Revert "Move Run Workflow button to top of page" (#4614)
This commit is contained in:
@@ -504,60 +504,6 @@ function RunWorkflowForm({
|
||||
onSubmit={form.handleSubmit(onSubmit, handleInvalid)}
|
||||
className="space-y-8"
|
||||
>
|
||||
<header className="flex items-end justify-between gap-4">
|
||||
<div className="space-y-5">
|
||||
<h1 className="text-3xl">
|
||||
Parameters{workflow?.title ? ` - ${workflow.title}` : ""}
|
||||
</h1>
|
||||
<h2 className="text-lg text-slate-400">
|
||||
Fill the placeholder values that you have linked throughout your
|
||||
workflow.
|
||||
</h2>
|
||||
</div>
|
||||
<div className="flex shrink-0 gap-2">
|
||||
<CopyApiCommandDropdown
|
||||
getOptions={() => {
|
||||
const values = form.getValues();
|
||||
const body = getRunWorkflowRequestBody(
|
||||
values,
|
||||
workflowParameters,
|
||||
);
|
||||
const transformedBody = transformToWorkflowRunRequest(
|
||||
body,
|
||||
workflowPermanentId,
|
||||
);
|
||||
|
||||
// Build headers - x-max-steps-override is optional and can be added manually if needed
|
||||
const headers: Record<string, string> = {
|
||||
"Content-Type": "application/json",
|
||||
"x-api-key": apiCredential ?? "<your-api-key>",
|
||||
};
|
||||
|
||||
return {
|
||||
method: "POST",
|
||||
url: `${runsApiBaseUrl}/run/workflows`,
|
||||
body: transformedBody,
|
||||
headers,
|
||||
} satisfies ApiCommandOptions;
|
||||
}}
|
||||
/>
|
||||
<Button
|
||||
type="submit"
|
||||
disabled={
|
||||
runWorkflowMutation.isPending || hasLoginBlockValidationError
|
||||
}
|
||||
>
|
||||
{runWorkflowMutation.isPending && (
|
||||
<ReloadIcon className="mr-2 h-4 w-4 animate-spin" />
|
||||
)}
|
||||
{!runWorkflowMutation.isPending && (
|
||||
<PlayIcon className="mr-2 h-4 w-4" />
|
||||
)}
|
||||
Run workflow
|
||||
</Button>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
{hasLoginBlockValidationError && (
|
||||
<Alert variant="destructive">
|
||||
<ExclamationTriangleIcon className="h-4 w-4" />
|
||||
@@ -1105,6 +1051,49 @@ function RunWorkflowForm({
|
||||
</AccordionItem>
|
||||
</Accordion>
|
||||
</div>
|
||||
|
||||
<div className="flex justify-end gap-2">
|
||||
<CopyApiCommandDropdown
|
||||
getOptions={() => {
|
||||
const values = form.getValues();
|
||||
const body = getRunWorkflowRequestBody(
|
||||
values,
|
||||
workflowParameters,
|
||||
);
|
||||
const transformedBody = transformToWorkflowRunRequest(
|
||||
body,
|
||||
workflowPermanentId,
|
||||
);
|
||||
|
||||
// Build headers - x-max-steps-override is optional and can be added manually if needed
|
||||
const headers: Record<string, string> = {
|
||||
"Content-Type": "application/json",
|
||||
"x-api-key": apiCredential ?? "<your-api-key>",
|
||||
};
|
||||
|
||||
return {
|
||||
method: "POST",
|
||||
url: `${runsApiBaseUrl}/run/workflows`,
|
||||
body: transformedBody,
|
||||
headers,
|
||||
} satisfies ApiCommandOptions;
|
||||
}}
|
||||
/>
|
||||
<Button
|
||||
type="submit"
|
||||
disabled={
|
||||
runWorkflowMutation.isPending || hasLoginBlockValidationError
|
||||
}
|
||||
>
|
||||
{runWorkflowMutation.isPending && (
|
||||
<ReloadIcon className="mr-2 h-4 w-4 animate-spin" />
|
||||
)}
|
||||
{!runWorkflowMutation.isPending && (
|
||||
<PlayIcon className="mr-2 h-4 w-4" />
|
||||
)}
|
||||
Run workflow
|
||||
</Button>
|
||||
</div>
|
||||
</form>
|
||||
</Form>
|
||||
);
|
||||
|
||||
@@ -44,16 +44,22 @@ function WorkflowRunParameters() {
|
||||
|
||||
const initialValues = getInitialValues(location, workflowParameters ?? []);
|
||||
|
||||
const header = (
|
||||
<header className="space-y-5">
|
||||
<h1 className="text-3xl">
|
||||
Parameters{workflow?.title ? ` - ${workflow.title}` : ""}
|
||||
</h1>
|
||||
<h2 className="text-lg text-slate-400">
|
||||
Fill the placeholder values that you have linked throughout your
|
||||
workflow.
|
||||
</h2>
|
||||
</header>
|
||||
);
|
||||
|
||||
if (isFetching) {
|
||||
return (
|
||||
<div className="space-y-8">
|
||||
<header className="space-y-5">
|
||||
<h1 className="text-3xl">Parameters</h1>
|
||||
<h2 className="text-lg text-slate-400">
|
||||
Fill the placeholder values that you have linked throughout your
|
||||
workflow.
|
||||
</h2>
|
||||
</header>
|
||||
{header}
|
||||
<Skeleton className="h-96 w-full" />
|
||||
</div>
|
||||
);
|
||||
@@ -64,21 +70,26 @@ function WorkflowRunParameters() {
|
||||
}
|
||||
|
||||
return (
|
||||
<RunWorkflowForm
|
||||
initialValues={initialValues}
|
||||
workflowParameters={workflowParameters}
|
||||
initialSettings={{
|
||||
proxyLocation:
|
||||
proxyLocation ?? workflow.proxy_location ?? ProxyLocation.Residential,
|
||||
webhookCallbackUrl:
|
||||
webhookCallbackUrl ?? workflow.webhook_callback_url ?? "",
|
||||
maxScreenshotScrolls:
|
||||
maxScreenshotScrolls ?? workflow.max_screenshot_scrolls ?? null,
|
||||
extraHttpHeaders:
|
||||
extraHttpHeaders ?? workflow.extra_http_headers ?? null,
|
||||
cdpAddress: null,
|
||||
}}
|
||||
/>
|
||||
<div className="space-y-8">
|
||||
{header}
|
||||
<RunWorkflowForm
|
||||
initialValues={initialValues}
|
||||
workflowParameters={workflowParameters}
|
||||
initialSettings={{
|
||||
proxyLocation:
|
||||
proxyLocation ??
|
||||
workflow.proxy_location ??
|
||||
ProxyLocation.Residential,
|
||||
webhookCallbackUrl:
|
||||
webhookCallbackUrl ?? workflow.webhook_callback_url ?? "",
|
||||
maxScreenshotScrolls:
|
||||
maxScreenshotScrolls ?? workflow.max_screenshot_scrolls ?? null,
|
||||
extraHttpHeaders:
|
||||
extraHttpHeaders ?? workflow.extra_http_headers ?? null,
|
||||
cdpAddress: null,
|
||||
}}
|
||||
/>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -188,7 +188,7 @@ const nodeLibraryItems: Array<{
|
||||
/>
|
||||
),
|
||||
title: "File Parser Block",
|
||||
description: "Parse PDFs, CSVs, and Excel files",
|
||||
description: "Parse PDFs, CSVs, Excel files, and Images",
|
||||
},
|
||||
// {
|
||||
// nodeType: "pdfParser",
|
||||
|
||||
@@ -415,7 +415,7 @@ export type SendEmailBlock = WorkflowBlockBase & {
|
||||
export type FileURLParserBlock = WorkflowBlockBase & {
|
||||
block_type: "file_url_parser";
|
||||
file_url: string;
|
||||
file_type: "csv" | "excel" | "pdf";
|
||||
file_type: "csv" | "excel" | "pdf" | "image";
|
||||
json_schema: Record<string, unknown> | null;
|
||||
};
|
||||
|
||||
|
||||
@@ -350,7 +350,7 @@ export type SendEmailBlockYAML = BlockYAMLBase & {
|
||||
export type FileUrlParserBlockYAML = BlockYAMLBase & {
|
||||
block_type: "file_url_parser";
|
||||
file_url: string;
|
||||
file_type: "csv" | "excel" | "pdf";
|
||||
file_type: "csv" | "excel" | "pdf" | "image";
|
||||
json_schema?: Record<string, unknown> | null;
|
||||
};
|
||||
|
||||
|
||||
@@ -2,4 +2,4 @@
|
||||
|
||||
import typing
|
||||
|
||||
FileType = typing.Union[typing.Literal["csv", "excel", "pdf"], typing.Any]
|
||||
FileType = typing.Union[typing.Literal["csv", "excel", "pdf", "image"], typing.Any]
|
||||
|
||||
19
skyvern/forge/prompts/skyvern/extract-text-from-image.j2
Normal file
19
skyvern/forge/prompts/skyvern/extract-text-from-image.j2
Normal file
@@ -0,0 +1,19 @@
|
||||
Extract all visible text from this image.
|
||||
|
||||
MAKE SURE YOU OUTPUT VALID JSON. No text before or after JSON, no trailing commas, no comments, no unnecessary quotes.
|
||||
|
||||
Reply in JSON format with the following keys:
|
||||
{
|
||||
"extracted_text": str // All text extracted from the image
|
||||
}
|
||||
|
||||
TEXT EXTRACTION GUIDELINES:
|
||||
- Preserve reading order (top to bottom, left to right)
|
||||
- For tables: format as rows separated by newlines, columns separated by " | "
|
||||
- For multi-column layouts: extract each column separately, separated by blank lines
|
||||
- For forms: format as "Label: Value" on each line
|
||||
- Preserve line breaks where they appear meaningful (paragraphs, list items)
|
||||
- Include all visible text: headers, body text, labels, captions, watermarks
|
||||
- For handwritten text: do your best to transcribe, use [illegible] for unclear parts
|
||||
|
||||
If no text is visible in the image, return an empty string for extracted_text.
|
||||
@@ -3063,6 +3063,8 @@ class FileParserBlock(Block):
|
||||
return FileType.PDF
|
||||
elif suffix == ".tsv":
|
||||
return FileType.CSV # TSV files are handled by the CSV parser
|
||||
elif suffix in (".png", ".jpg", ".jpeg", ".gif", ".bmp", ".webp", ".tiff", ".tif"):
|
||||
return FileType.IMAGE
|
||||
else:
|
||||
return FileType.CSV # Default to CSV for .csv and any other extensions
|
||||
|
||||
@@ -3112,6 +3114,12 @@ class FileParserBlock(Block):
|
||||
validate_pdf_file(file_path, file_identifier=file_url_used)
|
||||
except PDFParsingError as e:
|
||||
raise InvalidFileType(file_url=file_url_used, file_type=self.file_type, error=str(e))
|
||||
elif self.file_type == FileType.IMAGE:
|
||||
kind = filetype.guess(file_path)
|
||||
if kind is None or not kind.mime.startswith("image/"):
|
||||
raise InvalidFileType(
|
||||
file_url=file_url_used, file_type=self.file_type, error="File is not a valid image"
|
||||
)
|
||||
|
||||
async def _parse_csv_file(self, file_path: str) -> list[dict[str, Any]]:
|
||||
"""Parse CSV/TSV file and return list of dictionaries."""
|
||||
@@ -3184,6 +3192,27 @@ class FileParserBlock(Block):
|
||||
except PDFParsingError as e:
|
||||
raise InvalidFileType(file_url=self.file_url, file_type=self.file_type, error=str(e))
|
||||
|
||||
async def _parse_image_file(self, file_path: str) -> str:
|
||||
"""Parse image file using vision LLM for OCR."""
|
||||
try:
|
||||
with open(file_path, "rb") as f:
|
||||
image_bytes = f.read()
|
||||
|
||||
llm_prompt = prompt_engine.load_prompt("extract-text-from-image")
|
||||
llm_api_handler = LLMAPIHandlerFactory.get_override_llm_api_handler(
|
||||
self.override_llm_key, default=app.LLM_API_HANDLER
|
||||
)
|
||||
llm_response = await llm_api_handler(
|
||||
prompt=llm_prompt,
|
||||
prompt_name="extract-text-from-image",
|
||||
screenshots=[image_bytes],
|
||||
force_dict=True,
|
||||
)
|
||||
return llm_response.get("extracted_text", "")
|
||||
except Exception:
|
||||
LOG.exception("Failed to extract text from image via OCR", file_url=self.file_url)
|
||||
raise
|
||||
|
||||
async def _extract_with_ai(
|
||||
self, content: str | list[dict[str, Any]], workflow_run_context: WorkflowRunContext
|
||||
) -> dict[str, Any]:
|
||||
@@ -3210,9 +3239,8 @@ class FileParserBlock(Block):
|
||||
"extract-information-from-file-text", extracted_text_content=content_str, json_schema=schema_to_use
|
||||
)
|
||||
|
||||
llm_api_handler = LLMAPIHandlerFactory.get_override_llm_api_handler(
|
||||
self.override_llm_key, default=app.LLM_API_HANDLER
|
||||
)
|
||||
llm_key = self.override_llm_key
|
||||
llm_api_handler = LLMAPIHandlerFactory.get_override_llm_api_handler(llm_key, default=app.LLM_API_HANDLER)
|
||||
|
||||
llm_response = await llm_api_handler(
|
||||
prompt=llm_prompt, prompt_name="extract-information-from-file-text", force_dict=False
|
||||
@@ -3261,9 +3289,9 @@ class FileParserBlock(Block):
|
||||
else:
|
||||
file_path = await download_file(self.file_url)
|
||||
|
||||
# Auto-detect file type based on file extension
|
||||
detected_file_type = self._detect_file_type_from_url(self.file_url)
|
||||
self.file_type = detected_file_type
|
||||
# Auto-detect file type if not explicitly set (IMAGE/EXCEL/PDF are explicit choices)
|
||||
if self.file_type not in (FileType.IMAGE, FileType.EXCEL, FileType.PDF):
|
||||
self.file_type = self._detect_file_type_from_url(self.file_url)
|
||||
|
||||
# Validate the file type
|
||||
self.validate_file_type(self.file_url, file_path)
|
||||
@@ -3283,6 +3311,8 @@ class FileParserBlock(Block):
|
||||
parsed_data = await self._parse_excel_file(file_path)
|
||||
elif self.file_type == FileType.PDF:
|
||||
parsed_data = await self._parse_pdf_file(file_path)
|
||||
elif self.file_type == FileType.IMAGE:
|
||||
parsed_data = await self._parse_image_file(file_path)
|
||||
else:
|
||||
return await self.build_block_result(
|
||||
success=False,
|
||||
|
||||
@@ -67,6 +67,7 @@ class FileType(StrEnum):
|
||||
CSV = "csv"
|
||||
EXCEL = "excel"
|
||||
PDF = "pdf"
|
||||
IMAGE = "image"
|
||||
|
||||
|
||||
class PDFFormat(StrEnum):
|
||||
|
||||
Reference in New Issue
Block a user