arcade-mcp/toolkits/google_jobs/evals/eval_google_jobs.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

157 lines
5.4 KiB
Python

from arcade_evals import (
BinaryCritic,
EvalRubric,
EvalSuite,
ExpectedToolCall,
NoneCritic,
SimilarityCritic,
tool_eval,
)
from arcade_tdk import ToolCatalog
import arcade_google_jobs
from arcade_google_jobs.constants import DEFAULT_GOOGLE_JOBS_LANGUAGE
from arcade_google_jobs.tools import search_jobs
# Evaluation rubric
rubric = EvalRubric(
fail_threshold=0.8,
warn_threshold=0.9,
)
catalog = ToolCatalog()
# Register the Google Jobs tool
catalog.add_module(arcade_google_jobs)
@tool_eval()
def google_jobs_eval_suite() -> EvalSuite:
"""Create an evaluation suite for the Google Jobs tool."""
suite = EvalSuite(
name="Google Jobs Tool Evaluation",
system_message="You are an AI assistant that can perform job searches using the provided tools.",
catalog=catalog,
rubric=rubric,
)
suite.add_case(
name="Search for 'backend engineer' jobs",
user_message="Search for 'backend engineer' jobs",
expected_tool_calls=[
ExpectedToolCall(
func=search_jobs,
args={
"query": "backend engineer",
"location": None,
"language": DEFAULT_GOOGLE_JOBS_LANGUAGE,
"limit": 10,
"next_page_token": None,
},
)
],
critics=[
SimilarityCritic(critic_field="query", weight=0.5),
NoneCritic(critic_field="location", weight=0.1),
BinaryCritic(critic_field="language", weight=0.1),
BinaryCritic(critic_field="limit", weight=0.1),
NoneCritic(critic_field="next_page_token", weight=0.1),
],
)
suite.add_case(
name="Search for 'senior backend engineer' jobs that are part-time",
user_message="Search for senior backend engineer jobs that are part-time",
expected_tool_calls=[
ExpectedToolCall(
func=search_jobs,
args={
"query": "part-time senior backend engineer",
"location": None,
"language": DEFAULT_GOOGLE_JOBS_LANGUAGE,
"limit": 10,
"next_page_token": None,
},
)
],
critics=[
SimilarityCritic(critic_field="query", weight=0.5),
NoneCritic(critic_field="location", weight=0.1),
BinaryCritic(critic_field="language", weight=0.1),
BinaryCritic(critic_field="limit", weight=0.1),
NoneCritic(critic_field="next_page_token", weight=0.1),
],
)
suite.add_case(
name="Search for 'backend engineer' jobs in San Francisco",
user_message="Search for 'backend engineer' jobs in San Francisco",
expected_tool_calls=[
ExpectedToolCall(
func=search_jobs,
args={
"query": "backend engineer",
"location": "San Francisco",
"language": DEFAULT_GOOGLE_JOBS_LANGUAGE,
"limit": 10,
"next_page_token": None,
},
)
],
critics=[
SimilarityCritic(critic_field="query", weight=0.35),
SimilarityCritic(critic_field="location", weight=0.35),
BinaryCritic(critic_field="language", weight=0.1),
BinaryCritic(critic_field="limit", weight=0.1),
NoneCritic(critic_field="next_page_token", weight=0.1),
],
)
suite.add_case(
name="Get the first 3 jobs for 'backend engineer' in San Francisco",
user_message="Get the first 3 jobs for 'backend engineer' in San Francisco",
expected_tool_calls=[
ExpectedToolCall(
func=search_jobs,
args={
"query": "backend engineer",
"location": "San Francisco",
"language": DEFAULT_GOOGLE_JOBS_LANGUAGE,
"limit": 3,
"next_page_token": None,
},
)
],
critics=[
SimilarityCritic(critic_field="query", weight=0.25),
SimilarityCritic(critic_field="location", weight=0.25),
BinaryCritic(critic_field="language", weight=0.125),
BinaryCritic(critic_field="limit", weight=0.25),
NoneCritic(critic_field="next_page_token", weight=0.125),
],
)
suite.add_case(
name="Search for 'engenheiro de software' jobs in Brazil, return results in Portuguese",
user_message="Search for 'engenheiro de software' jobs in Brazil, return results in Portuguese",
expected_tool_calls=[
ExpectedToolCall(
func=search_jobs,
args={
"query": "engenheiro de software",
"location": "Brazil",
"language": "pt",
"limit": 10,
"next_page_token": None,
},
)
],
critics=[
SimilarityCritic(critic_field="query", weight=0.25),
SimilarityCritic(critic_field="location", weight=0.125),
BinaryCritic(critic_field="language", weight=0.25),
BinaryCritic(critic_field="limit", weight=0.125),
NoneCritic(critic_field="next_page_token", weight=0.125),
],
)
return suite