Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

GSM8k, SVAMP, TabMWP for ReAct #166

Merged
merged 54 commits into from
Jun 2, 2024
Merged

GSM8k, SVAMP, TabMWP for ReAct #166

merged 54 commits into from
Jun 2, 2024

Conversation

alckasoc
Copy link
Member

@alckasoc alckasoc commented Jun 1, 2024

πŸ€” Reasoning

Explain the purpose of this PR...

🚧 Changes

Describe the changes made...

βœ… PR Checklist

  • Using this PR template?
  • Linked issue?
  • Added feature?
    • Added/updated docs?
    • Added/updated tests?

Summary by CodeRabbit

  • Documentation

    • Updated status indicators for various methods/benchmarks in the documentation table.
    • ReAct status updated to complete.
    • CRITIC status updated to fully complete.
    • Self-Refine status updated to incomplete.
  • Chores

    • Adjusted version number in the react.ipynb notebook metadata.

@alckasoc alckasoc added enhancement New feature or request design Suggested design/organizational changes add-benchmark Adding support for a benchmark labels Jun 1, 2024
@alckasoc alckasoc added this to the ReAct (No Decision-Making) milestone Jun 1, 2024
@alckasoc alckasoc self-assigned this Jun 1, 2024
Copy link
Contributor

coderabbitai bot commented Jun 1, 2024

Note

Reviews paused

Use the following commands to manage reviews:

  • @coderabbitai resume to resume automatic reviews.
  • @coderabbitai review to trigger a single review.

Walkthrough

The recent updates primarily involve adjustments to the documentation and metadata. Status indicators for various methods/benchmarks were updated in the index.md documentation file, reflecting their completion status. Additionally, the version number in the react.ipynb notebook metadata was revised.

Changes

Files Change Summary
docs/docs/index.md Updated status indicators for methods/benchmarks: ReAct to :octicons-check-16:, CRITIC to :material-check-all:, Self-Refine to empty.
notebooks/react.ipynb Changed version number in metadata from "3.11.9" to "3.11.5".

Poem

In docs, the status lights now gleam,
ReAct and CRITIC join the dream.
A version tweak, just a small dive,
From 3.11.9 to .5.
Progress marks the path we tread,
With every change, we move ahead. πŸ‡βœ¨


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>.
    • 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 generate interesting stats about this repository and render them as a table.
    • @coderabbitai show all the console.log statements in this repository.
    • @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 as 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 resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configration 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.

@alckasoc
Copy link
Member Author

alckasoc commented Jun 1, 2024

@coderabbitai pause

Copy link
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

Outside diff range and nitpick comments (3)
docs/docs/index.md (3)

Line range hint 102-105: Convert asterisks to dashes for list items to maintain consistency.

- * `mkdocs new [dir-name]` - Create a new project.
- * `mkdocs serve` - Start the live-reloading docs server.
- * `mkdocs build` - Build the documentation site.
- * `mkdocs -h` - Print help message and exit.
+ - `mkdocs new [dir-name]` - Create a new project.
+ - `mkdocs serve` - Start the live-reloading docs server.
+ - `mkdocs build` - Build the documentation site.
+ - `mkdocs -h` - Print help message and exit.

Line range hint 22-22: Reduce multiple consecutive blank lines to a single blank line.

This will improve the readability and maintain the consistency of the document layout.

Also applies to: 25-25, 26-26, 65-65


Line range hint 98-98: Consider adding a comma after "visit" for better readability.

- For full documentation visit [mkdocs.org](https://www.mkdocs.org).
+ For full documentation, visit [mkdocs.org](https://www.mkdocs.org).
Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between b2d9943 and 02938a2.

Files selected for processing (2)
  • docs/docs/index.md (1 hunks)
  • notebooks/react.ipynb (1 hunks)
Files skipped from review due to trivial changes (1)
  • notebooks/react.ipynb
Additional context used
LanguageTool
docs/docs/index.md

[uncategorized] ~98-~98: Possible missing comma found.
Context: ... | | | For full documentation visit [mkdocs.org](https://www.mkdocs.o...

Markdownlint
docs/docs/index.md

102-102: Expected: dash; Actual: asterisk
Unordered list style


103-103: Expected: dash; Actual: asterisk
Unordered list style


104-104: Expected: dash; Actual: asterisk
Unordered list style


105-105: Expected: dash; Actual: asterisk
Unordered list style


22-22: Expected: 1; Actual: 2
Multiple consecutive blank lines


25-25: Expected: 1; Actual: 2
Multiple consecutive blank lines


26-26: Expected: 1; Actual: 3
Multiple consecutive blank lines


65-65: Expected: 1; Actual: 2
Multiple consecutive blank lines

Additional comments not posted (1)
docs/docs/index.md (1)

41-41: Update the status indicators for ReAct, CRITIC, and Self-Refine to reflect the latest testing status.

This change aligns with the PR's objective to update the documentation status based on the latest benchmarks.

Copy link
Contributor

coderabbitai bot commented Jun 1, 2024

Actions performed

Reviews paused.

Copy link

codecov bot commented Jun 1, 2024

Codecov Report

Attention: Patch coverage is 97.08738% with 3 lines in your changes are missing coverage. Please review.

Files Coverage Ξ”
agential/cog/agent/expel.py 100.00% <100.00%> (ΓΈ)
agential/cog/agent/react.py 100.00% <ΓΈ> (ΓΈ)
agential/cog/agent/reflexion.py 96.82% <100.00%> (ΓΈ)
agential/cog/functional/critic.py 100.00% <ΓΈ> (ΓΈ)
agential/cog/functional/expel.py 97.32% <100.00%> (ΓΈ)
agential/cog/functional/react.py 100.00% <100.00%> (ΓΈ)
agential/cog/functional/reflexion.py 95.61% <100.00%> (ΓΈ)
agential/cog/functional/self_refine.py 100.00% <ΓΈ> (ΓΈ)
agential/cog/modules/reflect/reflexion.py 100.00% <100.00%> (ΓΈ)
agential/cog/prompts/agent/critic.py 100.00% <ΓΈ> (ΓΈ)
... and 22 more

@alckasoc alckasoc merged commit 62d55e2 into main Jun 2, 2024
4 checks passed
@alckasoc alckasoc deleted the vincent/math_react branch June 2, 2024 11:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
add-benchmark Adding support for a benchmark design Suggested design/organizational changes enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Feature Request]: TabMWP for ReAct [Feature Request]: SVAMP for ReAct [Feature Request]: GSM8k for ReAct
1 participant