Upgrade MiniMax default model to MiniMax-M3 in dagworks RAG examples#1620
Open
octo-patch wants to merge 3 commits into
Open
Upgrade MiniMax default model to MiniMax-M3 in dagworks RAG examples#1620octo-patch wants to merge 3 commits into
octo-patch wants to merge 3 commits into
Conversation
Updates the default model returned by `model__minimax()` in the `conversational_rag` and `faiss_rag` dataflows from `MiniMax-M2.7` to `MiniMax-M3`. The base URL (`https://api.minimax.io/v1`) and the OpenAI-compatible client wiring stay the same; only the model ID constant and its references in tests/README change. - contrib/hamilton/contrib/dagworks/conversational_rag/__init__.py: `model__minimax()` now returns `MiniMax-M3`. - contrib/hamilton/contrib/dagworks/faiss_rag/__init__.py: `model__minimax()` now returns `MiniMax-M3`. - Unit tests updated to assert the new model constant and to pass `MiniMax-M3` into mocked chat completion calls. - README config tables and "uses the [MiniMax-...] model" lines refreshed to reference MiniMax-M3. Co-Authored-By: Octopus <liyuan851277048@icloud.com> Signed-off-by: Octopus <liyuan851277048@icloud.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Updates the default MiniMax model in the two dagworks RAG dataflows
(
conversational_rag,faiss_rag) fromMiniMax-M2.7toMiniMax-M3.MiniMax-M3 is the latest generation MiniMax model and replaces M2.7 as the recommended default. It exposes the same OpenAI-compatible Chat Completions interface, so the existing
openai.OpenAI(base_url="https://api.minimax.io/v1", ...)wiring continues to work without code changes — only the model string constant needs to be bumped.Changes
contrib/hamilton/contrib/dagworks/conversational_rag/__init__.py:model__minimax()now returns"MiniMax-M3".contrib/hamilton/contrib/dagworks/faiss_rag/__init__.py:model__minimax()now returns"MiniMax-M3"."MiniMax-M3"into mocked chat completion calls.The
MINIMAX_API_KEYenv var, the OpenAI-compatible base URL, and the@config.when(provider="minimax")switch are all unchanged.Test plan
pytest hamilton/contrib/dagworks/conversational_rag/test_conversational_rag.py hamilton/contrib/dagworks/faiss_rag/test_faiss_rag.py -k "not Integration"— 38 passed (coversTestModelConfig,TestMiniMaxProvider,TestHamiltonDriverConfig, including driver build + end-to-end mocked execution under{"provider": "minimax"}).MINIMAX_API_KEYand run theTestMiniMaxIntegrationclasses to hit the real MiniMax-M3 API.