07c52100f3
# 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.
49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
from typing import Annotated, Any
|
|
|
|
from arcade_tdk import ToolContext, tool
|
|
from firecrawl import FirecrawlApp
|
|
|
|
from arcade_firecrawl.enums import Formats
|
|
|
|
|
|
# TODO: Support actions. This would enable clicking, scrolling, screenshotting, etc.
|
|
# TODO: Support extract.
|
|
# TODO: Support headers param?
|
|
@tool(requires_secrets=["FIRECRAWL_API_KEY"])
|
|
async def scrape_url(
|
|
context: ToolContext,
|
|
url: Annotated[str, "URL to scrape"],
|
|
formats: Annotated[
|
|
list[Formats] | None, "Formats to retrieve. Defaults to ['markdown']."
|
|
] = None,
|
|
only_main_content: Annotated[
|
|
bool | None,
|
|
"Only return the main content of the page excluding headers, navs, footers, etc.",
|
|
] = True,
|
|
include_tags: Annotated[list[str] | None, "List of tags to include in the output"] = None,
|
|
exclude_tags: Annotated[list[str] | None, "List of tags to exclude from the output"] = None,
|
|
wait_for: Annotated[
|
|
int | None,
|
|
"Specify a delay in milliseconds before fetching the content, allowing the page "
|
|
"sufficient time to load.",
|
|
] = 10,
|
|
timeout: Annotated[int | None, "Timeout in milliseconds for the request"] = 30000,
|
|
) -> Annotated[dict[str, Any], "Scraped data in specified formats"]:
|
|
"""Scrape a URL using Firecrawl and return the data in specified formats."""
|
|
|
|
api_key = context.get_secret("FIRECRAWL_API_KEY")
|
|
|
|
formats = formats or [Formats.MARKDOWN]
|
|
|
|
app = FirecrawlApp(api_key=api_key)
|
|
params = {
|
|
"formats": formats,
|
|
"onlyMainContent": only_main_content,
|
|
"includeTags": include_tags or [],
|
|
"excludeTags": exclude_tags or [],
|
|
"waitFor": wait_for,
|
|
"timeout": timeout,
|
|
}
|
|
response = app.scrape_url(url, params=params)
|
|
|
|
return dict(response)
|