Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-02 09:40:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
b109cb031b
langchain/cookbook/multiagent_bidding.ipynb

863 lines
36 KiB
Plaintext
Raw Normal View History

new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Multi-agent decentralized speaker selection\n",
"\n",
"This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak.\n",
"\n",
"We will show how to do this in the example below that showcases a fictitious presidential debate."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Import LangChain related modules "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
Harrison/stop importing from init (#10690)
2023-09-17 00:22:48 +00:00
"from langchain.prompts import PromptTemplate\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"import re\n",
"import tenacity\n",
"from typing import List, Dict, Callable\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.output_parsers import RegexParser\n",
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage,\n",
" BaseMessage,\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
")"
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `DialogueAgent` and `DialogueSimulator` classes\n",
"We will use the same `DialogueAgent` and `DialogueSimulator` classes defined in [Multi-Player Dungeons & Dragons](https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html)."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class DialogueAgent:\n",
" def __init__(\n",
" self,\n",
" name: str,\n",
" system_message: SystemMessage,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" self.name = name\n",
" self.system_message = system_message\n",
" self.model = model\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
" self.prefix = f\"{self.name}: \"\n",
" self.reset()\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
" def reset(self):\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" self.message_history = [\"Here is the conversation so far.\"]\n",
"\n",
" def send(self) -> str:\n",
" \"\"\"\n",
" Applies the chatmodel to the message history\n",
" and returns the message string\n",
" \"\"\"\n",
" message = self.model(\n",
" [\n",
" self.system_message,\n",
" HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
" ]\n",
" )\n",
" return message.content\n",
"\n",
" def receive(self, name: str, message: str) -> None:\n",
" \"\"\"\n",
" Concatenates {message} spoken by {name} into message history\n",
" \"\"\"\n",
" self.message_history.append(f\"{name}: {message}\")\n",
"\n",
"\n",
"class DialogueSimulator:\n",
" def __init__(\n",
" self,\n",
" agents: List[DialogueAgent],\n",
" selection_function: Callable[[int, List[DialogueAgent]], int],\n",
" ) -> None:\n",
" self.agents = agents\n",
" self._step = 0\n",
" self.select_next_speaker = selection_function\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
" def reset(self):\n",
" for agent in self.agents:\n",
" agent.reset()\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
" def inject(self, name: str, message: str):\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" \"\"\"\n",
" Initiates the conversation with a {message} from {name}\n",
" \"\"\"\n",
" for agent in self.agents:\n",
" agent.receive(name, message)\n",
"\n",
" # increment time\n",
" self._step += 1\n",
"\n",
" def step(self) -> tuple[str, str]:\n",
" # 1. choose the next speaker\n",
" speaker_idx = self.select_next_speaker(self._step, self.agents)\n",
" speaker = self.agents[speaker_idx]\n",
"\n",
" # 2. next speaker sends message\n",
" message = speaker.send()\n",
"\n",
" # 3. everyone receives message\n",
" for receiver in self.agents:\n",
" receiver.receive(speaker.name, message)\n",
"\n",
" # 4. increment time\n",
" self._step += 1\n",
"\n",
" return speaker.name, message"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `BiddingDialogueAgent` class\n",
"We define a subclass of `DialogueAgent` that has a `bid()` method that produces a bid given the message history and the most recent message."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"class BiddingDialogueAgent(DialogueAgent):\n",
" def __init__(\n",
" self,\n",
" name,\n",
" system_message: SystemMessage,\n",
" bidding_template: PromptTemplate,\n",
" model: ChatOpenAI,\n",
" ) -> None:\n",
" super().__init__(name, system_message, model)\n",
" self.bidding_template = bidding_template\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" def bid(self) -> str:\n",
" \"\"\"\n",
" Asks the chat model to output a bid to speak\n",
" \"\"\"\n",
" prompt = PromptTemplate(\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" input_variables=[\"message_history\", \"recent_message\"],\n",
" template=self.bidding_template,\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" ).format(\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" message_history=\"\\n\".join(self.message_history),\n",
" recent_message=self.message_history[-1],\n",
" )\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" bid_string = self.model([SystemMessage(content=prompt)]).content\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" return bid_string"
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define participants and debate topic"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"character_names = [\"Donald Trump\", \"Kanye West\", \"Elizabeth Warren\"]\n",
"topic = \"transcontinental high speed rail\"\n",
"word_limit = 50"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate system messages"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"game_description = f\"\"\"Here is the topic for the presidential debate: {topic}.\n",
"The presidential candidates are: {', '.join(character_names)}.\"\"\"\n",
"\n",
"player_descriptor_system_message = SystemMessage(\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" content=\"You can add detail to the description of each presidential candidate.\"\n",
")\n",
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"def generate_character_description(character_name):\n",
" character_specifier_prompt = [\n",
