WrenAI icon indicating copy to clipboard operation
WrenAI copied to clipboard

[DONT MERGE]feat(wren-ai-service): generate semantics for alias

Open paopa opened this issue 1 year ago • 1 comments

This PR refactors the semantics description service to improve clarity and functionality:

  1. Renamed Components

    • Renamed semantics_description to semantics_enrichment for better clarity
    • Updated all related imports, class names, and configuration references
  2. Enhanced Model Properties

    • Added alias field to model and column properties
    • Improved property handling for better business context
  3. API Improvements

    • Added new /semantics-enrichment endpoint
    • Deprecated old /semantics-descriptions endpoint (maintaining backward compatibility)
    • Updated response format to include display names
  4. System Prompt Updates

    • Enhanced LLM system prompt to focus on business-friendly descriptions
    • Added guidelines for generating clear aliases and descriptions
  5. Model Processing

    • Removed explicit model selection filtering (now supports wildcard "*")
    • Improved chunking logic for better performance

Migration

Existing clients should migrate to the new /semantics-enrichment endpoint. The old endpoint will be maintained temporarily but is marked as deprecated.

Configuration Updates

Updated configuration files:

  • deployment/kustomizations/base/cm.yaml
  • docker/config.example.yaml
  • tools/config/config.example.yaml
  • tools/config/config.full.yaml

Testing for Endpoint

Request Body

{
  "selected_models": [
    "*"
  ],
  "user_prompt": "Track student enrollments, grades, and GPA calculations to monitor academic performance and identify areas for student support",
    "mdl": "{\"catalog\":\"canner-cml\",\"schema\":\"spider\",\"models\":[{\"name\":\"Course\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Course\\\"\",\"columns\":[{\"name\":\"CID\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"CID\",\"properties\":{}},{\"name\":\"CName\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"CName\",\"properties\":{}},{\"name\":\"Credits\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Credits\",\"properties\":{}},{\"name\":\"Instructor\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Instructor\",\"properties\":{}},{\"name\":\"Days\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Days\",\"properties\":{}},{\"name\":\"Hours\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Hours\",\"properties\":{}},{\"name\":\"DNO\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"DNO\",\"properties\":{}},{\"name\":\"Faculty\",\"type\":\"Faculty\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Course_Faculty\",\"properties\":{}},{\"name\":\"Department\",\"type\":\"Department\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Course_Department\",\"properties\":{}}],\"primaryKey\":\"CID\"},{\"name\":\"Department\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Department\\\"\",\"columns\":[{\"name\":\"DNO\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"DNO\",\"properties\":{}},{\"name\":\"Division\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Division\",\"properties\":{}},{\"name\":\"DName\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"DName\",\"properties\":{}},{\"name\":\"Room\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Room\",\"properties\":{}},{\"name\":\"Building\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Building\",\"properties\":{}},{\"name\":\"DPhone\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"DPhone\",\"properties\":{}}],\"primaryKey\":\"DNO\"},{\"name\":\"Enrolled_in\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Enrolled_in\\\"\",\"columns\":[{\"name\":\"StuID\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"StuID\",\"properties\":{}},{\"name\":\"CID\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"CID\",\"properties\":{}},{\"name\":\"Grade\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Grade\",\"properties\":{}},{\"name\":\"Student\",\"type\":\"Student\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Enrolled_in_Student\",\"properties\":{}},{\"name\":\"Course\",\"type\":\"Course\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Enrolled_in_Course\",\"properties\":{}},{\"name\":\"Gradeconversion\",\"type\":\"Gradeconversion\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Enrolled_in_Gradeconversion\",\"properties\":{}}],\"primaryKey\":\"\"},{\"name\":\"Faculty\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Faculty\\\"\",\"columns\":[{\"name\":\"FacID\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"FacID\",\"properties\":{}},{\"name\":\"Lname\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Lname\",\"properties\":{}},{\"name\":\"Fname\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Fname\",\"properties\":{}},{\"name\":\"Rank\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Rank\",\"properties\":{}},{\"name\":\"Sex\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Sex\",\"properties\":{}},{\"name\":\"Phone\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Phone\",\"properties\":{}},{\"name\":\"Room\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Room\",\"properties\":{}},{\"name\":\"Building\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Building\",\"properties\":{}}],\"primaryKey\":\"FacID\"},{\"name\":\"Gradeconversion\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Gradeconversion\\\"\",\"columns\":[{\"name\":\"lettergrade\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"lettergrade\",\"properties\":{}},{\"name\":\"gradepoint\",\"type\":\"FLOAT\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"gradepoint\",\"properties\":{}}],\"primaryKey\":\"lettergrade\"},{\"name\":\"Member_of\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Member_of\\\"\",\"columns\":[{\"name\":\"FacID\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"FacID\",\"properties\":{}},{\"name\":\"DNO\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"DNO\",\"properties\":{}},{\"name\":\"Appt_Type\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Appt_Type\",\"properties\":{}},{\"name\":\"Faculty\",\"type\":\"Faculty\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Member_of_Faculty\",\"properties\":{}},{\"name\":\"Department\",\"type\":\"Department\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Member_of_Department\",\"properties\":{}}],\"primaryKey\":\"\"},{\"name\":\"Minor_in\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Minor_in\\\"\",\"columns\":[{\"name\":\"StuID\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"StuID\",\"properties\":{}},{\"name\":\"DNO\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"DNO\",\"properties\":{}},{\"name\":\"Student\",\"type\":\"Student\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Minor_in_Student\",\"properties\":{}},{\"name\":\"Department\",\"type\":\"Department\",\"notNull\":true,\"isCalculated\":false,\"relationship\":\"Minor_in_Department\",\"properties\":{}}],\"primaryKey\":\"\"},{\"name\":\"Student\",\"properties\":{},\"refSql\":\"select * from wrenai.spider.\\\"college_3-Student\\\"\",\"columns\":[{\"name\":\"StuID\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"StuID\",\"properties\":{}},{\"name\":\"LName\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"LName\",\"properties\":{}},{\"name\":\"Fname\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Fname\",\"properties\":{}},{\"name\":\"Age\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Age\",\"properties\":{}},{\"name\":\"Sex\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Sex\",\"properties\":{}},{\"name\":\"Major\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Major\",\"properties\":{}},{\"name\":\"Advisor\",\"type\":\"INTEGER\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"Advisor\",\"properties\":{}},{\"name\":\"city_code\",\"type\":\"VARCHAR\",\"notNull\":false,\"isCalculated\":false,\"expression\":\"city_code\",\"properties\":{}}],\"primaryKey\":\"StuID\"}],\"relationships\":[{\"name\":\"Course_Faculty\",\"models\":[\"Course\",\"Faculty\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Course.Instructor = Faculty.FacID\"},{\"name\":\"Course_Department\",\"models\":[\"Course\",\"Department\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Course.DNO = Department.DNO\"},{\"name\":\"Enrolled_in_Student\",\"models\":[\"Enrolled_in\",\"Student\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Enrolled_in.StuID = Student.StuID\"},{\"name\":\"Enrolled_in_Course\",\"models\":[\"Enrolled_in\",\"Course\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Enrolled_in.CID = Course.CID\"},{\"name\":\"Enrolled_in_Gradeconversion\",\"models\":[\"Enrolled_in\",\"Gradeconversion\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Enrolled_in.Grade = Gradeconversion.lettergrade\"},{\"name\":\"Member_of_Faculty\",\"models\":[\"Member_of\",\"Faculty\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Member_of.FacID = Faculty.FacID\"},{\"name\":\"Member_of_Department\",\"models\":[\"Member_of\",\"Department\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Member_of.DNO = Department.DNO\"},{\"name\":\"Minor_in_Student\",\"models\":[\"Minor_in\",\"Student\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Minor_in.StuID = Student.StuID\"},{\"name\":\"Minor_in_Department\",\"models\":[\"Minor_in\",\"Department\"],\"joinType\":\"MANY_TO_ONE\",\"condition\":\"Minor_in.DNO = Department.DNO\"}],\"metrics\":[],\"cumulativeMetrics\":[],\"enumDefinitions\":[],\"views\":[],\"macros\":[]}",
  "project_id": "string",
  "configuration": {
    "language": "zh_TW",
    "timezone": {
      "name": "Asia/Taipei",
      "utc_offset": ""
    }
  }
}

Screenshots

image image image image image image

Summary by CodeRabbit

Summary by CodeRabbit

  • Refactor

    • Renamed "Semantics Description" pipeline to "Semantics Enrichment" across multiple configuration and service files.
    • Updated service, router, and test files to reflect the new pipeline name.
  • New Features

    • Enhanced model and column metadata handling in the semantics enrichment pipeline.
    • Added more detailed information like display names and aliases for models.
  • Documentation

    • Updated configuration examples to match new pipeline terminology.
    • Adjusted test configurations to align with the updated pipeline name.

paopa avatar Dec 05 '24 07:12 paopa

Walkthrough

The pull request introduces a comprehensive renaming of the "Semantics Description" functionality to "Semantics Enrichment" across multiple configuration files, service implementations, and test suites in the Wren AI service. The changes involve updating pipeline names, service classes, router endpoints, and configuration files to reflect the new terminology. The modifications are consistent across different components, ensuring a unified approach to semantics enrichment while maintaining the existing functionality.

Changes

File Path Change Summary
deployment/kustomizations/base/cm.yaml Renamed pipeline from semantics_description to semantics_enrichment in ConfigMap.
docker/config.example.yaml Updated pipeline name from semantics_description to semantics_enrichment.
wren-ai-service/src/globals.py Refactored service container with updated service names and reintroduced chart-related services.
wren-ai-service/src/pipelines/generation/* Renamed classes, updated imports, and modified __all__ declarations.
wren-ai-service/src/web/v1/routers/* Updated router configurations and endpoints for semantics enrichment.
wren-ai-service/src/web/v1/services/semantics_enrichment.py Comprehensive renaming and slight logic modifications.
Configuration files Updated pipeline names across multiple YAML configuration files.

Possibly related PRs

  • Canner/WrenAI#1009: The changes in the main PR, specifically the renaming of the pipeline from semantics_description to semantics_enrichment, are directly related to the modifications in the retrieved PR, which also involve updates to the same pipeline name in various configurations.
  • Canner/WrenAI#1253: The changes in the main PR, specifically the renaming of the pipeline from semantics_description to semantics_enrichment, are directly related to the modifications in the retrieved PR, which also involve updates to the pipeline configurations and references to the same pipeline name.
  • Canner/WrenAI#1082: The changes in the main PR, specifically the renaming of the pipeline entry from semantics_description to semantics_enrichment, are directly related to the changes in the retrieved PR, which also involves renaming a pipeline entry from sql_pairs_preparation to sql_pairs_indexing, indicating a similar pattern of modification in pipeline identifiers.

Poem

🐰 Hop, hop, semantics dance!
From description to enrichment's glance,
Rename the pipeline, update the code,
A rabbit's refactor down this winding road!
Semantic magic, now more bright! 🌟

✨ Finishing Touches
  • [ ] 📝 Generate Docstrings (Beta)

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

coderabbitai[bot] avatar Dec 27 '24 05:12 coderabbitai[bot]