### Overview Major restructuring from monolithic `arcade-ai` package to modular library architecture with standardized uv-based dependency management.  ### New Package Structure - **`arcade-tdk`** - Lightweight toolkit development kit (core decorators, auth) - **`arcade-core`** - Core execution engine and catalog functionality - **`arcade-serve`** - FastAPI/MCP server components - **`arcade-ai`** - Meta package that includes CLI functionality. Optionally include evals via the `evals` extra. Optionally include all packages via the `all` extra. ### Key Benefits - **Lighter Dependencies**: Toolkits now depend only on `arcade-tdk` (~2 deps) vs full `arcade-ai` (~30+ deps) - **Faster Builds**: uv provides 10-100x faster dependency resolution and installation - **Better Modularity**: Clear separation of concerns, consumers import only what they need - **Standard Tooling**: Eliminates custom poetry scripts, uses standard Python packaging ### Migration Impact - All 20 toolkits converted from poetry → uv with `arcade-tdk` dependencies plus `arcade-ai[evals]` and `arcade-serve` dev dependencies. When developing locally, devs should install toolkits via `make install-local`. - Modern Python 3.10+ type hints throughout - Standardized build system with hatchling backend - Enhanced Makefile with robust toolkit management commands - Removed `arcade dev` CLI command - Reduce the number of files created by `arcade new` and add an option to not generate a tests and evals folder. This foundation enables faster development cycles and cleaner dependency chains for the growing toolkit ecosystem. ### Todo After this PR is merged - [ ] Post-merge workflow(s) (release & publish containers, etc) - [ ] Release order plan. @EricGustin suggests releasing in the following order: 1. `arcade-core` version 0.1.0 2. `arcade-serve` version 0.1.0 and `arcade-tdk` version 0.1.0 3. `arcade-ai` version 2.0.0 4. Patch release for all toolkits (all changes in toolkits are internal refactors) - [ ] [Update docs](https://github.com/ArcadeAI/docs/pull/318) --------- Co-authored-by: Eric Gustin <eric@arcade.dev> Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
94 lines
3.3 KiB
Python
94 lines
3.3 KiB
Python
from arcade_evals import (
|
|
BinaryCritic,
|
|
EvalRubric,
|
|
EvalSuite,
|
|
ExpectedToolCall,
|
|
SimilarityCritic,
|
|
tool_eval,
|
|
)
|
|
from arcade_tdk import ToolCatalog
|
|
|
|
from arcade_microsoft.outlook_calendar import create_event
|
|
|
|
# Evaluation rubric
|
|
rubric = EvalRubric(
|
|
fail_threshold=0.9,
|
|
warn_threshold=0.95,
|
|
)
|
|
|
|
catalog = ToolCatalog()
|
|
catalog.add_tool(create_event, "Microsoft")
|
|
|
|
|
|
@tool_eval()
|
|
def outlook_calendar_create_event_eval_suite() -> EvalSuite:
|
|
"""Create an evaluation suite for Outlook Calendar create event tool."""
|
|
suite = EvalSuite(
|
|
name="Outlook Calendar Create Event Evaluation",
|
|
system_message=(
|
|
"You are an AI that has access to tools to view and manage calendar events. "
|
|
"The current time date and time is April 25, 2025, 5:18 PM PST."
|
|
),
|
|
catalog=catalog,
|
|
rubric=rubric,
|
|
)
|
|
|
|
suite.add_case(
|
|
name="Create virtual event",
|
|
user_message=(
|
|
"schedule a virtual team meeting 'Standup' tomorrow at 3pm for 1 hour. "
|
|
"john@example.com and sarah@example.com need to be there"
|
|
),
|
|
expected_tool_calls=[
|
|
ExpectedToolCall(
|
|
func=create_event,
|
|
args={
|
|
"subject": "Standup",
|
|
"start_date_time": "2025-04-26T15:00:00",
|
|
"end_date_time": "2025-04-26T16:00:00",
|
|
"attendee_emails": ["john@example.com", "sarah@example.com"],
|
|
"is_online_meeting": True,
|
|
},
|
|
)
|
|
],
|
|
critics=[
|
|
SimilarityCritic(critic_field="subject", weight=1 / 5),
|
|
BinaryCritic(critic_field="start_date_time", weight=1 / 5),
|
|
BinaryCritic(critic_field="end_date_time", weight=1 / 5),
|
|
BinaryCritic(critic_field="attendee_emails", weight=1 / 5),
|
|
BinaryCritic(critic_field="is_online_meeting", weight=1 / 5),
|
|
],
|
|
)
|
|
|
|
suite.add_case(
|
|
name="Create event with physical location and virtual link",
|
|
user_message=(
|
|
"schedule a team meeting 'All hands' tomorrow at 3pm for 1 hour. "
|
|
"john@example.com and sarah@example.com need to be there. "
|
|
"The meeting will be in Conference Room A, but there will be a virtual link "
|
|
"for those who cannot attend in person."
|
|
),
|
|
expected_tool_calls=[
|
|
ExpectedToolCall(
|
|
func=create_event,
|
|
args={
|
|
"subject": "All hands",
|
|
"start_date_time": "2025-04-26T15:00:00",
|
|
"end_date_time": "2025-04-26T16:00:00",
|
|
"location": "Conference Room A",
|
|
"attendee_emails": ["john@example.com", "sarah@example.com"],
|
|
"is_online_meeting": True,
|
|
},
|
|
)
|
|
],
|
|
critics=[
|
|
SimilarityCritic(critic_field="subject", weight=1 / 6),
|
|
BinaryCritic(critic_field="start_date_time", weight=1 / 6),
|
|
BinaryCritic(critic_field="end_date_time", weight=1 / 6),
|
|
SimilarityCritic(critic_field="location", weight=1 / 6),
|
|
BinaryCritic(critic_field="attendee_emails", weight=1 / 6),
|
|
BinaryCritic(critic_field="is_online_meeting", weight=1 / 6),
|
|
],
|
|
)
|
|
|
|
return suite
|