arcade-mcp/toolkits/google_drive/evals/eval_google_drive.py
Eric Gustin 07c52100f3
Split and rename multiple toolkits (#438)
# PR Description
## Split toolkits

This PR splits the `Microsoft`, `Google`, and `Search` toolkits into
multiple toolkits each.
 * `Microsoft` --> `OutlookCalendar`, `OutlookMail`.
* `Google` -----> `GoogleCalendar`, `GoogleContacts`, `GoogleDocs`,
`GoogleDrive`, `Gmail`, `GoogleSheets`
* `Search` -----> `GoogleFinance`, `GoogleFlights`, `GoogleHotels`,
`GoogleJobs`, `GoogleMaps`, `GoogleNews`, `GoogleSearch`,
`GoogleShopping`, `Walmart`, `Youtube`

> The original monolithic toolkits (`Microsoft`, `Google`, `Search`) are
not removed in this PR. The plan is to keep those toolkits around while
we
> 1. Stop documenting the toolkits, 
> 2. Stop displaying the toolkits in the dashboard, and 
> 3. Help customers migrate over to the new split toolkits.

## Rename toolkits
This PR renames the following toolkits 
* `Web` ------------> `Firecrawl`
* `CodeSandbox` ---> `E2B`

> The `Web` and `CodeSandbox` toolkits are not removed in this PR. The
plan is to keep them around while we
> 1. Stop documenting the toolkits, 
> 2. Stop displaying the toolkits in the dashboard, and 
> 3. Help customers migrate over to the new renamed toolkits.

## Rename tools
Since toolkit names were changed, this called for some tools to be
renamed as well.
* `GoogleSearch.SearchGoogle` ----------------> `GoogleSearch.Search`
* `GoogleShopping.SearchShoppingProducts` --->
`GoogleShopping.SearchProducts`
* `Walmart.SearchWalmartProducts` ------------> `Walmart.SearchProducts`
* `Walmart.GetWalmartProductDetails` --------->
`Walmart.GetProductDetails`
* `Youtube.SearchYoutubeVideos` -------------->
`Youtube.SearchForVideos`

## Google File Picker
Improvements to the Google File Picker experience were also added in
this PR.

The following tools will ALWAYS provide llm_instructions in their
response to "let the end-user know that they have the option to select
more files via the file picker url if they want to":
* `GoogleDocs.SearchDocuments`
* `GoogleDocs.SearchAndRetrieveDocuments`
* `GoogleDrive.GetFileTreeStructure`

The following tools will only provide the file picker URL if a 404 or
403 from the Google API:
* `GoogleDocs.InsertTextAtEndOfDocument`
* `GoogleDocs.GetDocumentById`
* `GoogleSheets.GetSpreadsheet`
* `GoogleSheets.WriteToCell`

Also, a standalone `GoogleDrive.GenerateGoogleFilePickerUrl` tool
exists.

## Other
* The `SearchDocuments` and `SearchAndRetrieveDocuments` tools used to
be organized within the Drive portion of the Google toolkit, but I moved
these into the new GoogleDocs toolkit because they are specific to Docs.

# Progress

- [x] `OutlookCalendar`
- [x] `OutlookMail`
- [x] `GoogleFinance`
- [x] `GoogleFlights`
- [x] `GoogleHotels`
- [x] `GoogleJobs`
- [x] `GoogleMaps`
- [x] `GoogleNews`
- [x] `GoogleSearch`
- [x] `GoogleShopping`
- [x] `Walmart`
- [x] `Youtube`
- [x] `GoogleCalendar`
- [x] `GoogleContacts`
- [x] `GoogleDocs`
- [x] `GoogleDrive`
- [x] `Gmail`
- [x] `GoogleSheets`
- [x] `Firecrawl`
- [x] `E2B`
- [x] File picker

# Discussion
* Repeated code is a consequence of splitting toolkits that use the same
provider. I am open to any ideas that would allow multiple toolkits to
reference common code. Comment your ideas in this PR.
2025-07-09 16:00:09 -07:00

