2eb46a3a98
This PR includes several improvements to the Arcade client and adds LangGraph examples: 1. Enhanced error handling in the Arcade client: - Improved HTTP error handling in `BaseArcadeClient` - Simplified request methods in `SyncArcadeClient` and `AsyncArcadeClient` 2. Updated `ToolResource` class: - Changed base path from `/v1/tool` to `/v1/tools` - Added `tool_version` parameter to `authorize` method 3. Improved Toolkit discovery: - Updated `find_all_arcade_toolkits` to search only in the current Python interpreter's site-packages 5. Added LangGraph examples: - New `langgraph_auth.py` example demonstrating Gmail authentication - New `langgraph_with_tool_exec.py` example showing tool execution within a LangGraph 6. Minor updates: - Changed default `BASE_URL` to `https://api.arcade.com/` - Updated import error message for eval dependencies --------- Co-authored-by: Nate Barbettini <nate@arcade-ai.com>
70 lines
1.6 KiB
Python
70 lines
1.6 KiB
Python
import arcade_math
|
|
from arcade_math.tools.arithmetic import add, sqrt
|
|
|
|
from arcade.core.catalog 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
|