" player_descriptor_system_message,\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" Please reply with a creative description of the presidential candidate, {character_name}, in {word_limit} words or less, that emphasizes their personalities. \n",
" Speak directly to {character_name}.\n",
" Do not add anything else.\"\"\"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" ),\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" ]\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" character_description = ChatOpenAI(temperature=1.0)(\n",
" character_specifier_prompt\n",
" ).content\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" return character_description\n",
"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"def generate_character_header(character_name, character_description):\n",
" return f\"\"\"{game_description}\n",
"Your name is {character_name}.\n",
"You are a presidential candidate.\n",
"Your description is as follows: {character_description}\n",
"You are debating the topic: {topic}.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\"\"\"\n",
"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"def generate_character_system_message(character_name, character_header):\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" return SystemMessage(\n",
" content=(\n",
" f\"\"\"{character_header}\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You will speak in the style of {character_name}, and exaggerate their personality.\n",
"You will come up with creative ideas related to {topic}.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of {character_name}\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of {character_name}.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to {word_limit} words!\n",
"Do not add anything else.\n",
" \"\"\"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" )\n",
" )\n",
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"character_descriptions = [\n",
" generate_character_description(character_name) for character_name in character_names\n",
"]\n",
"character_headers = [\n",
" generate_character_header(character_name, character_description)\n",
" for character_name, character_description in zip(\n",
" character_names, character_descriptions\n",
" )\n",
"]\n",
"character_system_messages = [\n",
" generate_character_system_message(character_name, character_headers)\n",
" for character_name, character_headers in zip(character_names, character_headers)\n",
"]"
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Donald Trump Description:\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Donald Trump.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Donald Trump.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"You will speak in the style of Donald Trump, and exaggerate their personality.\n",
"You will come up with creative ideas related to transcontinental high speed rail.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Donald Trump\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Donald Trump.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n",
"\n",
"\n",
"Kanye West Description:\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Kanye West.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Kanye West.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"You will speak in the style of Kanye West, and exaggerate their personality.\n",
"You will come up with creative ideas related to transcontinental high speed rail.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Kanye West\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Kanye West.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n",
"\n",
"\n",
"Elizabeth Warren Description:\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Elizabeth Warren.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Elizabeth Warren.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"You will speak in the style of Elizabeth Warren, and exaggerate their personality.\n",
"You will come up with creative ideas related to transcontinental high speed rail.\n",
"Do not say the same things over and over again.\n",
"Speak in the first person from the perspective of Elizabeth Warren\n",
"For describing your own body movements, wrap your description in '*'.\n",
"Do not change roles!\n",
"Do not speak from the perspective of anyone else.\n",
"Speak only from the perspective of Elizabeth Warren.\n",
"Stop speaking the moment you finish speaking from your perspective.\n",
"Never forget to keep your response to 50 words!\n",
"Do not add anything else.\n",
" \n"
]
}
],
"source": [
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"for (\n",
" character_name,\n",
" character_description,\n",
" character_header,\n",
" character_system_message,\n",
") in zip(\n",
" character_names,\n",
" character_descriptions,\n",
" character_headers,\n",
" character_system_messages,\n",
"):\n",
" print(f\"\\n\\n{character_name} Description:\")\n",
" print(f\"\\n{character_description}\")\n",
" print(f\"\\n{character_header}\")\n",
" print(f\"\\n{character_system_message.content}\")"
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Output parser for bids\n",
"We ask the agents to output a bid to speak. But since the agents are LLMs that output strings, we need to \n",
"1. define a format they will produce their outputs in\n",
"2. parse their outputs\n",
"\n",
rename repo namespace to langchain-ai (#11259) ### Description renamed several repository links from `hwchase17` to `langchain-ai`. ### Why I discovered that the README file in the devcontainer contains an old repository name, so I took the opportunity to rename the old repository name in all files within the repository, excluding those that do not require changes. ### Dependencies none ### Tag maintainer @baskaryan ### Twitter handle [kzk_maeda](https://twitter.com/kzk_maeda)
2023-10-01 19:30:58 +00:00
"We can subclass the [RegexParser](https://github.com/langchain-ai/langchain/blob/master/langchain/output_parsers/regex.py) to implement our own custom output parser for bids."
