036ad54ac6
This PR ensures that `arcade.core` does not show up anywhere in "user space". This is crucial for helping developers understand what objects are safe to use, and helps maintain a good developer experience. Specific changes: - `ToolAuthorizationContext` and `ToolContext` are now visible via `arcade.sdk` - `ToolCatalog` is now visible via `arcade.sdk` - `Toolkit` is now visible via `arcade.sdk` - `config` is now visible via `arcade.sdk.config`
68 lines
1.5 KiB
Python
68 lines
1.5 KiB
Python
import arcade_math
|
|
from arcade_math.tools.arithmetic import add, sqrt
|
|
|
|
from arcade.sdk import ToolCatalog
|
|
from arcade.sdk.eval import (
|
|
BinaryCritic,
|
|
EvalRubric,
|
|
EvalSuite,
|
|
tool_eval,
|
|
)
|
|
|
|
# Evaluation rubric
|
|
rubric = EvalRubric(
|
|
fail_threshold=0.85,
|
|
warn_threshold=0.95,
|
|
)
|
|
|
|
|
|
catalog = ToolCatalog()
|
|
catalog.add_module(arcade_math)
|
|
|
|
|
|
@tool_eval()
|
|
def math_eval_suite():
|
|
suite = EvalSuite(
|
|
name="Math Tools Evaluation",
|
|
system_message="You are an AI assistant with access to math tools. Use them to help the user with their math-related tasks.",
|
|
catalog=catalog,
|
|
rubric=rubric,
|
|
)
|
|
|
|
suite.add_case(
|
|
name="Add two large numbers",
|
|
user_message="Add 12345 and 987654321",
|
|
expected_tool_calls=[
|
|
(
|
|
add,
|
|
{
|
|
"a": 12345,
|
|
"b": 987654321,
|
|
},
|
|
)
|
|
],
|
|
rubric=rubric,
|
|
critics=[
|
|
BinaryCritic(critic_field="a", weight=0.5), # TODO: weight should be optional
|
|
BinaryCritic(critic_field="b", weight=0.5),
|
|
],
|
|
)
|
|
|
|
suite.add_case(
|
|
name="Take the square root of a large number",
|
|
user_message="What is the square root of 3224990521?",
|
|
expected_tool_calls=[
|
|
(
|
|
sqrt,
|
|
{
|
|
"a": 3224990521,
|
|
},
|
|
)
|
|
],
|
|
rubric=rubric,
|
|
critics=[
|
|
BinaryCritic(critic_field="a", weight=1.0),
|
|
],
|
|
)
|
|
|
|
return suite
|