Skip to content

New gpt-image-1 model for openai_conversation.generate_image action #38826

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

Open
wants to merge 5 commits into
base: next
Choose a base branch
from

Conversation

Shulyaka
Copy link
Contributor

@Shulyaka Shulyaka commented Apr 30, 2025

Proposed change

Latest image model gpt-image-1 for openai_conversation.generate_image action: https://openai.com/index/image-generation-api

Type of change

  • Spelling, grammar or other readability improvements (current branch).
  • Adjusted missing or incorrect information in the current documentation (current branch).
  • Added documentation for a new integration I'm adding to Home Assistant (next branch).
  • Added documentation for a new feature I'm adding to Home Assistant (next branch).
  • Removed stale or deprecated documentation.

Additional information

Checklist

  • This PR uses the correct branch, based on one of the following:
    • I made a change to the existing documentation and used the current branch.
    • I made a change that is related to an upcoming version of Home Assistant and used the next branch.
  • The documentation follows the Home Assistant documentation standards.

Summary by CodeRabbit

  • Documentation
    • Updated image generation parameters with new size, quality, background, and moderation options.
    • Expanded details on response data, including local image saving and media source usage.
    • Added guidance on organization verification for image model access and fallback procedures.
    • Refreshed example usage to demonstrate new parameters and values.

@Shulyaka Shulyaka requested a review from balloob as a code owner April 30, 2025 16:37
@home-assistant home-assistant bot added has-parent This PR has a parent PR in a other repo next This PR goes into the next branch labels Apr 30, 2025
Copy link

netlify bot commented Apr 30, 2025

Deploy Preview for home-assistant-docs ready!

Name Link
🔨 Latest commit eb0d458
🔍 Latest deploy log https://app.netlify.com/sites/home-assistant-docs/deploys/681267042be5bf0008663768
😎 Deploy Preview https://deploy-preview-38826--home-assistant-docs.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

Copy link
Contributor

coderabbitai bot commented Apr 30, 2025

📝 Walkthrough

Walkthrough

The documentation for the openai_conversation.generate_image action was updated to reflect changes in parameter options and defaults, including expanded values for size and quality, and the addition of new parameters background and moderation. The example YAML configuration was revised to demonstrate the updated usage. The response section now describes that generated images are saved locally and can be used as media sources. An additional note explains the requirement for OpenAI organization verification to access certain models, with fallback behavior and repair issue handling described.

Changes

File(s) Change Summary
source/_integrations/openai_conversation.markdown Updated documentation for generate_image action: revised parameter options and defaults, added background and moderation parameters, updated example YAML, expanded response description, and added a section on OpenAI organization verification and model fallback behavior.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant openai_conversation Action
    participant OpenAI API
    participant Local Storage
    participant Media Source

    User ->> openai_conversation Action: Call generate_image (with parameters)
    openai_conversation Action ->> OpenAI API: Request image generation (with parameters)
    OpenAI API -->> openai_conversation Action: Return generated image URL
    openai_conversation Action ->> Local Storage: Save image locally
    openai_conversation Action ->> Media Source: Make image available as media source
    openai_conversation Action -->> User: Return image URL and local path

    Note over openai_conversation Action,OpenAI API: If organization not verified, fallback to older model and raise repair issue
Loading

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.
    • 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.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in 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 or @coderabbitai title 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.

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

🧹 Nitpick comments (3)
source/_integrations/openai_conversation.markdown (3)

103-106: Ensure consistent quoting in YAML examples
The initial example leaves values unquoted, while later examples wrap similar strings in quotes. For consistency and to avoid YAML parsing corner-cases, consider quoting all string-type parameters:

-  quality: high
+  quality: "high"
-  background: opaque
+  background: "opaque"
-  moderation: auto
+  moderation: "auto"

110-111: Enhance clarity on where images are stored
Nice callout that the image is saved locally. To help users locate it, you might add a link to the Media Source docs or mention the default path (e.g., media/openai_conversation/).


114-115: Fix grammar and remove duplicate word
There’s a duplicated “the” and “fallback” should be two words when used as a verb. Please apply:

- If you don't have access the the model, the `generate_image` action will fallback to the previous `dall-e-3` model and a [repair issue](/integrations/repairs/) will be raised.
+ If you don't have access to the model, the `generate_image` action will fall back to the previous `dall-e-3` model, and a [repair issue](/integrations/repairs/) will be raised.
🧰 Tools
🪛 LanguageTool

[grammar] ~114-~114: The verb form ‘access’ does not seem to be suitable in this context.
Context: ...rganization/general). If you don't have access the the model, the generate_image act...

(HAVE_VB)


[duplication] ~114-~114: Possible typo: you repeated a word.
Context: ...tion/general). If you don't have access the the model, the generate_image action will...

(ENGLISH_WORD_REPEAT_RULE)


[grammar] ~114-~114: The word “fallback” is a noun. The verb is spelled with a space.
Context: ...model, the generate_image action will fallback to the previous dall-e-3 model and a ...

(NOUN_VERB_CONFUSION)

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 657569e and 6a79839.

📒 Files selected for processing (1)
  • source/_integrations/openai_conversation.markdown (2 hunks)
🧰 Additional context used
🪛 LanguageTool
source/_integrations/openai_conversation.markdown

[grammar] ~114-~114: The verb form ‘access’ does not seem to be suitable in this context.
Context: ...rganization/general). If you don't have access the the model, the generate_image act...

(HAVE_VB)


[duplication] ~114-~114: Possible typo: you repeated a word.
Context: ...tion/general). If you don't have access the the model, the generate_image action will...

