feat(Engine): initial commit for generate engine metadata#2022
Open
shubhammahure wants to merge 11 commits intodevfrom
Open
feat(Engine): initial commit for generate engine metadata#2022shubhammahure wants to merge 11 commits intodevfrom
shubhammahure wants to merge 11 commits intodevfrom
Conversation
3 tasks
1 task
This was referenced Feb 23, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Using LLM, generate meta data for empty fields within an engine.
Should not overwrite fields that contain data
Generate meta data for empty fields
User should have some way to select what info is being sent to LLM for generation. Ex: give option for engine schema, sample rows, typing in additional details etc. User should always know what is being sent so data is not being leaked unknowingly.
How to Test
You can test in run pixel(Notebook cell) call
just replace your engineid and model id and provide options listed below(engine wise)
GenerateEngineMetadata(engine=["engineid"], model=["modelid"], metaKeys=[["description","tag"]], storagePath=["storagepath"], filePath=['filepath'], options=[{"includeSchema":true,"includeVectorFileNames":false,"includeVectorChunks":true,"includeStorageFileNames":true,"includeModelSmssInfo":true, "includeFunctionSmssInfo":2, "includeStorageFileContent":true }]);Example for StorageEngine
GenerateEngineMetadata(engine=["ed23348f-842c-417d-...."], model=["4801422a-5c62-421e-a00c-05c6...."], metaKeys=[["description","tag"]], storagePath=["/abcd3"], filePath=['/shubh'], options=[{"includeStorageFileNames":true,"includeStorageFileContent":true }]);Note: The storagePath and filePath keys are only supported for StorageEngine
Replace options according to your engine:
Supported options:
1) Database
Include database schema details such as tables and columns.
Max tables to include (default: 5)
Max columns per table (default: 10)
2) Vectors
Include vector document file names.
Maximum number of vector file names to include (default: 5).
Include sample text chunks from vector documents.
Maximum number of vector text chunks to include (default: 3).
3) Storages
Include storage file names.
Maximum number of storage file names to include (default: 5).
Copy files locally and read content snippets for context.
Max number of files to read content from (default: 3).
Max characters to read per file (default: 500).
4) Models
Include model smss file content.
5) Functions
Include function smss file content.
6) User-specific options
Refine and enhance an existing description instead of generating a new one.
Extra user-provided context to guide metadata generation.
Writing tone for the generated description.
Supported values: neutral | business | scientific (default: neutral).****