demilich

no profile record

投稿

Nemotron-4 340B

research.nvidia.com

3 ポイント·投稿者 demilich·2 年前·0 コメント

·2 年前·議論

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

demilich

·2 年前·議論

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 年前·議論

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

demilich

·2 年前·議論

Infinity supports HNSW vector index.

demilich

·2 年前·議論

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

demilich

·2 年前·議論

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

An implementation: github.com/infiniflow/ragflow

demilich

·2 年前·議論

Agreed

demilich

·2 年前·議論

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 年前·議論

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

demilich

·2 年前·議論

Cool! This is really helpful.

demilich

·2 年前·議論

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 年前·議論

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.