Publish Snowflake Doc AI package #235
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
c02mo
approved these changes
Oct 16, 2025
Comment on lines
+99
to
+106
| # Validate supported file types (Snowflake AI_PARSE_DOCUMENT supports .pdf, .docx, .pptx) | ||
| supported_extensions = {'.pdf', '.docx', '.pptx'} | ||
| if file_ext_lower not in supported_extensions: | ||
| unsupported_msg = ( | ||
| f"Unsupported file type '{file_ext}'. Only PDF, DOCX, and PPTX are supported " | ||
| f"by AI_PARSE_DOCUMENT for this action. See docs: https://docs.snowflake.com/en/user-guide/snowflake-cortex/parse-document" | ||
| ) | ||
| return Response(error=unsupported_msg) |
Contributor
There was a problem hiding this comment.
This is not quite bulletproof.
Typically these kind of checks should be done over MIME.
But I guess it's good enough for now.
| # Execute PUT command with the correctly named file | ||
| put_command = f"PUT 'file://{correct_name_path}' '{stage_location}' OVERWRITE=TRUE AUTO_COMPRESS=FALSE SOURCE_COMPRESSION=NONE" | ||
| print(f"[{datetime.datetime.now().strftime('%H:%M:%S.%f')}] Executing PUT command to upload file...") | ||
| print("Uploading file to stage...") |
Contributor
There was a problem hiding this comment.
Reason for removing timestamp?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Snowflake Doc AI has a new "one shot parse" function. This action pack exposes it as an action (along with list files in stage helper action). Supports only digital documents like PDF, PPTX and DOCX for now, but later can be expanded to support OCRable docs.
In the whitelist file this is only published to Team Edition connected Studios.
How can (was) this tested?
Locally in Cursor and Studio with ~10 different docs.
Checklist: