Skip to content

Feat/ppio rerank #7567

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 6 commits into from
Jun 30, 2025
Merged

Feat/ppio rerank #7567

merged 6 commits into from
Jun 30, 2025

Conversation

cnJasonZ
Copy link
Contributor

What this PR does

Before this PR:

Model provider PPIO have outdated models. Cannot get rerank or embedding models.

After this PR:

Use the most updated models from PPIO as default models. Rerank and embedding models are available now.

Checklist

This checklist is not enforcing, but it's a reminder of items that could be relevant to every PR.
Approvers are expected to review this list.

Release note

1. Use PPIO's most updated and powerful models as default models.
2. PPIO's rerank and embedding models are available now.

@dosubot dosubot bot added kind/feature Models Categorizes an issue or PR as relevant to SIG LLM labels Jun 26, 2025
DeJeune
DeJeune reviewed Jun 26, 2025
View reviewed changes
@DeJeune DeJeune requested a review from eeee0717 June 29, 2025 16:17
@DeJeune DeJeune merged commit 4c988ed into CherryHQ:main Jun 30, 2025
1 check passed
eeee0717 added a commit that referenced this pull request Jun 30, 2025
@eeee0717
Squashed commit of the following:
db3ee13 
commit 21ba35b
Author: SuYao <sy20010504@gmail.com>
Date:   Mon Jun 30 15:17:05 2025 +0800

    fix(ImageGenerationMiddleware): read image binary data (#7681)

    - Replaced direct API call for reading binary images with FileManager's readBinaryImage method to streamline image handling in the ImageGenerationMiddleware.

commit a9a9d88
Author: SuYao <sy20010504@gmail.com>
Date:   Mon Jun 30 13:51:23 2025 +0800

    Fix/gemini (#7659)

    * refactor: update Gemini and OpenAI API clients for improved reasoning model handling

    - Replaced isGeminiReasoningModel with isSupportedThinkingTokenGeminiModel in GeminiAPIClient for better model validation.
    - Enhanced OpenAIAPIClient to support additional configurations for reasoning efforts and thinking budgets based on model type.
    - Introduced new thinking tags for Gemini models in ThinkingTagExtractionMiddleware.
    - Updated model checks in models.ts to streamline reasoning model identification.
    - Adjusted ThinkingButton component to differentiate between Gemini and Gemini Pro models based on regex checks.

    * refactor(GeminiAPIClient): streamline reasoning configuration handling

    - Simplified the logic for returning thinking configuration when reasoningEffort is undefined in GeminiAPIClient.
    - Updated ApiService to include enableReasoning flag for API calls, enhancing control over reasoning capabilities.

    * fix(OpenAIAPIClient): add support for non-flash Gemini models in reasoning configuration

    - Introduced a check for non-flash models in the OpenAIAPIClient to enhance reasoning configuration handling for supported Gemini models.
    - This change ensures that reasoning is correctly configured based on the model type, improving overall model validation.

commit 1034b94
Author: Wang Jiyuan <59059173+EurFelux@users.noreply.github.com>
Date:   Mon Jun 30 10:43:19 2025 +0800

    fix(translate): improve language options with clearer values (#7640)

    * fix(翻译配置): 修正简体中文语言选项的值和标签显示

    将'chinese'改为更明确的'chinese-simplified'

    * style(translate): 统一语言选项的显示格式为规范名称

commit 4c988ed
Author: cnJasonZ <gbdzxalbb@qq.com>
Date:   Mon Jun 30 10:16:22 2025 +0800

    Feat/ppio rerank (#7567)

    * feat: add PPIO rerank and embedding models

    * fix: fix migrate.ts

    * fix: set ppio provider type to openai

    * fix: remove 'ppio' from ProviderType definition

    ---------

    Co-authored-by: suyao <sy20010504@gmail.com>

commit 7b78192
Author: David Zhang <61440144+WAcry@users.noreply.github.com>
Date:   Sun Jun 29 12:14:58 2025 -0700

    chore(OpenAIApiClient): handle empty delta objects in non-streaming esponses (#7658)

    chore(OpenAIApiClient): handle empty delta objects in non-streaming responses

commit b0053b9
Author: SuYao <sy20010504@gmail.com>
Date:   Mon Jun 30 00:15:36 2025 +0800

    fix(models): enhance Doubao model checks to include model.id conditions (#7657)

    - Updated model checks in isFunctionCallingModel, isEmbeddingModel, isVisionModel, and isReasoningModel functions to consider model.id for 'doubao' provider.
    - Improved isOpenAIWebSearchModel to include additional conditions for model.id.

commit 218dcc2
Author: Yiyang Suen <suenyiyang+github@gmail.com>
Date:   Mon Jun 30 00:01:28 2025 +0800

    fix: textarea not resizing back after clearing long input (#7609) (#7632)

    * fix: textarea not resizing back after clearing long input (#7609)

    * fix: text area auto size only when not dragged

commit 8f64c5a
Author: beyondkmp <beyondkmp@gmail.com>
Date:   Sun Jun 29 23:58:24 2025 +0800

    feat: support linux deb (#7652)

commit 9a4c695
Author: Kingsword <kingsword09@gmail.com>
Date:   Sun Jun 29 21:32:05 2025 +0800

    fix: restore message content className logic to resolve search issue (#7651)

commit 486c5c4
Author: Xin Rui <71483384+Konjac-XZ@users.noreply.github.com>
Date:   Sun Jun 29 20:47:17 2025 +0800

    chore: format zh-cn and zh-tw i18n strings with pangu. (#7644)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@DeJeune DeJeune DeJeune approved these changes

@eeee0717 eeee0717 eeee0717 approved these changes

Assignees
No one assigned
Labels
Models Categorizes an issue or PR as relevant to SIG LLM
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@cnJasonZ @DeJeune @eeee0717