(ENGLISH_WORD_REPEAT_RULE)


[grammar] ~114-~114: The word “fallback” is a noun. The verb is spelled with a space.
Context: ...model, the generate_image action will fallback to the previous dall-e-3 model and a ...

(NOUN_VERB_CONFUSION)

🪛 markdownlint-cli2 (0.17.2)
source/_integrations/openai_conversation.markdown

107-107: Fenced code blocks should be surrounded by blank lines
null

(MD031, blanks-around-fences)

⏰ Context from checks skipped due to timeout of 90000ms (3)
  • GitHub Check: Redirect rules - home-assistant-docs
  • GitHub Check: Header rules - home-assistant-docs
  • GitHub Check: Pages changed - home-assistant-docs
🔇 Additional comments (1)
source/_integrations/openai_conversation.markdown (1)

91-94: Verify parameter table against official API docs
Ensure that the new valid values and default (auto) for size, quality, background, and moderation exactly match the OpenAI Image Generation API. Consider highlighting the default values visually (e.g., bold or italics) to make them stand out in the table.

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

🧹 Nitpick comments (2)
source/_integrations/openai_conversation.markdown (2)

96-108: Surround fenced code blocks with blank lines
markdownlint (MD031) expects blank lines before and after fenced code blocks. To improve readability and satisfy the linter, add a blank line above {% raw %} and below the closing backticks.

Suggested diff:

-{% raw %}
-```yaml
+ 
+{% raw %}
+
+```yaml
   action: openai_conversation.generate_image
   data:
     config_entry: abce6b8696a15e107b4bd843de722249
     prompt: "Cute picture of a dog chasing a herd of cats"
     size: 1024x1024
     quality: high
     background: opaque
     moderation: auto
     response_variable: generated_image
-```
-{% endraw %}
+```
+ 
+{% endraw %}
🧰 Tools
🪛 markdownlint-cli2 (0.17.2)

97-97: Fenced code blocks should be surrounded by blank lines
null

(MD031, blanks-around-fences)


107-107: Fenced code blocks should be surrounded by blank lines
null

(MD031, blanks-around-fences)


103-106: Quote YAML values for consistency
In the first example block, the values for quality, background, and moderation are unquoted, whereas in the later automation snippet they appear in quotes. To avoid confusion, quote all string-valued fields in the snippet:

-  quality: high
+  quality: "high"
-  background: opaque
+  background: "opaque"
-  moderation: auto
+  moderation: "auto"
📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 6a79839 and 1a13916.

📒 Files selected for processing (1)
  • source/_integrations/openai_conversation.markdown (2 hunks)
🧰 Additional context used
🪛 LanguageTool
source/_integrations/openai_conversation.markdown

[grammar] ~114-~114: The word “fallback” is a noun. The verb is spelled with a space.
Context: ...model, the generate_image action will fallback to the previous dall-e-3 model and a ...

(NOUN_VERB_CONFUSION)

🪛 markdownlint-cli2 (0.17.2)
source/_integrations/openai_conversation.markdown

107-107: Fenced code blocks should be surrounded by blank lines
null

(MD031, blanks-around-fences)

⏰ Context from checks skipped due to timeout of 90000ms (3)
  • GitHub Check: Redirect rules - home-assistant-docs
  • GitHub Check: Header rules - home-assistant-docs
  • GitHub Check: Pages changed - home-assistant-docs
🔇 Additional comments (2)
source/_integrations/openai_conversation.markdown (2)

91-94: Verify parameter options and defaults against OpenAI API docs
The table now supports new values for size, quality, background, and moderation. Please double-check that these options and their defaults (auto) exactly match the official OpenAI image-generation API at https://platform.openai.com/docs/models/gpt-image-1.


110-110: Approve saving generated images locally
Great clarification that the url field still holds the direct link and that images are now also stored in local media files via the media_source integration. This helps users understand how to reference generated images in automations and dashboards.

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
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

🧹 Nitpick comments (1)
source/_integrations/openai_conversation.markdown (1)

110-111: Refine response data description wording

The phrasing “saved into local media files” is a bit awkward. You might reword it to something like:

The response data field `url` will contain the generated image’s URL. The image is also saved locally and registered as a [media source](/integrations/media_source/).

This improves clarity around where the file lives and how to access it.

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 1a13916 and fb1e43c.

📒 Files selected for processing (1)
  • source/_integrations/openai_conversation.markdown (2 hunks)
🧰 Additional context used
🪛 markdownlint-cli2 (0.17.2)
source/_integrations/openai_conversation.markdown

107-107: Fenced code blocks should be surrounded by blank lines
null

(MD031, blanks-around-fences)

⏰ Context from checks skipped due to timeout of 90000ms (3)
  • GitHub Check: Redirect rules - home-assistant-docs
  • GitHub Check: Header rules - home-assistant-docs
  • GitHub Check: Pages changed - home-assistant-docs
🔇 Additional comments (3)
source/_integrations/openai_conversation.markdown (3)

91-94: Confirm updated parameter options for generate_image action

The table correctly reflects the new size and quality values and introduces the background and moderation parameters with appropriate defaults. Please verify that these match the official OpenAI documentation and stay consistent with other Home Assistant integration docs.


103-105: Verify example YAML for new parameters

The example now includes quality, background, and moderation fields matching the updated table. Consider adding a brief inline note that omitting these fields will default to auto, to help readers understand default behavior.


112-114: Approve organization verification fallback note

The “fall back” phrasing is now correct, and the section clearly explains the need for organization verification, the fallback to dall-e-3, and the resulting repair issue. This aligns with our previous feedback.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
has-parent This PR has a parent PR in a other repo next This PR goes into the next branch
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant