feat(openmemory-py): upgrade MiniMax default chat model to M3#184
Open
octo-patch wants to merge 1 commit into
Open
feat(openmemory-py): upgrade MiniMax default chat model to M3#184octo-patch wants to merge 1 commit into
octo-patch wants to merge 1 commit into
Conversation
Upgrade the MiniMax adapter default chat model from MiniMax-M2.7 to the new MiniMax-M3 flagship. M2.7 and M2.7-highspeed remain available as explicit alternatives via the `model=` argument or `OM_MINIMAX_MODEL` env. - src/openmemory/ai/minimax.py: change fallback default to "MiniMax-M3" - tests/test_minimax.py: update default-model assertion and switch the custom / integration test models to MiniMax-M2.7-highspeed (the still-supported fast variant) - README.md: update the chat-model availability note for the minimax section
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Upgrade the
MiniMaxadapter inopenmemory-pyto default to the newflagship
MiniMax-M3model.MiniMax-M2.7andMiniMax-M2.7-highspeedremain available as explicit alternatives.
Changes
packages/openmemory-py/src/openmemory/ai/minimax.py: change the fallbackdefault chat model from
MiniMax-M2.7toMiniMax-M3(still overridablevia the
model=argument orOM_MINIMAX_MODELenv var).packages/openmemory-py/tests/test_minimax.py:MiniMax-M3.MiniMax-M2.7-highspeed, the still-supported low-latency variant.packages/openmemory-py/README.md: refresh the minimax section to listMiniMax-M3(default),MiniMax-M2.7, andMiniMax-M2.7-highspeed.Why
MiniMax-M3is the current flagship chat model. Pointing the default at itmeans new users get the latest capabilities (longer context, better quality)
out of the box, while users who pin a specific model can still pick the
M2.7 variants.
Testing
pytest tests/test_minimax.py -k "not Integration"— all 24 unit testspass.
MiniMax-M3(default) andMiniMax-M2.7-highspeedagainst
https://api.minimax.io/v1— both are accepted by the API.No changes to embeddings, base URL, env vars, or temperature handling.