demilich

no profile record

Submissions

Nemotron-4 340B

research.nvidia.com

3 pointsby demilichقبل سنتين0 comments

comments

قبل سنتينdiscuss

https://github.com/infiniflow/infinity, dense vector + sparse vector + fulltext search(BM25) + late interact reranker(Colbert)

demilich

قبل سنتينdiscuss

GraphRAG is to parse data to create a KG and retrieval the information from KB.

RAGFlow is to create a Graph workflow to solve multi-hop question-answering issue.

demilich

قبل سنتينdiscuss

Current RAG is more and more complex, will future LLM or New AI model overthrow the RAG?

demilich

قبل سنتينdiscuss

Infinity supports HNSW vector index.

demilich

قبل سنتينdiscuss

Check https://github.com/infiniflow/infinity which combines vector search and full-text search providing extremely fast search performance.

demilich

قبل سنتينdiscuss

Try RAPTOR: https://arxiv.org/html/2401.18059v1

An implementation: github.com/infiniflow/ragflow

demilich

قبل سنتينdiscuss

Agreed

demilich

قبل سنتينdiscuss

RAGFlow (github.com/infiniflow/ragflow) use OCR/layout recognition/TSR(table structure recognition) to understand the document structure and context. Is there any difference between RAGFlow and ZenDB?

demilich

قبل سنتينdiscuss

Use C++20 modules, take a look at this project: https://github.com/infiniflow/infinity

demilich

قبل سنتينdiscuss

Cool! This is really helpful.

demilich

قبل سنتينdiscuss

Each project has its own detailed requirements and scenarios, and we cannot demand that each project use same library to implement similar functions

demilich

قبل سنتينdiscuss

The recognition of file layout to parse file content is indeed a very innovative idea. Compared to many open-source projects we have seen before, this provides us with new ideas for using RAG to solve problems in the future. I hope the author of this project will continue to update it, so that more people can benefit from it.