feat: add MiniMax as alternative LLM provider (default: M3)#192
Open
octo-patch wants to merge 2 commits into
Open
feat: add MiniMax as alternative LLM provider (default: M3)#192octo-patch wants to merge 2 commits into
octo-patch wants to merge 2 commits into
Conversation
… and mongostory - Add LLM provider abstraction (getLLMModel) to both apps - Support MiniMax-M2.7 and MiniMax-M2.7-highspeed via OpenAI-compatible API - Configurable via LLM_PROVIDER env var (openai/xai default, minimax) - Update READMEs with MiniMax setup instructions - Add unit tests (15 tests) and integration tests (6 tests)
- Set MiniMax-M3 as the default model in both apps' provider factories - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Update unit tests to assert M3 as default - Update integration tests to exercise M3 - Update READMEs with M3 capabilities (512K context, 128K max output, image input)
octo-patch
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 an alternative LLM provider for two showcase apps (
vercel_sdk_hr_agentandmongostory), with MiniMax-M3 set as the default. Demonstrates how the latest MiniMax model can power diverse GenAI use cases with MongoDB.Changes
vercel_sdk_hr_agent (HR Team Matcher)
utils/llm-provider.ts— provider factory that selects between OpenAI and MiniMax based onLLM_PROVIDERenv var; default MiniMax model isMiniMax-M3app/api/build-team/route.tsto use the provider abstraction instead of hardcoded OpenAImongostory (Content Management Platform)
lib/llm-provider.ts— provider factory that selects between xAI/Grok and MiniMax; default MiniMax model isMiniMax-M3getLLMModel()instead of directxai()calls@ai-sdk/openaidependency for MiniMax OpenAI-compatible APITests
MiniMax-M3as defaultMiniMax-M3(basic chat, tool calling, structured output, streaming) and keep oneMiniMax-M2.7-highspeedcheck for the lower-latency aliasConfiguration
To use MiniMax, set:
Supported models:
MiniMax-M3— default; 512K context, up to 128K output tokens, image inputMiniMax-M2.7— previous generationMiniMax-M2.7-highspeed— previous-generation low-latency variantAPI Documentation