Get Started with TinyTroupe
Visit our GitHub repository to get started with TinyTroupe. You'll find installation instructions, documentation, and examples to help you begin your journey with TinyTroupe.
TinyTroupe is an experimental Python library that allows the simulation of people with specific personalities, interests, and goals. These artificial agents - TinyPersons - can listen to us and one another, reply back, and go about their lives in simulated TinyWorld environments. This is achieved by leveraging the power of Large Language Models (LLMs), notably GPT-4, to generate realistic simulated behavior.
Here are some application ideas to enhance human imagination:
- Advertisement: Evaluate digital ads offline with a simulated audience before spending money on them! 📺
- Software Testing: Provide test input to systems and evaluate the results. 🧪
- Training and exploratory data: Generate realistic synthetic data for training models or opportunity analyses. 📊
- Product and project management: Read project or product proposals and give feedback from the perspective of specific personas. 📋
- Brainstorming: Simulate focus groups and deliver great product feedback at a fraction of the cost! 💡
P.S.: We know Comic Sans is a terrible font choice, except for fun projects like this one! 😜
Some code snippets 👇
{ "type": "TinyPerson", "persona": { "name": "Lisa Carter", "age": 28, "occupation": { "title": "Data Scientist", "organization": "Microsoft" }, "personality": { "traits": [ "You are curious.", "You are analytical.", "You are friendly.", "You don't give up." ] } (...) } }
# Interact with a TinyPerson
lisa.listen_and_act("Tell me about your life.")
# Define a TinyWorld
world = TinyWorld("Chat Room", [lisa, oscar])
world.make_everyone_accessible()
world.run(4)
# Generate a new TinyPerson using TinyPersonFactory
factory = TinyPersonFactory("A hospital in São Paulo.")
person = factory.generate_person("Create a Brazilian doctor who loves pets and nature.")