a8be207ea3
commit
893f3014af
@ -1,274 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "9926203f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
|
||||
"os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
|
||||
"os.environ[\"LANGCHAIN_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "45bc4149",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_instructions = \"\"\"You are a helpful assistant. Help the user answer any questions.\n",
|
||||
"\n",
|
||||
"You have access to the following tools:\n",
|
||||
"\n",
|
||||
"{tools}\n",
|
||||
"\n",
|
||||
"In order to use a tool, you can use <tool></tool> and <tool_input></tool_input> tags. \\\n",
|
||||
"You will then get back a response in the form <observation></observation>\n",
|
||||
"For example, if you have a tool called 'search' that could run a google search, in order to search for the weather in SF you would respond:\n",
|
||||
"\n",
|
||||
"<tool>search</tool><tool_input>weather in SF</tool_input>\n",
|
||||
"<observation>64 degrees</observation>\n",
|
||||
"\n",
|
||||
"When you are done, respond with a final answer between <final_answer></final_answer>. For example:\n",
|
||||
"\n",
|
||||
"<final_answer>The weather in SF is 64 degrees</final_answer>\n",
|
||||
"\n",
|
||||
"Begin!\n",
|
||||
"\n",
|
||||
"Question: {question}\"\"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "4da4c0d2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.6.14) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
|
||||
" warnings.warn(\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatAnthropic\n",
|
||||
"from langchain.prompts import ChatPromptTemplate, AIMessagePromptTemplate\n",
|
||||
"from langchain.agents import tool"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "b81e9120",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = ChatAnthropic(model=\"claude-2\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "5271f612",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt_template = ChatPromptTemplate.from_template(agent_instructions) + AIMessagePromptTemplate.from_template(\"{intermediate_steps}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "83780d81",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = prompt_template | model.bind(stop=[\"</tool_input>\", \"</final_answer>\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "c091d0e1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"@tool\n",
|
||||
"def search(query: str) -> str:\n",
|
||||
" \"\"\"Search things about current events.\"\"\"\n",
|
||||
" return \"32 degrees\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "1e81b05d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool_list = [search]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "5f0d986f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import Tool, AgentExecutor, BaseSingleActionAgent\n",
|
||||
"from typing import List, Tuple, Any, Union\n",
|
||||
"from langchain.schema import AgentAction, AgentFinish\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"class AnthropicAgent(BaseSingleActionAgent):\n",
|
||||
" \n",
|
||||
" tools: List[Tool]\n",
|
||||
" chain: Any\n",
|
||||
"\n",
|
||||
" @property\n",
|
||||
" def input_keys(self):\n",
|
||||
" return [\"input\"]\n",
|
||||
"\n",
|
||||
" def plan(\n",
|
||||
" self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
|
||||
" ) -> Union[AgentAction, AgentFinish]:\n",
|
||||
" \"\"\"Given input, decided what to do.\n",
|
||||
"\n",
|
||||
" Args:\n",
|
||||
" intermediate_steps: Steps the LLM has taken to date,\n",
|
||||
" along with observations\n",
|
||||
" **kwargs: User inputs.\n",
|
||||
"\n",
|
||||
" Returns:\n",
|
||||
" Action specifying what tool to use.\n",
|
||||
" \"\"\"\n",
|
||||
" log = \"\"\n",
|
||||
" for action, observation in intermediate_steps:\n",
|
||||
" log += f\"<tool>{action.tool}</tool><tool_input>{action.tool_input}</tool_input><observation>{observation}</observation>\"\n",
|
||||
" tools = \"\"\n",
|
||||
" for tool in self.tools:\n",
|
||||
" tools += f\"{tool.name}: {tool.description}\\n\"\n",
|
||||
" response = self.chain.invoke({\"intermediate_steps\": log, \"tools\": tools, \"question\": kwargs[\"input\"]})\n",
|
||||
" if \"</tool>\" in response.content:\n",
|
||||
" t, ti = response.content.split(\"</tool>\")\n",
|
||||
" _t = t.split(\"<tool>\")[1]\n",
|
||||
" _ti = ti.split(\"<tool_input>\")[1]\n",
|
||||
" return AgentAction(tool=_t, tool_input=_ti, log=response.content)\n",
|
||||
" elif \"<final_answer>\" in response.content:\n",
|
||||
" t, ti = response.content.split(\"<final_answer>\")\n",
|
||||
" return AgentFinish(return_values={\"output\": ti}, log=response.content)\n",
|
||||
" else:\n",
|
||||
" raise ValueError\n",
|
||||
"\n",
|
||||
" async def aplan(\n",
|
||||
" self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
|
||||
" ) -> Union[AgentAction, AgentFinish]:\n",
|
||||
" \"\"\"Given input, decided what to do.\n",
|
||||
"\n",
|
||||
" Args:\n",
|
||||
" intermediate_steps: Steps the LLM has taken to date,\n",
|
||||
" along with observations\n",
|
||||
" **kwargs: User inputs.\n",
|
||||
"\n",
|
||||
" Returns:\n",
|
||||
" Action specifying what tool to use.\n",
|
||||
" \"\"\"\n",
|
||||
" raise ValueError"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "315361c5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = AnthropicAgent(tools=tool_list, chain=chain)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "bca6096f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tool_list, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "71b872b1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m <tool>search</tool>\n",
|
||||
"<tool_input>weather in new york\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"<final_answer>The weather in New York is 32 degrees\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The weather in New York is 32 degrees'"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"whats the weather in New york?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cca87246",
|
||||
"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
|
||||
}
|
||||
149
docs/extras/modules/agents/agent_types/xml_agent.ipynb
Normal file
149
docs/extras/modules/agents/agent_types/xml_agent.ipynb
Normal file
@ -0,0 +1,149 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3c284df8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# XML Agent\n",
|
||||
"\n",
|
||||
"Some language models (like Anthropic's Claude) are particularly good at reasoning/writing XML. This goes over how to use an agent that uses XML when prompting. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "f9d2ead2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import XMLAgent, tool, AgentExecutor\n",
|
||||
"from langchain.chat_models import ChatAnthropic\n",
|
||||
"from langchain.chains import LLMChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "ebadf04f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = ChatAnthropic(model=\"claude-2\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "6ce9f9a5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"@tool\n",
|
||||
"def search(query: str) -> str:\n",
|
||||
" \"\"\"Search things about current events.\"\"\"\n",
|
||||
" return \"32 degrees\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "c589944e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool_list = [search]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "2d8454be",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = LLMChain(\n",
|
||||
" llm=model,\n",
|
||||
" prompt=XMLAgent.get_default_prompt(),\n",
|
||||
" output_parser=XMLAgent.get_default_output_parser()\n",
|
||||
")\n",
|
||||
"agent = XMLAgent(tools=tool_list, llm_chain=chain)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "bca6096f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tool_list, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "71b872b1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m <tool>search</tool>\n",
|
||||
"<tool_input>weather in New York\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"<final_answer>The weather in New York is 32 degrees\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The weather in New York is 32 degrees'"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.run(\"whats the weather in New york?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cca87246",
|
||||
"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
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user