feat: add MiniMax as first-class LLM provider - #1040
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Add MiniMax (https://www.minimaxi.com) as a new LLM vendor with full integration into the OpenAI-compatible dialect system. New files: - MiniMaxIcon.tsx: SVG icon component - minimax.vendor.ts: Vendor definition (dialect, key validation, CSF) - MiniMaxServiceSetup.tsx: Settings UI with API key + host fields - minimax.models.ts: Model definitions for M2.7, M2.5, M2.5-highspeed (204K context, function calling, JSON mode, vision) - minimax.models.test.ts: 24 unit tests for model filter/description/sort - minimax.integration.test.ts: 24 integration tests for vendor config Modified files: - vendors.registry.ts: Register 'minimax' vendor ID - LLMVendorIcon/Setup/IconSprite: Wire icon and setup components - openai.access.ts: Add 'minimax' dialect with Bearer auth - listModels.dispatch.ts: Hardcoded models (no /v1/models API) - chatGenerate.dispatch.ts: Add 'minimax' to dialect switches - env.server.ts: Register MINIMAX_API_KEY env var - backend capabilities: Add hasLlmMiniMax flag MiniMax provides OpenAI-compatible chat completions at https://api.minimax.io/v1 but has no models listing endpoint, so models are hardcoded following the Perplexity pattern.
|
Someone is attempting to deploy a commit to the Token Fabrics Pro Team on Vercel. A member of the Team first needs to authorize it. |
Owner
|
Considering merge of this one if we see interest or requests by our users. |
Author
|
Thanks for considering, @enricoros! Happy to address any feedback if you'd like changes before merging. The implementation follows the same OpenAI-compatible pattern used by other vendors in the codebase. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add MiniMax as a new LLM vendor with full integration into big-AGI's OpenAI-compatible dialect system.
MINIMAX_API_KEY), backend capabilities flag/v1/modelsendpoint, so models follow the Perplexity pattern with hardcoded descriptionsFiles changed (16 files, 465 additions)
New files (6):
MiniMaxIcon.tsx- SVG icon componentminimax.vendor.ts- Vendor definition (dialect, key validation, CSF support)MiniMaxServiceSetup.tsx- Settings UI with API key + optional host overrideminimax.models.ts- Model definitions with filter, description mapping, and sortminimax.models.test.ts- 24 unit testsminimax.integration.test.ts- 24 integration testsModified files (10):
vendors.registry.ts- Registerminimaxvendor IDLLMVendorIcon.tsx/LLMVendorSetup.tsx/LLMVendorIconSprite.tsx- Wire icon and setup componentsopenai.access.ts- Addminimaxdialect with Bearer token auth and multi-key supportlistModels.dispatch.ts- Hardcoded models dispatch (no API fetch)chatGenerate.dispatch.ts- Addminimaxto both dialect switch groupsenv.server.ts- RegisterMINIMAX_API_KEYenvironment variablestore-backend-capabilities.ts/backend.router.ts- AddhasLlmMiniMaxcapability flagTest plan
tsc --noEmitpasses (only pre-existing errors in news.data.tsx)npx tsx minimax.models.test.ts)npx tsx minimax.integration.test.ts)MINIMAX_API_KEYMiniMax API Notes
https://api.minimax.io/v1/v1/modelsendpoint (returns 404) - hardcoded model descriptions used instead