-
Notifications
You must be signed in to change notification settings - Fork 398
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
add gpt4o-mini support #625
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 Looks good to me! Reviewed everything up to f8cc351 in 19 seconds
More details
- Looked at
21
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
1
drafted comments based on config settings.
1. skyvern/forge/sdk/api/llm/config_registry.py:80
- Draft comment:
Please ensure to provide a PR description in future submissions to explain the context and necessity of the changes. - Reason this comment was not posted:
Confidence changes required:33%
The PR adds support for a new model configuration,OPENAI_GPT4O_MINI
, which is similar to the existingOPENAI_GPT4O
but presumably for a smaller version of the model. The configuration specifies that it supports vision and does not add an assistant prefix, which is consistent with the other configurations for OpenAI models in this file. However, the PR description is empty, which is not ideal as it does not provide context or justification for the changes. It would be beneficial to have a description explaining why this change is necessary or what issue it addresses.
Workflow ID: wflow_0ZuyQ5pe5YCcjKqZ
You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 Looks good to me! Incremental review on 7c16e2a in 35 seconds
More details
- Looked at
54
lines of code in2
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_pN7je5Zow6XJjkm4
You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
7c16e2a
to
912b38c
Compare
912b38c
to
add80f4
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on add80f4 in 58 seconds
More details
- Looked at
54
lines of code in2
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_yB5jc9QrLP1qHlUs
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
@@ -1,2 +1,3 @@ | |||
See our [open source quickstart doc](https://github.com/Skyvern-AI/skyvern?tab=readme-ov-file#quickstart). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The link provided in the quickstart-open-source.mdx
seems to point to a non-existent tab or section (readme-ov-file#quickstart
). Please verify and update the link to ensure it directs users to the correct documentation section.
See our [open source quickstart doc](https://github.com/Skyvern-AI/skyvern?tab=readme-ov-file#quickstart). | |
See our [open source quickstart doc](https://github.com/Skyvern-AI/skyvern#quickstart). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on 093e754 in 35 seconds
More details
- Looked at
9
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_4o2a9piShSZFyHwn
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
<img src="https://thumbs.dreamstime.com/b/pug-dog-holding-pliers-screwdriver-behind-old-wooden-sign-text-under-construction-white-background-constructor-92836854.jpg" /> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The image used here is sourced from a stock photo website, which might not be appropriate for official documentation due to potential copyright issues. Consider using an image that is owned by the company or is licensed for free use.
Summary:
Added support for
gpt-4o-mini
model inLLMConfigRegistry
and updated related documentation.Key points:
gpt-4o-mini
model inLLMConfigRegistry
.skyvern/forge/sdk/api/llm/config_registry.py
to registergpt-4o-mini
.OPENAI_API_KEY
,supports_vision=True
, andadd_assistant_prefix=False
.README.md
to listgpt-4o-mini
under supported models.docs/getting-started/quickstart-open-source.mdx
with a link to the open source quickstart documentation.Generated with ❤️ by ellipsis.dev