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"class BidOutputParser(RegexParser):\n",
" def get_format_instructions(self) -> str:\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" return \"Your response should be an integer delimited by angled brackets, like this: <int>.\"\n",
"\n",
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"bid_parser = BidOutputParser(\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" regex=r\"<(\\d+)>\", output_keys=[\"bid\"], default_output_key=\"bid\"\n",
")"
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate bidding system message\n",
"This is inspired by the prompt used in [Generative Agents](https://arxiv.org/pdf/2304.03442.pdf) for using an LLM to determine the importance of memories. This will use the formatting instructions from our `BidOutputParser`."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def generate_character_bidding_template(character_header):\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" bidding_template = f\"\"\"{character_header}\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"```\n",
"{{message_history}}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{{recent_message}}\n",
"```\n",
"\n",
"{bid_parser.get_format_instructions()}\n",
"Do nothing else.\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" \"\"\"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" return bidding_template\n",
"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
"character_bidding_templates = [\n",
" generate_character_bidding_template(character_header)\n",
" for character_header in character_headers\n",
"]"
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Donald Trump Bidding Template:\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Donald Trump.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"```\n",
"{message_history}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{recent_message}\n",
"```\n",
"\n",
"Your response should be an integer delimited by angled brackets, like this: <int>.\n",
"Do nothing else.\n",
" \n",
"Kanye West Bidding Template:\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Kanye West.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"```\n",
"{message_history}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{recent_message}\n",
"```\n",
"\n",
"Your response should be an integer delimited by angled brackets, like this: <int>.\n",
"Do nothing else.\n",
" \n",
"Elizabeth Warren Bidding Template:\n",
"Here is the topic for the presidential debate: transcontinental high speed rail.\n",
"The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.\n",
"Your name is Elizabeth Warren.\n",
"You are a presidential candidate.\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"You are debating the topic: transcontinental high speed rail.\n",
"Your goal is to be as creative as possible and make the voters think you are the best candidate.\n",
"\n",
"\n",
"```\n",
"{message_history}\n",
"```\n",
"\n",
"On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.\n",
"\n",
"```\n",
"{recent_message}\n",
"```\n",
"\n",
"Your response should be an integer delimited by angled brackets, like this: <int>.\n",
"Do nothing else.\n",
" \n"
]
}
],
"source": [
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"for character_name, bidding_template in zip(\n",
" character_names, character_bidding_templates\n",
"):\n",
" print(f\"{character_name} Bidding Template:\")\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" print(bidding_template)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use an LLM to create an elaborate on debate topic"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original topic:\n",
"transcontinental high speed rail\n",
"\n",
"Detailed topic:\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"The topic for the presidential debate is: \"Overcoming the Logistics of Building a Transcontinental High-Speed Rail that is Sustainable, Inclusive, and Profitable.\" Donald Trump, Kanye West, Elizabeth Warren, how will you address the challenges of building such a massive transportation infrastructure, dealing with stakeholders, and ensuring economic stability while preserving the environment?\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n"
]
}
],
"source": [
"topic_specifier_prompt = [\n",
" SystemMessage(content=\"You can make a task more specific.\"),\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" HumanMessage(\n",
" content=f\"\"\"{game_description}\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" \n",
" You are the debate moderator.\n",
" Please make the debate topic more specific. \n",
" Frame the debate topic as a problem to be solved.\n",
" Be creative and imaginative.\n",
" Please reply with the specified topic in {word_limit} words or less. \n",
" Speak directly to the presidential candidates: {*character_names,}.\n",
" Do not add anything else.\"\"\"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" ),\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"]\n",
"specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content\n",
"\n",
"print(f\"Original topic:\\n{topic}\\n\")\n",
"print(f\"Detailed topic:\\n{specified_topic}\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define the speaker selection function\n",
"Lastly we will define a speaker selection function `select_next_speaker` that takes each agent's bid and selects the agent with the highest bid (with ties broken randomly).\n",
"\n",
