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.

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

feat(blocks): Add new openrouter models #8905

Merged
merged 2 commits into from
Dec 9, 2024

Conversation

Torantulino
Copy link
Member

@Torantulino Torantulino commented Dec 6, 2024

Summary:
This PR removes the GEMINI_FLASH_1_5_EXP model (due to inference on OpenRouter not working) and introduces several new models to the LlmModel enum. Corresponding updates have been made to the metadata configurations and block cost settings to reflect the changes.

Key Changes:

  1. Removed Models:

    • GEMINI_FLASH_1_5_EXP
  2. Added New Models:

    • QWEN_QWQ_32B_PREVIEW
    • NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B
    • NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B
    • AMAZON_NOVA_LITE_V1
    • AMAZON_NOVA_MICRO_V1
    • AMAZON_NOVA_PRO_V1
    • MICROSOFT_WIZARDLM_2_8X22B
    • GRYPHE_MYTHOMAX_L2_13B
  3. Metadata Updates:

    • Added metadata entries for the new models with a max output tokens of 4,000 tokens.
  4. Cost Configuration Updates:

    • Defined block costs for the newly added models:
      • QWEN_QWQ_32B_PREVIEW: 2 credits
      • All other new models: 1 credit

Testing:

  • Verified that all models can be called without errors with the AI Text generator block

@Torantulino Torantulino requested review from a team as code owners December 6, 2024 23:38
@Torantulino Torantulino requested review from kcze and aarushik93 and removed request for a team December 6, 2024 23:38
Copy link
Contributor

github-actions bot commented Dec 6, 2024

This PR targets the master branch but does not come from dev or a hotfix/* branch.

Automatically setting the base branch to dev.

@github-actions github-actions bot changed the base branch from master to dev December 6, 2024 23:38
@Torantulino Torantulino changed the title Toran/open 2145 add new openrouter models feat(blocks): Add new openrouter models Dec 6, 2024
Copy link

netlify bot commented Dec 6, 2024

Deploy Preview for auto-gpt-docs ready!

Name Link
🔨 Latest commit 11ad07d
🔍 Latest deploy log https://app.netlify.com/sites/auto-gpt-docs/deploys/67538b03ca35e1000840df4e
😎 Deploy Preview https://deploy-preview-8905--auto-gpt-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

codecov bot commented Dec 6, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Please upload report for BASE (dev@b62f411). Learn more about missing BASE report.

Additional details and impacted files
@@          Coverage Diff           @@
##             dev    #8905   +/-   ##
======================================
  Coverage       ?   58.16%           
======================================
  Files          ?      106           
  Lines          ?     5765           
  Branches       ?      720           
======================================
  Hits           ?     3353           
  Misses         ?     2306           
  Partials       ?      106           
Flag Coverage Δ
Linux 57.86% <ø> (?)
Windows 54.64% <ø> (?)
forge 58.03% <ø> (?)
macOS 57.03% <ø> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@aarushik93 aarushik93 added this pull request to the merge queue Dec 9, 2024
Merged via the queue into dev with commit 1a85eb1 Dec 9, 2024
27 checks passed
@aarushik93 aarushik93 deleted the toran/open-2145-add-new-openrouter-models branch December 9, 2024 12:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants