Skip to main content

​
final class atoti_ai.AiConfig

Atoti Intelligence configuration.
This feature is experimental, its key is "ai".

​
Example

>>> from atoti_ai import AiConfig
>>> from atoti_ai_amazon_bedrock import (
...     ChatConfig,
...     ConnectionConfig,
... )
>>> with tt.experimental({"ai"}):
...     ai_config = AiConfig(
...         connection=ConnectionConfig(
...             aws_access_key="...",
...             aws_secret_key="...",
...         ),
...         chat=ChatConfig(
...             model="anthropic.claude-3-sonnet-20240229-v1:0",
...         ),
...     )
Atoti Intelligence can also be enabled without configuring an LLM provider by leaving connection and chat to None. AutoExplain then still works but returns a default, non-AI summary, and the chat feature is disabled: 
>>> with tt.experimental({"ai"}):
...     ai_config = AiConfig()

​
chat : ChatConfig | None = None

The configuration of the chat model, or None to not configure any LLM.

​
connection : ConnectionConfig | None = None

The connection to the LLM provider, or None to not configure any LLM.