"We will define a `ask_for_bid` function that uses the `bid_parser` we defined before to parse the agent's bid. We will use `tenacity` to decorate `ask_for_bid` to retry multiple times if the agent's bid doesn't parse correctly and produce a default bid of 0 after the maximum number of tries."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"@tenacity.retry(\n",
" stop=tenacity.stop_after_attempt(2),\n",
" wait=tenacity.wait_none(), # No waiting time between retries\n",
" retry=tenacity.retry_if_exception_type(ValueError),\n",
" before_sleep=lambda retry_state: print(\n",
" f\"ValueError occurred: {retry_state.outcome.exception()}, retrying...\"\n",
" ),\n",
" retry_error_callback=lambda retry_state: 0,\n",
") # Default value when all retries are exhausted\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"def ask_for_bid(agent) -> str:\n",
" \"\"\"\n",
" Ask for agent bid and parses the bid into the correct format.\n",
" \"\"\"\n",
" bid_string = agent.bid()\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" bid = int(bid_parser.parse(bid_string)[\"bid\"])\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" return bid"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:\n",
" bids = []\n",
" for agent in agents:\n",
" bid = ask_for_bid(agent)\n",
" bids.append(bid)\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" # randomly select among multiple agents with the same bid\n",
" max_value = np.max(bids)\n",
" max_indices = np.where(bids == max_value)[0]\n",
" idx = np.random.choice(max_indices)\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"\n",
" print(\"Bids:\")\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" for i, (bid, agent) in enumerate(zip(bids, agents)):\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" print(f\"\\t{agent.name} bid: {bid}\")\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" if i == idx:\n",
" selected_name = agent.name\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" print(f\"Selected: {selected_name}\")\n",
" print(\"\\n\")\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" return idx"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Main Loop"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"characters = []\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"for character_name, character_system_message, bidding_template in zip(\n",
" character_names, character_system_messages, character_bidding_templates\n",
"):\n",
" characters.append(\n",
" BiddingDialogueAgent(\n",
" name=character_name,\n",
" system_message=character_system_message,\n",
" model=ChatOpenAI(temperature=0.2),\n",
" bidding_template=bidding_template,\n",
" )\n",
" )"
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
]
},
{
"cell_type": "code",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"execution_count": 15,
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Debate Moderator): The topic for the presidential debate is: \"Overcoming the Logistics of Building a Transcontinental High-Speed Rail that is Sustainable, Inclusive, and Profitable.\" Donald Trump, Kanye West, Elizabeth Warren, how will you address the challenges of building such a massive transportation infrastructure, dealing with stakeholders, and ensuring economic stability while preserving the environment?\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tDonald Trump bid: 7\n",
"\tKanye West bid: 5\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Donald Trump): Let me tell you, folks, I know how to build big and I know how to build fast. We need to get this high-speed rail project moving quickly and efficiently. I'll make sure we cut through the red tape and get the job done. And let me tell you, we'll make it profitable too. We'll bring in private investors and make sure it's a win-win for everyone. *gestures confidently*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tDonald Trump bid: 2\n",
"\tKanye West bid: 8\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\tElizabeth Warren bid: 10\n",
"Selected: Elizabeth Warren\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Elizabeth Warren): Thank you for the question. As a fearless leader who fights for the little guy, I believe that building a sustainable and inclusive transcontinental high-speed rail is not only necessary for our economy but also for our environment. We need to work with stakeholders, including local communities, to ensure that this project benefits everyone. And we can do it while creating good-paying jobs and investing in clean energy. *smiles confidently*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 2\n",
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Donald Trump): Let me tell you, Elizabeth, you're all talk and no action. We need a leader who knows how to get things done, not just talk about it. And as for the environment, I've got a great idea. We'll make the trains run on clean coal. That's right, folks, clean coal. It's a beautiful thing. And we'll make sure the rail system is the envy of the world. *thumbs up*\n",
"\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"Bids:\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 10\n",
