feat: implement Document AI Functions and IK Custom Dictionary#1083
Open
ShiXing321 wants to merge 2 commits into
Open
feat: implement Document AI Functions and IK Custom Dictionary#1083ShiXing321 wants to merge 2 commits into
ShiXing321 wants to merge 2 commits into
Conversation
LOAD_FILE(location, filename) - read file from LOCATION as BLOB. AI_SPLIT_DOCUMENT(content[, params]) - table function for text chunking, supports by=sentence, by=word, type=markdown, max, overlap params. Co-Authored-By: Claude <[email protected]>
LOAD_FILE: fix location existence check order, error codes, path separator AI_SPLIT_DOCUMENT: fix JSON key parsing, column type, trailing whitespace, enum IK Custom Dict: fix property parsing, cache invalidation, table name handling, grammar Co-Authored-By: Claude <[email protected]>
|
|
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Three modules implemented:
1. LOAD_FILE(location_name, file_name) -> BLOB
Reads file from LOCATION object with privilege check.
2. AI_SPLIT_DOCUMENT(content[, params]) -> table function
Splits text/markdown into chunk rows (chunk_id, chunk_offset, chunk_length, chunk_text).
Supports by=sentence, by=word, type=markdown/text, max, overlap.
3. IK Custom Dictionary
Fixes from code review includes location existence check before privilege check, JSON key matching, IK dict_table property parsing, cache invalidation key alignment, and grammar support for dotted table names.