131 lines
4.8 KiB
Python

from arcade_evals import (
BinaryCritic,
EvalRubric,
EvalSuite,
ExpectedToolCall,
tool_eval,
)
from arcade_tdk import ToolCatalog
import arcade_google_drive
from arcade_google_drive.tools import (
get_file_tree_structure,
)
# Evaluation rubric
rubric = EvalRubric(
fail_threshold=0.9,
warn_threshold=0.95,
)
catalog = ToolCatalog()
catalog.add_module(arcade_google_drive)
@tool_eval()
def get_file_tree_structure_eval_suite() -> EvalSuite:
"""Create an evaluation suite for Google Drive tools."""
suite = EvalSuite(
name="Google Drive Tools Evaluation",
system_message="You are an AI assistant that can manage Google Drive documents using the provided tools.",
catalog=catalog,
rubric=rubric,
)
suite.add_case(
name="get my google drive's file tree structure including shared drives",
user_message="get my google drive's file tree structure including shared drives",
expected_tool_calls=[
ExpectedToolCall(
func=get_file_tree_structure,
args={
"restrict_to_shared_drive_id": None,
"include_shared_drives": True,
"include_organization_domain_documents": False,
"order_by": None,
"limit": None,
},
)
],
critics=[
BinaryCritic(critic_field="include_shared_drives", weight=0.5),
BinaryCritic(critic_field="restrict_to_shared_drive_id", weight=0.5 / 4),
BinaryCritic(critic_field="include_organization_domain_documents", weight=0.5 / 4),
BinaryCritic(critic_field="order_by", weight=0.5 / 4),
BinaryCritic(critic_field="limit", weight=0.5 / 4),
],
)
suite.add_case(
name="get my google drive's file tree structure without shared drives",
user_message="get my google drive's file tree structure without shared drives",
expected_tool_calls=[
ExpectedToolCall(
func=get_file_tree_structure,
args={
"restrict_to_shared_drive_id": None,
"include_shared_drives": False,
"include_organization_domain_documents": False,
"order_by": None,
"limit": None,
},
)
],
critics=[
BinaryCritic(critic_field="include_shared_drives", weight=0.5),
BinaryCritic(critic_field="restrict_to_shared_drive_id", weight=0.5 / 4),
BinaryCritic(critic_field="include_organization_domain_documents", weight=0.5 / 4),
BinaryCritic(critic_field="order_by", weight=0.5 / 4),
BinaryCritic(critic_field="limit", weight=0.5 / 4),
],
)
suite.add_case(
name="what are the files in the folder 'hello world' in my google drive?",
user_message="what are the files in the folder 'hello world' in my google drive?",
expected_tool_calls=[
ExpectedToolCall(
func=get_file_tree_structure,
args={
"restrict_to_shared_drive_id": None,
"include_shared_drives": False,
"include_organization_domain_documents": False,
"order_by": None,
"limit": None,
},
)
],
critics=[
BinaryCritic(critic_field="include_shared_drives", weight=0.5),
BinaryCritic(critic_field="restrict_to_shared_drive_id", weight=0.5 / 4),
BinaryCritic(critic_field="include_organization_domain_documents", weight=0.5 / 4),
BinaryCritic(critic_field="order_by", weight=0.5 / 4),
BinaryCritic(critic_field="limit", weight=0.5 / 4),
],
)
suite.add_case(
name="how many files are there in all my google drives, including shared ones?",
user_message="how many files are there in all my google drives, including shared ones?",
expected_tool_calls=[
ExpectedToolCall(
func=get_file_tree_structure,
args={
"restrict_to_shared_drive_id": None,
"include_shared_drives": True,
"include_organization_domain_documents": False,
"order_by": None,
"limit": None,
},
)
],
critics=[
BinaryCritic(critic_field="include_shared_drives", weight=0.5),
BinaryCritic(critic_field="restrict_to_shared_drive_id", weight=0.5 / 4),
BinaryCritic(critic_field="include_organization_domain_documents", weight=0.5 / 4),
BinaryCritic(critic_field="order_by", weight=0.5 / 4),
BinaryCritic(critic_field="limit", weight=0.5 / 4),
],
)
return suite