MaxCode: Add RAG knowledge base — JAX/Flax docs and targeted migration rules#23
Open
MaxCode: Add RAG knowledge base — JAX/Flax docs and targeted migration rules#23
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
…n rules Adds 55 new RAG source documents to improve migration quality: Generic sources (22 files): - JAX/Flax documentation: module API, layers API, setup vs compact, gotchas, lax primitives, attention patterns - Flash Linear Attention (FLA) library references: gated delta net layers/models, l2norm, layernorm gated, rotary, short conv, ops - MaxText reference implementations: attentions, embeddings, linears, normalizations, Qwen3/DeepSeek model layers Targeted sources (30 files): - Migration-specific rules covering: dtype fidelity, causal conv1d, config dataclasses, stop_gradient, mixed precision, KV cache, encoder-decoder cache, Flax checkpoint API, train/eval mode, float32 softmax upcast, fused QKV projection, weight init patterns, class hierarchy preservation, source faithfulness, triangular masking, WY representation, and more Also updates rag_agent.py and vector_db.py to support the expanded corpus with targeted RAG retrieval. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
gvanica
force-pushed
the
split/1-rag-knowledge-base
branch
from
d1c6e43 to
53a3c6d
Compare
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
Adds 55 new RAG source documents to the MaxCode knowledge base, significantly expanding the corpus available for retrieval-augmented generation during PyTorch-to-JAX migrations. Also updates the RAG agent and vector DB to support the expanded corpus with targeted retrieval.
Generic sources (22 files)
Reference implementations and documentation that the LLM retrieves as context during conversion:
Targeted sources (30 files)
Focused migration rules that address specific conversion pitfalls discovered during iterative testing:
Infrastructure changes
Test plan
Split from #17 — PR 1 of 8