Hi, thanks for maintaining this curated list. It has been a helpful reference when navigating embedding models and related tooling.
I would like to suggest adding WFGY ProblemMap as a practical resource under “Implementations and Tools” (or any section you think fits better).
WFGY ProblemMap is an open source diagnostic map for RAG and LLM pipelines. It organizes common real world failure modes into 16 clearly defined problems and provides concrete fix patterns. A large portion of the content is directly about embedding and retrieval pitfalls seen in production, such as metric mismatch, normalization issues, chunking to embedding contract breaks, and vector store related degradation.
Link:
https://github.com/onestardao/WFGY/tree/main/ProblemMap
If it sounds relevant, a short entry could be:
WFGY ProblemMap: 16 problem map for debugging embeddings and retrieval failures in RAG and LLM pipelines
If you prefer, I can also open a PR in the format you want.
Hi, thanks for maintaining this curated list. It has been a helpful reference when navigating embedding models and related tooling.
I would like to suggest adding WFGY ProblemMap as a practical resource under “Implementations and Tools” (or any section you think fits better).
WFGY ProblemMap is an open source diagnostic map for RAG and LLM pipelines. It organizes common real world failure modes into 16 clearly defined problems and provides concrete fix patterns. A large portion of the content is directly about embedding and retrieval pitfalls seen in production, such as metric mismatch, normalization issues, chunking to embedding contract breaks, and vector store related degradation.
Link:
https://github.com/onestardao/WFGY/tree/main/ProblemMap
If it sounds relevant, a short entry could be:
WFGY ProblemMap: 16 problem map for debugging embeddings and retrieval failures in RAG and LLM pipelines
If you prefer, I can also open a PR in the format you want.