Human UI

Bitca provides a beautiful Human UI for interacting with your humans.

Human Ambient

Let’s take it for a spin, create a file playground.py

playground.py

from bitca.human import Human
from bitca.model.openai import OpenAIChat
from bitca.storage.human.sqlite import SqlhumanStorage
from bitca.tools.duckduckgo import DuckDuckGo
from bitca.tools.yfinance import YFinanceTools
from bitca.playground import Playground, serve_playground_app

web_human = Human(
    name="Web Human",
    model=OpenAIChat(id="gpt-4o"),
    tools=[DuckDuckGo()],
    instructions=["Always include sources"],
    storage=SqlhumanStorage(table_name="web_human", db_file="humans.db"),
    add_history_to_messages=True,
    markdown=True,
)

finance_human = Human(
    name="Finance Human",
    model=OpenAIChat(id="gpt-4o"),
    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True, company_news=True)],
    instructions=["Use tables to display data"],
    storage=SqlhumanStorage(table_name="finance_human", db_file="humans.db"),
    add_history_to_messages=True,
    markdown=True,
)

app = Ambient(humans=[finance_human, web_human]).get_app()

if __name__ == "__main__":
    serve_ambient_app("ambient:app", reload=True)

Authenticate with bitca

Authenticate with bitca by running the following command:

bitca auth

or by exporting the BITCA_API_KEY for your workspace from bitca.app

MacWindows

setx BITCA_API_KEY bitca-***

Run the playground

Install dependencies and run the Human Ambient:

pip install 'fastapi[standard]' sqlalchemy

python human.py

View the playground

• Open the link provided or navigate to http://projectbit.ca/ambient (login required)

• Select the localhost:7777 endpoint and start chatting with your humans!

Demo Humans

The Human Ambient includes a few demo humans that you can test with. If you have recommendations for other humans we should build, please let us know in the community forum.