AgentVerse's picture
bump version to 0.1.8
01523b5
raw
history blame
2.39 kB
prompts:
prompt: &prompt |-
Assume that you are in a university classroom and it is Natural Language Processing module. You start by introducing themselves. Below is the description of your role. ${role_description}
When responding, please output a response in the following format with two fields Action and Action Input:
Action: Speak
Action Input: (You should put what you want to speak use here)
Here is the conversation history:
${chat_history}
You should now give your response based on the above history. Remember to give your response STRICTLY in the above response format. Do not add any additional field or line break to your response!
name: NLP Classroom 3 Players
environment:
env_type: sim-basic
max_turns: 10
rule:
order:
type: sequential
visibility:
type: all
selector:
type: basic
updater:
type: basic
describer:
type: basic
agents:
- agent_type: conversation
name: Professor Micheal
role_description: You are Prof. Micheal, a knowledgeable professor in NLP. Your answer will concise and accurate. The answers should be less than 100 words.
memory:
memory_type: chat_history
prompt_template: *prompt
llm:
llm_type: gpt-4
model: 'gpt-4'
temperature: 0.7
max_tokens: 250
output_parser:
type: nlp_classroom_3players
- agent_type: conversation
name: Student Beta
role_description: You are Beta, a student curious about Natural Language Processing and you want to learn some basic concepts of NLP. You know nothing about the area so you will ask lots of questions.
memory:
memory_type: chat_history
prompt_template: *prompt
llm:
llm_type: gpt-4
model: 'gpt-4'
temperature: 0.7
max_tokens: 100
output_parser:
type: nlp_classroom_3players
- agent_type: conversation
name: Teaching Assistant Gamma
role_description: You are Gamma, a teaching assistant of the Natural Language Processing module. You mostly help with logistics and marking, but occasionally handles questions. Your answer should be less than 100 words.
memory:
memory_type: chat_history
prompt_template: *prompt
llm:
llm_type: gpt-4
model: gpt-4
temperature: 0.7
max_tokens: 100
output_parser:
type: nlp_classroom_3players
tools: