b6b4cd0a4c
### 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>
111 lines
3 KiB
Python
111 lines
3 KiB
Python
from arcade_evals import (
|
|
BinaryCritic,
|
|
EvalRubric,
|
|
EvalSuite,
|
|
ExpectedToolCall,
|
|
tool_eval,
|
|
)
|
|
from arcade_tdk import ToolCatalog
|
|
|
|
import arcade_confluence
|
|
from arcade_confluence.tools import (
|
|
search_content,
|
|
)
|
|
from evals.critics import ListCritic
|
|
|
|
# Evaluation rubric
|
|
rubric = EvalRubric(
|
|
fail_threshold=0.85,
|
|
warn_threshold=0.95,
|
|
)
|
|
|
|
|
|
catalog = ToolCatalog()
|
|
catalog.add_module(arcade_confluence)
|
|
|
|
|
|
@tool_eval()
|
|
def confluence_search_eval_suite() -> EvalSuite:
|
|
suite = EvalSuite(
|
|
name="Confluence search content tool evaluation",
|
|
system_message="You are an AI assistant with access to Confluence tools.",
|
|
catalog=catalog,
|
|
rubric=rubric,
|
|
)
|
|
|
|
suite.add_case(
|
|
name="Search for content - easy case",
|
|
user_message="Find all pages that contain 'Arcade.dev'",
|
|
expected_tool_calls=[
|
|
ExpectedToolCall(func=search_content, args={"can_contain_any": ["Arcade.dev"]})
|
|
],
|
|
rubric=rubric,
|
|
critics=[
|
|
BinaryCritic(critic_field="can_contain_any", weight=1),
|
|
],
|
|
)
|
|
|
|
suite.add_case(
|
|
name="Search for content - medium case",
|
|
user_message=("Find 20 pages that contain 'Arcade' or 'AI', or 'tool calls'"),
|
|
expected_tool_calls=[
|
|
ExpectedToolCall(
|
|
func=search_content,
|
|
args={
|
|
"can_contain_any": ["Arcade", "AI", "tool calls"],
|
|
"limit": 20,
|
|
},
|
|
)
|
|
],
|
|
rubric=rubric,
|
|
critics=[
|
|
ListCritic(
|
|
critic_field="can_contain_any",
|
|
weight=0.9,
|
|
case_sensitive=False,
|
|
order_matters=False,
|
|
),
|
|
BinaryCritic(critic_field="limit", weight=0.1),
|
|
],
|
|
)
|
|
|
|
suite.add_case(
|
|
name="Search for content - hard case",
|
|
user_message=(
|
|
"Look for 25 databases that have 'How to', "
|
|
"and also have 'carborator' in the content and "
|
|
"also has one of the following: 'money', 'redbull gives you wings', "
|
|
"'honey hole', 'don't snap the pasta!'."
|
|
),
|
|
expected_tool_calls=[
|
|
ExpectedToolCall(
|
|
func=search_content,
|
|
args={
|
|
"must_contain_all": ["carborator", "How to"],
|
|
"can_contain_any": [
|
|
"money",
|
|
"redbull gives you wings",
|
|
"honey hole",
|
|
"don't snap the pasta!",
|
|
],
|
|
},
|
|
),
|
|
],
|
|
rubric=rubric,
|
|
critics=[
|
|
ListCritic(
|
|
critic_field="must_contain_all",
|
|
weight=0.5,
|
|
case_sensitive=False,
|
|
order_matters=False,
|
|
),
|
|
ListCritic(
|
|
critic_field="can_contain_any",
|
|
weight=0.5,
|
|
case_sensitive=False,
|
|
order_matters=False,
|
|
),
|
|
],
|
|
)
|
|
|
|
return suite
|