# 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.
129 lines
4.2 KiB
Python
129 lines
4.2 KiB
Python
from unittest.mock import patch
|
|
|
|
import pytest
|
|
from arcade_tdk import ToolContext, ToolSecretItem
|
|
from arcade_tdk.errors import ToolExecutionError
|
|
|
|
from arcade_firecrawl.tools import (
|
|
cancel_crawl,
|
|
crawl_website,
|
|
get_crawl_data,
|
|
get_crawl_status,
|
|
map_website,
|
|
scrape_url,
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_context():
|
|
return ToolContext(secrets=[ToolSecretItem(key="firecrawl_api_key", value="fake_api_key")])
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_firecrawl_app_for_scrape():
|
|
with patch("arcade_firecrawl.tools.scrape.FirecrawlApp") as app:
|
|
yield app.return_value
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_firecrawl_app_for_crawl():
|
|
with patch("arcade_firecrawl.tools.crawl.FirecrawlApp") as app:
|
|
yield app.return_value
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_firecrawl_app_for_map():
|
|
with patch("arcade_firecrawl.tools.map.FirecrawlApp") as app:
|
|
yield app.return_value
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_scrape_url_success(mock_firecrawl_app_for_scrape, mock_context):
|
|
expected_response = {
|
|
"success": True,
|
|
"data": {"scraped_content": "scraped content"},
|
|
}
|
|
mock_firecrawl_app_for_scrape.scrape_url.return_value = expected_response
|
|
|
|
result = await scrape_url(mock_context, "http://example.com")
|
|
assert result == expected_response
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_crawl_website_success(mock_firecrawl_app_for_crawl, mock_context):
|
|
expected_response = {
|
|
"id": "12345",
|
|
"success": True,
|
|
}
|
|
mock_firecrawl_app_for_crawl.async_crawl_url.return_value = expected_response
|
|
mock_firecrawl_app_for_crawl.check_crawl_status.return_value = expected_response
|
|
|
|
result = await crawl_website(mock_context, "http://example.com")
|
|
assert result == expected_response
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_crawl_status_success(mock_firecrawl_app_for_crawl, mock_context):
|
|
expected_response = {"status": "completed"}
|
|
mock_firecrawl_app_for_crawl.check_crawl_status.return_value = expected_response
|
|
|
|
result = await get_crawl_status(mock_context, "12345")
|
|
assert result == expected_response
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_crawl_data_success(mock_firecrawl_app_for_crawl, mock_context):
|
|
expected_response = {"data": "crawl data"}
|
|
mock_firecrawl_app_for_crawl.check_crawl_status.return_value = expected_response
|
|
|
|
result = await get_crawl_data(mock_context, "12345")
|
|
assert result == expected_response
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cancel_crawl_success(mock_firecrawl_app_for_crawl, mock_context):
|
|
expected_response = {"status": "cancelled"}
|
|
mock_firecrawl_app_for_crawl.cancel_crawl.return_value = expected_response
|
|
|
|
result = await cancel_crawl(mock_context, "12345")
|
|
assert result == expected_response
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_map_website_success(mock_firecrawl_app_for_map, mock_context):
|
|
expected_response = {"map": "website map"}
|
|
mock_firecrawl_app_for_map.map_url.return_value = expected_response
|
|
|
|
result = await map_website(mock_context, "http://example.com")
|
|
assert result == expected_response
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize(
|
|
"method,params,error_message",
|
|
[
|
|
(scrape_url, ("http://example.com",), "Error scraping URL"),
|
|
(crawl_website, ("http://example.com",), "Error crawling website"),
|
|
(get_crawl_status, ("12345",), "Error getting crawl status"),
|
|
(get_crawl_data, ("12345",), "Error getting crawl data"),
|
|
(cancel_crawl, ("12345",), "Error cancelling crawl"),
|
|
(map_website, ("http://example.com",), "Error mapping website"),
|
|
],
|
|
)
|
|
async def test_firecrawl_error(
|
|
mock_firecrawl_app_for_scrape,
|
|
mock_firecrawl_app_for_crawl,
|
|
mock_firecrawl_app_for_map,
|
|
mock_context,
|
|
method,
|
|
params,
|
|
error_message,
|
|
):
|
|
mock_firecrawl_app_for_scrape.scrape_url.side_effect = Exception(error_message)
|
|
mock_firecrawl_app_for_crawl.async_crawl_url.side_effect = Exception(error_message)
|
|
mock_firecrawl_app_for_crawl.check_crawl_status.side_effect = Exception(error_message)
|
|
mock_firecrawl_app_for_crawl.cancel_crawl.side_effect = Exception(error_message)
|
|
mock_firecrawl_app_for_map.map_url.side_effect = Exception(error_message)
|
|
|
|
with pytest.raises(ToolExecutionError):
|
|
await method(mock_context, *params)
|