Skip to content

fix(ai): cumulative fixes for AI GW #14416

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
Open
wants to merge 14 commits into
base: master
Choose a base branch
from
Open

fix(ai): cumulative fixes for AI GW #14416

wants to merge 14 commits into from

Conversation

fffonion
Copy link
Contributor

@fffonion fffonion commented Apr 14, 2025 •
edited
Loading

Summary

Checklist

  • The Pull Request has tests
  • A changelog file has been created under changelog/unreleased/kong or skip-changelog label added on PR if changelog is unnecessary. README.md
  • There is a user-facing docs PR against https://github.com/Kong/docs.konghq.com - PUT DOCS PR HERE

Issue reference

AG-258

tysoekong and others added 8 commits April 17, 2025 13:50
@tysoekong @fffonion @oowl
feat(llm): support Bedrock and Gemini native format (#10820)
ac2bfe3 
AG-83

Co-authored-by: Wangchong Zhou <wangchong@konghq.com>
Co-authored-by: Jun Ouyang <ouyangjun1999@gmail.com>
@tysoekong @fffonion
fix(llm): add restrictions on new llm_format field (#11539)
adca236 
Follow up of AG-83 (#10820)
@tysoekong @oowl
@github-actions @fffonion
fix(llm): send analytics before log phase (#11384)
6d7ee36 
AG-196

Co-authored-by: Jun Ouyang <ouyangjun1999@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@fffonion
fix(llm): issue of template not being resolved correctly and support …
b2dc48d 
…nested fields (#11596)

AG-236
@tysoekong @fffonion
fix(ai): do not replace chunked response with native formats
9f69a72 
Streaming was still coming back in OpenAI format for the new "native" bedrock and gemini llm_format config settings.

AG-233
@fffonion
fix(llm): fix preserve mode (#11677)
aec6d2f 
AG-238
@fffonion
fix(llm): fix issue of SSE body may have extra trailing in some cases (…
6648289 
…#11705)

Especially when ai-semantic-cache is used with ai-proxy, the first
uncached stream request could have duplicate (as trailing) data at
the end

Co-authored-by: Jun Ouyang <ouyangjun1999@gmail.com>

AG-240
@oowl @fffonion
fix(llm): seperate user specified value from plugin conf
2803608 
AG-252 FTI-6603
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees

@fffonion fffonion

Labels
cherry-pick kong-ee schedule this PR for cherry-picking to kong/kong-ee core/clustering plugins/ai-prompt-decorator plugins/ai-prompt-guard plugins/ai-proxy plugins/ai-request-transformer plugins/ai-response-transformer schema-change-noteworthy size/XXL
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@fffonion @tysoekong @oowl