mirror of https://github.com/hwchase17/langchain
runnable powered agent (#10407)
parent
6ad6bb46c4
commit
40d9191955
@ -0,0 +1,203 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e89f490d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Agents\n",
|
||||
"\n",
|
||||
"You can pass a Runnable into an agent."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "af4381de",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import XMLAgent, tool, AgentExecutor\n",
|
||||
"from langchain.chat_models import ChatAnthropic"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "24cc8134",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = ChatAnthropic(model=\"claude-2\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "67c0b0e4",
|
||||
"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": 4,
|
||||
"id": "7203b101",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool_list = [search]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "b68e756d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get prompt to use\n",
|
||||
"prompt = XMLAgent.get_default_prompt()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "61ab3e9a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Logic for going from intermediate steps to a string to pass into model\n",
|
||||
"# This is pretty tied to the prompt\n",
|
||||
"def convert_intermediate_steps(intermediate_steps):\n",
|
||||
" log = \"\"\n",
|
||||
" for action, observation in intermediate_steps:\n",
|
||||
" log += (\n",
|
||||
" f\"<tool>{action.tool}</tool><tool_input>{action.tool_input}\"\n",
|
||||
" f\"</tool_input><observation>{observation}</observation>\"\n",
|
||||
" )\n",
|
||||
" return log\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Logic for converting tools to string to go in prompt\n",
|
||||
"def convert_tools(tools):\n",
|
||||
" return \"\\n\".join([f\"{tool.name}: {tool.description}\" for tool in tools])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "260f5988",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Building an agent from a runnable usually involves a few things:\n",
|
||||
"\n",
|
||||
"1. Data processing for the intermediate steps. These need to represented in a way that the language model can recognize them. This should be pretty tightly coupled to the instructions in the prompt\n",
|
||||
"\n",
|
||||
"2. The prompt itself\n",
|
||||
"\n",
|
||||
"3. The model, complete with stop tokens if needed\n",
|
||||
"\n",
|
||||
"4. The output parser - should be in sync with how the prompt specifies things to be formatted."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "e92f1d6f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = (\n",
|
||||
" {\n",
|
||||
" \"question\": lambda x: x[\"question\"],\n",
|
||||
" \"intermediate_steps\": lambda x: convert_intermediate_steps(x[\"intermediate_steps\"])\n",
|
||||
" }\n",
|
||||
" | prompt.partial(tools=convert_tools(tool_list))\n",
|
||||
" | model.bind(stop=[\"</tool_input>\", \"</final_answer>\"])\n",
|
||||
" | XMLAgent.get_default_output_parser()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "6ce6ec7a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tool_list, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "fb5cb2e3",
|
||||
"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": [
|
||||
"{'question': 'whats the weather in New york?',\n",
|
||||
" 'output': 'The weather in New York is 32 degrees'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"question\": \"whats the weather in New york?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bce86dd8",
|
||||
"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": "3.10.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
Loading…
Reference in New Issue