demilich

no profile record

Submissions

Nemotron-4 340B

research.nvidia.com

3 pointsby demilich2 tahun yang lalu0 comments

comments

2 tahun yang laludiscuss

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

demilich

2 tahun yang laludiscuss

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

2 tahun yang laludiscuss

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

demilich

2 tahun yang laludiscuss

Infinity supports HNSW vector index.

demilich

2 tahun yang laludiscuss

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

demilich

2 tahun yang laludiscuss

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

An implementation: github.com/infiniflow/ragflow

demilich

2 tahun yang laludiscuss

Agreed

demilich

2 tahun yang laludiscuss

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

2 tahun yang laludiscuss

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

demilich

2 tahun yang laludiscuss

Cool! This is really helpful.

demilich

2 tahun yang laludiscuss

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

demilich

2 tahun yang laludiscuss

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.