Skip to content

OpenAI: Added support for structured outputs in Chat action #13725

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 1 commit into from
Aug 29, 2024
Merged

OpenAI: Added support for structured outputs in Chat action #13725

merged 1 commit into from
Aug 29, 2024

Conversation

jcortes
Copy link
Collaborator

@jcortes jcortes commented Aug 28, 2024 •
edited by coderabbitai bot
Loading

WHY

Resolves #13707

Summary by CodeRabbit

  • New Features

    • Improved response formatting logic with enhanced support for JSON schema in the Chat API.
    • New method added to define strict output requirements based on selected response formats.

  • Bug Fixes

    • Minor version updates across various modules suggest enhancements or bug fixes, including the "Analyze Image Content," "Cancel Run," and "Create Moderation" actions.

  • Documentation

    • Updated descriptions for response formats in the Chat API to provide clearer guidance on available output options.

  • Chores

    • Incremented version numbers for multiple modules to reflect minor updates and improvements in functionality.

@jcortes jcortes added enhancement New feature or request action New Action Request labels Aug 28, 2024
@jcortes jcortes self-assigned this Aug 28, 2024
@coderabbitai coderabbitai
Copy link
Contributor

coderabbitai bot commented Aug 28, 2024 •
edited
Loading

Walkthrough

The recent changes introduce support for structured outputs in OpenAI Actions, particularly enhancing the Chat action to utilize a new json_schema option for the response_format. This update allows users to specify structured output formats, ensuring that responses conform to a defined JSON schema. Additionally, minor version increments across various modules reflect ongoing maintenance and improvements in functionality.

Changes

Files Change Summary
components/openai/actions/chat/chat.mjs Updated version to 0.1.12; enhanced responseFormat with structured output options and added additionalProps method.
components/openai/common/constants.mjs Changed CHAT_RESPONSE_FORMATS from an array to an object with structured properties for response types.
components/openai/common/helpers.mjs Added a new function parse to handle input values, enhancing JSON parsing capabilities.
components/openai/actions/chat-with-assistant/chat-with-assistant.mjs Updated version to 0.0.4; no specific changes related to structured outputs.
components/openai/actions/create-chat/create-chat.mjs Updated version to 0.0.3; included structured output changes as part of the Chat API.

Assessment against linked issues

Objective Addressed Explanation
Add new json_schema option for response_format (#[13707]) ✅
Update Response Format description (#[13707]) ✅
Use additionalProps to unfurl the json_schema object (#[13707]) ✅

Poem

🐇 In the fields where bunnies play,
Structured outputs come our way!
With schemas neat and formats bright,
Our responses now take flight!
Hopping forth with joy and cheer,
OpenAI's magic is finally here! ✨

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 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.

@vercel Vercel
Copy link

vercel bot commented Aug 28, 2024

@jcortes is attempting to deploy a commit to the Pipedreamers Team on Vercel.

A member of the Team first needs to authorize it.

@vercel Vercel
Copy link

vercel bot commented Aug 28, 2024 •
edited
Loading

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Skipped Deployment
Name Status Preview Comments Updated (UTC)
pipedream-docs-redirect-do-not-edit ⬜️ Ignored (Inspect) Aug 28, 2024 5:21pm

@jcortes jcortes force-pushed the openai-support-structured-outputs branch from ec69d49 to ac352db Compare August 28, 2024 17:21
coderabbitai[bot]
coderabbitai bot reviewed Aug 28, 2024
View reviewed changes
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: 1

Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between 6c012d0 and ac352db.

Files selected for processing (37)
  • components/openai/actions/analyze-image-content/analyze-image-content.mjs (1 hunks)
  • components/openai/actions/cancel-run/cancel-run.mjs (1 hunks)
  • components/openai/actions/chat-with-assistant/chat-with-assistant.mjs (1 hunks)
  • components/openai/actions/chat/chat.mjs (2 hunks)
  • components/openai/actions/classify-items-into-categories/classify-items-into-categories.mjs (1 hunks)
  • components/openai/actions/common/common.mjs (2 hunks)
  • components/openai/actions/convert-text-to-speech/convert-text-to-speech.mjs (1 hunks)
  • components/openai/actions/create-assistant/create-assistant.mjs (1 hunks)
  • components/openai/actions/create-batch/create-batch.mjs (1 hunks)
  • components/openai/actions/create-embeddings/create-embeddings.mjs (1 hunks)
  • components/openai/actions/create-fine-tuning-job/create-fine-tuning-job.mjs (1 hunks)
  • components/openai/actions/create-image/create-image.mjs (1 hunks)
  • components/openai/actions/create-moderation/create-moderation.mjs (1 hunks)
  • components/openai/actions/create-thread/create-thread.mjs (1 hunks)
  • components/openai/actions/create-transcription/create-transcription.mjs (1 hunks)
  • components/openai/actions/delete-file/delete-file.mjs (1 hunks)
  • components/openai/actions/list-files/list-files.mjs (1 hunks)
  • components/openai/actions/list-messages/list-messages.mjs (1 hunks)
  • components/openai/actions/list-run-steps/list-run-steps.mjs (1 hunks)
  • components/openai/actions/list-runs/list-runs.mjs (1 hunks)
  • components/openai/actions/modify-assistant/modify-assistant.mjs (1 hunks)
  • components/openai/actions/retrieve-file-content/retrieve-file-content.mjs (1 hunks)
  • components/openai/actions/retrieve-file/retrieve-file.mjs (1 hunks)
  • components/openai/actions/retrieve-run-step/retrieve-run-step.mjs (1 hunks)
  • components/openai/actions/retrieve-run/retrieve-run.mjs (1 hunks)
  • components/openai/actions/send-prompt/send-prompt.mjs (1 hunks)
  • components/openai/actions/submit-tool-outputs-to-run/submit-tool-outputs-to-run.mjs (1 hunks)
  • components/openai/actions/summarize/summarize.mjs (1 hunks)
  • components/openai/actions/translate-text/translate-text.mjs (1 hunks)
  • components/openai/actions/upload-file/upload-file.mjs (1 hunks)
  • components/openai/common/constants.mjs (2 hunks)
  • components/openai/common/helpers.mjs (2 hunks)
  • components/openai/package.json (1 hunks)
  • components/openai/sources/new-batch-completed/new-batch-completed.mjs (1 hunks)
  • components/openai/sources/new-file-created/new-file-created.mjs (1 hunks)
  • components/openai/sources/new-fine-tuning-job-created/new-fine-tuning-job-created.mjs (1 hunks)
  • components/openai/sources/new-run-state-changed/new-run-state-changed.mjs (1 hunks)
Files skipped from review due to trivial changes (33)
  • components/openai/actions/analyze-image-content/analyze-image-content.mjs
  • components/openai/actions/cancel-run/cancel-run.mjs
  • components/openai/actions/chat-with-assistant/chat-with-assistant.mjs
  • components/openai/actions/classify-items-into-categories/classify-items-into-categories.mjs
  • components/openai/actions/convert-text-to-speech/convert-text-to-speech.mjs
  • components/openai/actions/create-assistant/create-assistant.mjs
  • components/openai/actions/create-batch/create-batch.mjs
  • components/openai/actions/create-embeddings/create-embeddings.mjs
  • components/openai/actions/create-fine-tuning-job/create-fine-tuning-job.mjs
  • components/openai/actions/create-image/create-image.mjs
  • components/openai/actions/create-moderation/create-moderation.mjs
  • components/openai/actions/create-thread/create-thread.mjs
  • components/openai/actions/create-transcription/create-transcription.mjs
  • components/openai/actions/delete-file/delete-file.mjs
  • components/openai/actions/list-files/list-files.mjs
  • components/openai/actions/list-messages/list-messages.mjs
  • components/openai/actions/list-run-steps/list-run-steps.mjs
  • components/openai/actions/list-runs/list-runs.mjs
  • components/openai/actions/modify-assistant/modify-assistant.mjs
  • components/openai/actions/retrieve-file-content/retrieve-file-content.mjs
  • components/openai/actions/retrieve-file/retrieve-file.mjs
  • components/openai/actions/retrieve-run-step/retrieve-run-step.mjs
  • components/openai/actions/retrieve-run/retrieve-run.mjs
  • components/openai/actions/send-prompt/send-prompt.mjs
  • components/openai/actions/submit-tool-outputs-to-run/submit-tool-outputs-to-run.mjs
  • components/openai/actions/summarize/summarize.mjs
  • components/openai/actions/translate-text/translate-text.mjs
  • components/openai/actions/upload-file/upload-file.mjs
  • components/openai/package.json
  • components/openai/sources/new-batch-completed/new-batch-completed.mjs
  • components/openai/sources/new-file-created/new-file-created.mjs
  • components/openai/sources/new-fine-tuning-job-created/new-fine-tuning-job-created.mjs
  • components/openai/sources/new-run-state-changed/new-run-state-changed.mjs
Additional comments not posted (9)
components/openai/common/helpers.mjs (3)

Line range hint 3-19: LGTM!

The function is correctly implemented and handles both specific string values and JSON parsing.

The code changes are approved.

22-27: LGTM!

The function is correctly implemented and handles empty strings appropriately.

The code changes are approved.

29-39: LGTM!

The function is correctly implemented, handling various input types and providing appropriate error messages for invalid JSON.

The code changes are approved.

components/openai/common/constants.mjs (1)

48-61: LGTM!

The constant is correctly implemented, providing a clear and extensible format for defining response types.

The code changes are approved.

components/openai/actions/chat/chat.mjs (4)

8-8: LGTM!

The version update is appropriate given the new features and enhancements.

The code changes are approved.

46-47: LGTM!

The description update is clear and provides valuable information about the new JSON Schema option.

The code changes are approved.

47-47: LGTM!

The update is appropriate and aligns with the new structure of CHAT_RESPONSE_FORMAT.

The code changes are approved.

54-66: LGTM!

The method is correctly implemented, enhancing the flexibility and usability of the Chat API.

The code changes are approved.

components/openai/actions/common/common.mjs (1)

153-159: Verify the correctness of constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value.

Ensure that constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value is correctly defined and used.

Run the following script to verify the definition and usage of constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value:

@jcortes jcortes merged commit 5d1e097 into PipedreamHQ:master Aug 29, 2024
9 of 12 checks passed
@coderabbitai coderabbitai bot mentioned this pull request Mar 12, 2025
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@coderabbitai coderabbitai[bot] coderabbitai[bot] left review comments

@lcaresia lcaresia lcaresia approved these changes

Assignees

@jcortes jcortes

Labels
action New Action Request enhancement New feature or request
Projects
Component (Source and Action) Backlog
Archived in project
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

[FEATURE] Add support for structured outputs for OpenAI Actions
2 participants
@jcortes @lcaresia