Skip to content

chore(wren-ai-service): improve text2sql#1839

Merged
cyyeh merged 1 commit intomainfrom
chore/ai-service/improve-text2sql
Jul 17, 2025
Merged

chore(wren-ai-service): improve text2sql#1839
cyyeh merged 1 commit intomainfrom
chore/ai-service/improve-text2sql

Conversation

@cyyeh
Copy link
Copy Markdown
Member

@cyyeh cyyeh commented Jul 17, 2025

add ranking rule

Summary by CodeRabbit

  • Documentation
    • Updated SQL generation instructions to explicitly require the use of DENSE_RANK() for ranking problems, including detailed steps for ranking and filtering results.
    • Clarified wording in the general rules to emphasize strict, step-by-step adherence to instructions and plans.

@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai bot commented Jul 17, 2025

Walkthrough

The update revises SQL generation system prompts by adding explicit instructions for handling ranking problems with the DENSE_RANK() function. The reasoning plan and SQL rules are updated to require using DENSE_RANK() and filtering with a WHERE clause for ranking tasks, with minor clarifications to prompt wording.

Changes

File(s) Change Summary
wren-ai-service/src/pipelines/generation/utils/sql.py Updated SQL generation prompt and rules to include explicit instructions for ranking problems using DENSE_RANK(); adjusted step numbering and clarified instruction wording.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant AI_System
    participant SQL_Generator

    User->>AI_System: Request SQL for ranking problem
    AI_System->>SQL_Generator: Generate reasoning plan
    SQL_Generator->>SQL_Generator: Add DENSE_RANK() step
    SQL_Generator->>SQL_Generator: Add WHERE clause filtering
    SQL_Generator->>AI_System: Return SQL query with DENSE_RANK()
    AI_System->>User: Provide SQL query result
Loading

Possibly related PRs

Suggested labels

module/ai-service, wren-ai-service

Suggested reviewers

  • imAsterSun

Poem

In the garden of code where queries bloom bright,
A rabbit hops in, setting ranking just right.
With DENSE_RANK() in paw and a WHERE clause in sight,
The SQL grows smarter, from morning to night.
Hop, hop, hooray—our queries take flight! 🐇✨

✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch chore/ai-service/improve-text2sql

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ 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.
    • Explain this complex logic.
    • 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 explain this code block.
    • @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 explain its main purpose.
    • @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.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

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.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai auto-generate unit tests to generate unit tests for this PR.
  • @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.

@cyyeh cyyeh added module/ai-service ai-service related ci/ai-service ai-service related labels Jul 17, 2025
@cyyeh cyyeh requested a review from yichieh-lu July 17, 2025 00:59
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (4)
wren-ai-service/src/pipelines/generation/utils/sql.py (4)

186-187: Condense step-2 into a single sentence for clarity
Splitting a single enumerated item across two lines creates visual noise and increases the risk of accidental re-numbering when this string is edited again.

-2. Explicitly state the following information in the reasoning plan: 
-if the user puts any specific timeframe(e.g. YYYY-MM-DD) in the user's question, you will put the absolute time frame in the SQL query; 
-Otherwise, you will put the relative timeframe in the SQL query.
+2. Explicitly state the following information in the reasoning plan: if the user specifies an absolute date (e.g., YYYY-MM-DD) use that absolute date in the SQL query; otherwise use a relative timeframe.

188-196: Ranking rule added – provide an example and disambiguate the filter condition
Great to see the explicit DENSE_RANK() guidance. Two small improvements would make the instruction unambiguous:

  1. Mention the mandatory ORDER BY clause inside the window, otherwise the assistant may omit it.
  2. Give a minimal example (rank <= 3) so it’s crystal-clear how the subsequent WHERE filter should look.
-3. For the ranking problem, you should use the ranking function, `DENSE_RANK()` to rank the results and then use `WHERE` clause to filter the results.
+3. For ranking problems, use the window function `DENSE_RANK() OVER (ORDER BY <sorting-column> DESC)` to assign ranks, and then filter with a `WHERE rank <= <N>` (or equivalent) clause.

252-253: Duplicate the clarification from the reasoning prompt to the SQL rules block
Nice consistency. Consider adding the same ORDER BY + example here as suggested above so both sections stay aligned.


262-265: Minor wording tweak to avoid repetition
“follow the instructions strictly to generate the SQL query” and “follow the plan step by step strictly” repeat “strictly” – trim one for readability.

-1. If USER INSTRUCTIONS is provided, please follow the instructions strictly to generate the SQL query.
+1. If USER INSTRUCTIONS is provided, please follow them to generate the SQL query.
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 1004513 and 1a1b9ed.

📒 Files selected for processing (1)
  • wren-ai-service/src/pipelines/generation/utils/sql.py (3 hunks)
🧰 Additional context used
🧠 Learnings (1)
📓 Common learnings
Learnt from: andreashimin
PR: Canner/WrenAI#1414
File: wren-ui/src/apollo/server/utils/error.ts:0-0
Timestamp: 2025-03-18T10:28:10.593Z
Learning: The typo in error code enum names ("IDENTIED_AS_GENERAL" and "IDENTIED_AS_MISLEADING_QUERY" instead of "IDENTIFIED_AS_GENERAL" and "IDENTIFIED_AS_MISLEADING_QUERY") in wren-ui/src/apollo/server/utils/error.ts was recognized but intentionally not fixed as it was considered out of scope for PR #1414.
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
  • GitHub Check: pytest
  • GitHub Check: pytest
  • GitHub Check: Analyze (javascript-typescript)
  • GitHub Check: Analyze (go)

@cyyeh cyyeh merged commit 6cd6b7e into main Jul 17, 2025
15 checks passed
@cyyeh cyyeh deleted the chore/ai-service/improve-text2sql branch July 17, 2025 01:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ci/ai-service ai-service related module/ai-service ai-service related wren-ai-service

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants