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.
99 lines
3.1 KiB
Python
99 lines
3.1 KiB
Python
def convert_document_to_html(document: dict) -> str:
|
|
html = (
|
|
"<html><head>"
|
|
f"<title>{document['title']}</title>"
|
|
f'<meta name="documentId" content="{document["documentId"]}">'
|
|
"</head><body>"
|
|
)
|
|
for element in document["body"]["content"]:
|
|
html += convert_structural_element(element)
|
|
html += "</body></html>"
|
|
return html
|
|
|
|
|
|
def convert_structural_element(element: dict, wrap_paragraphs: bool = True) -> str:
|
|
if "sectionBreak" in element or "tableOfContents" in element:
|
|
return ""
|
|
|
|
elif "paragraph" in element:
|
|
paragraph_content = ""
|
|
|
|
prepend, append = get_paragraph_style_tags(
|
|
style=element["paragraph"]["paragraphStyle"],
|
|
wrap_paragraphs=wrap_paragraphs,
|
|
)
|
|
|
|
for item in element["paragraph"]["elements"]:
|
|
if "textRun" not in item:
|
|
continue
|
|
paragraph_content += extract_paragraph_content(item["textRun"])
|
|
|
|
if not paragraph_content:
|
|
return ""
|
|
|
|
return f"{prepend}{paragraph_content.strip()}{append}"
|
|
|
|
elif "table" in element:
|
|
table = [
|
|
[
|
|
"".join([
|
|
convert_structural_element(element=cell_element, wrap_paragraphs=False)
|
|
for cell_element in cell["content"]
|
|
])
|
|
for cell in row["tableCells"]
|
|
]
|
|
for row in element["table"]["tableRows"]
|
|
]
|
|
return table_list_to_html(table)
|
|
|
|
else:
|
|
raise ValueError(f"Unknown document body element type: {element}")
|
|
|
|
|
|
def extract_paragraph_content(text_run: dict) -> str:
|
|
content = text_run["content"]
|
|
style = text_run["textStyle"]
|
|
return apply_text_style(content, style)
|
|
|
|
|
|
def apply_text_style(content: str, style: dict) -> str:
|
|
content = content.rstrip("\n")
|
|
content = content.replace("\n", "<br>")
|
|
italic = style.get("italic", False)
|
|
bold = style.get("bold", False)
|
|
if italic:
|
|
content = f"<i>{content}</i>"
|
|
if bold:
|
|
content = f"<b>{content}</b>"
|
|
return content
|
|
|
|
|
|
def get_paragraph_style_tags(style: dict, wrap_paragraphs: bool = True) -> tuple[str, str]:
|
|
named_style = style["namedStyleType"]
|
|
if named_style == "NORMAL_TEXT":
|
|
return ("<p>", "</p>") if wrap_paragraphs else ("", "")
|
|
elif named_style == "TITLE":
|
|
return "<h1>", "</h1>"
|
|
elif named_style == "SUBTITLE":
|
|
return "<h2>", "</h2>"
|
|
elif named_style.startswith("HEADING_"):
|
|
try:
|
|
heading_level = int(named_style.split("_")[1])
|
|
except ValueError:
|
|
return ("<p>", "</p>") if wrap_paragraphs else ("", "")
|
|
else:
|
|
return f"<h{heading_level}>", f"</h{heading_level}>"
|
|
return ("<p>", "</p>") if wrap_paragraphs else ("", "")
|
|
|
|
|
|
def table_list_to_html(table: list[list[str]]) -> str:
|
|
html = "<table>"
|
|
for row in table:
|
|
html += "<tr>"
|
|
for cell in row:
|
|
if cell.endswith("<br>"):
|
|
cell = cell[:-4]
|
|
html += f"<td>{cell}</td>"
|
|
html += "</tr>"
|
|
html += "</table>"
|
|
return html
|