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

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.

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

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

Infinity looks interesting, but I don't see any mention of support for clustering.

Infinity supports HNSW vector index.

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

An implementation: github.com/infiniflow/ragflow

Agreed

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?

I read the paper and there are some similarities between ZenDB and RAGFlow, but also many differences.

The goal of RAGFlow is to use computer vision models to recognize the structure of a document, including diagrams and tables, and then to slice these structures into appropriate formats, such as table information combined with table definitions into text, which is then sent to the RAG system to be used for retrieval and answering questions.

ZenDB also makes use of computer vision models to understand documents, but it is mainly used to understand the semantic structure of documents, such as headings, phrases, etc., which also involves semantic-based text clustering. ZenDB also defines a query language specifically for querying these semantics. ZenDB is pretty useful to query and summarize long text.

I think some combination of RAGFlow and ZenDB for processing unstructured document data could be interesting to work on.

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

Cool! This is really helpful.

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