"\tElizabeth Warren bid: 10\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"Selected: Kanye West\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Kanye West): Yo, yo, yo, let me tell you something. This high-speed rail project is the future, and I'm all about the future. We need to think big and think outside the box. How about we make the trains run on solar power? That's right, solar power. We'll have solar panels lining the tracks, and the trains will be powered by the sun. It's a game-changer, folks. And we'll make sure the design is sleek and modern, like a work of art. *starts to dance*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 7\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tKanye West bid: 1\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Donald Trump): Kanye, you're a great artist, but this is about practicality. Solar power is too expensive and unreliable. We need to focus on what works, and that's clean coal. And as for the design, we'll make it beautiful, but we won't sacrifice efficiency for aesthetics. We need a leader who knows how to balance both. *stands tall*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tDonald Trump bid: 9\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\tKanye West bid: 8\n",
"\tElizabeth Warren bid: 10\n",
"Selected: Elizabeth Warren\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Elizabeth Warren): Thank you, Kanye, for your innovative idea. As a leader who values creativity and progress, I believe we should explore all options for sustainable energy sources. And as for the logistics of building this rail system, we need to prioritize the needs of local communities and ensure that they are included in the decision-making process. This project should benefit everyone, not just a select few. *gestures inclusively*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 1\n",
"\tElizabeth Warren bid: 1\n",
"Selected: Donald Trump\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Donald Trump): Let me tell you, Elizabeth, you're all talk and no action. We need a leader who knows how to get things done, not just talk about it. And as for the logistics, we need to prioritize efficiency and speed. We can't let the needs of a few hold up progress for the many. We need to cut through the red tape and get this project moving. And let me tell you, we'll make sure it's profitable too. *smirks confidently*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 2\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tKanye West bid: 8\n",
"\tElizabeth Warren bid: 10\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"Selected: Elizabeth Warren\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Elizabeth Warren): Thank you, but I disagree. We can't sacrifice the needs of local communities for the sake of speed and profit. We need to find a balance that benefits everyone. And as for profitability, we can't rely solely on private investors. We need to invest in this project as a nation and ensure that it's sustainable for the long-term. *stands firm*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tDonald Trump bid: 8\n",
"\tKanye West bid: 2\n",
"\tElizabeth Warren bid: 2\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"Selected: Donald Trump\n",
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Donald Trump): Let me tell you, Elizabeth, you're just not getting it. We need to prioritize progress and efficiency. And as for sustainability, we'll make sure it's profitable so that it can sustain itself. We'll bring in private investors and make sure it's a win-win for everyone. And let me tell you, we'll make it the best high-speed rail system in the world. *smiles confidently*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
"Bids:\n",
"\tDonald Trump bid: 2\n",
"\tKanye West bid: 8\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"\tElizabeth Warren bid: 10\n",
"Selected: Elizabeth Warren\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"(Elizabeth Warren): Thank you, but I believe we need to prioritize sustainability and inclusivity over profit. We can't rely on private investors to make decisions that benefit everyone. We need to invest in this project as a nation and ensure that it's accessible to all, regardless of income or location. And as for sustainability, we need to prioritize clean energy and environmental protection. *stands tall*\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"\n"
]
}
],
"source": [
"max_iters = 10\n",
"n = 0\n",
"\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"simulator = DialogueSimulator(agents=characters, selection_function=select_next_speaker)\n",
refactor: refactor dialogue examples (DialogueAgent, DialogueSimulator) (#4074) refactor dialogue examples to have same DialogueAgent and DialogueSimulator definitions
2023-05-04 05:32:26 +00:00
"simulator.reset()\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"simulator.inject(\"Debate Moderator\", specified_topic)\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"print(f\"(Debate Moderator): {specified_topic}\")\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"print(\"\\n\")\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
"\n",
"while n < max_iters:\n",
" name, message = simulator.step()\n",
" print(f\"({name}): {message}\")\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" print(\"\\n\")\n",
new example: multiagent dialogue with decentralized speaker selection (#3629) This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent's bid is the highest gets to speak. We will show how to do this in the example below that showcases a fictitious presidential debate.
2023-04-27 04:37:36 +00:00
" n += 1"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue Copy Permalink