Skip to content
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

Support TTS and Speech2Text for Model Provider GPUStack #12381

Merged
merged 2 commits into from
Jan 7, 2025
Merged

Support TTS and Speech2Text for Model Provider GPUStack #12381

merged 2 commits into from
Jan 7, 2025

Conversation

alexcodelf
Copy link
Contributor

@alexcodelf alexcodelf commented Jan 6, 2025 •
edited
Loading

Summary

Checklist

Important

Please review the checklist below before submitting your pull request.

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

Type of Change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update, included: Dify Document
  • Improvement, including but not limited to code refactoring, performance optimization, and UI/UX improvement
  • Dependency upgrade

Testing Instructions:

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration.

  1. Install GPUStack and deploy the faster-whisper-medium Speech-to-Text model, cosyvoice-300m-sft model in GPUStack.
  2. Set GPUSTACK_SERVER_URL and GPUSTACK_API_KEY as in api/tests/integration_tests/.env.example
  3. Run the integration tests.

@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. ⚙️ feat:model-runtime 🐞 bug Something isn't working labels Jan 6, 2025
@crazywoola
Copy link
Member

Please fix the lint by running dev/reformat. :)

@alexcodelf
Copy link
Contributor Author

Please fix the lint by running dev/reformat. :)请通过运行 dev/reformat 来修复 lint 问题。 :)

image
I've already run the linter and found no errors, but I don't understand why the lint action is still failing.

@crazywoola
Copy link
Member

Never mind I have fixed for you.

@alexcodelf
Copy link
Contributor Author

Got it, ty :D

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Jan 7, 2025
@crazywoola crazywoola merged commit 2bb521b into langgenius:main Jan 7, 2025
5 checks passed
@crazywoola crazywoola mentioned this pull request Jan 7, 2025
Open
64 tasks
@crazywoola
Copy link
Member

crazywoola commented Jan 7, 2025 •
edited
Loading

These changes only applies for version under v1.0, we will release v1.0 soon. You might need to move these changes to this repo https://github.com/langgenius/dify-official-plugins/tree/main/models according to #12381 as well.

This was referenced Jan 7, 2025
Merged
Open
@alexcodelf alexcodelf mentioned this pull request Jan 7, 2025
Merged
Scorpion1221 added a commit to yybht155/dify that referenced this pull request Jan 11, 2025
@Scorpion1221
Merge commit 'c236f05f4b575884b42fc45819ad71b05a22115c'
9a4ecc0 
* commit 'c236f05f4b575884b42fc45819ad71b05a22115c': (135 commits)
  chore: bump version to 0.15.0 (langgenius#12297)
  refactor: enhance API token validation with session locking and last used timestamp update (langgenius#12426)
  Fix newline characters in tables during document parsing (langgenius#12112)
  fix:deepseek tool call not working correctly (langgenius#12437)
  add fish-speech-1.5 from siliconflow (langgenius#12425)
  chore(docker/.env.example): Add TOP_K_MAX_VALUE to the `.env.example`… (langgenius#12422)
  refactor: use tiktoken for token calculation (langgenius#12416)
  fix: [PromptEditorHeightResizeWrap] Bug  langgenius#12410  (langgenius#12406)
  Fixes langgenius#12414: Add cheaper model and long context model for Qwen2.5-72B-Instruct from siliconflow (langgenius#12415)
  Support TTS and Speech2Text for Model Provider GPUStack (langgenius#12381)
  mark deprecated models in siliconflow langgenius#12399 (langgenius#12405)
  fix: http method can be upper case and lower case close langgenius#11877 (langgenius#12401)
  fix: enhance chunk list management with new invalidation keys and imp… (langgenius#12396)
  [Fix] revert sagemaker llm to support model hub (langgenius#12378)
  sandbox doesn't provide auto disable log (langgenius#12388)
  feat: support config top max value by env (langgenius#12375)
  chore: chat app textarea auto focus (langgenius#12366)
  feat: support configuration of refresh token expiration by environment variable (langgenius#12335)
  fix: resolve issue with the opening statement generated by the `AutomaticRes` component failing to sync between states. (langgenius#12349)
  Fix the issue where `TextGeneration` component does not correctly clear input data. (langgenius#12351)
  ...

# Conflicts:
#	api/core/helper/code_executor/code_executor.py
#	api/poetry.lock
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@crazywoola crazywoola crazywoola approved these changes

Assignees
No one assigned
Labels
🐞 bug Something isn't working ⚙️ feat:model-runtime lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Add GPUStack as a Model Provider in Dify
2 participants
@alexcodelf @crazywoola