Viewing profile — yingfeng

RAGFlow v0.17.0 now enables Agentic Reasoning for Deep Research, integrating any LLM — no RLM dependency required.

Hybrid search of bm25,dense vector and sparse vector, and tensor based reranking(ColBERT). Technology details: https://medium.com/@infiniflowai/dense-vector-sparse-vector-...

Because colbert is not an end-to-end solution. As seen for RAGatouille, it has integrated colbertv2 into this repo. However, it's not a database, we implement tensor within infinit…

paradedb could also deliver three-way hybrid search through pg_vector, pg_sparse and pg_search. Compared with paradedb, infinity has following advantages: 1. Performance The perfor…

A noticeble work to demostrate the effectiveness of hybrid search is blended rag by IBM research ( https://arxiv.org/abs/2404.07220 ), which has shown that 3-way hybrid search coul…

There are some vector databases that already include both dense vector search and sparse vector search, such as qdrant. A hybrid search of these 2 does not solve many problems well…

Hi, I'm one of the creators of infinity, and the article has mentioned about the sparse vector vs bm25. While the sparse vector performs well under some evaluations, it is obtained…

From the viewpoint of RAG 2.0, during the stage of indexing or pre-processing, such approaches as knowledge graph is a MUST to resolve such issues as multi hop question answering, …

From 0.8, RAGFlow( https://github.com/infiniflow/ragflow ) will provide no code workflow orchestration. This article describes what kind of graph orchestration engine is needed, an…

RRF is a simple and effective means of fused ranking for multiple recall. Within our open source RAG product RAGFlow( https://github.com/infiniflow/ragflow ), Elasticsearch is curr…

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 structu…

Actually we've tried almost all lof existing open source models for document processing, and none of them performs well for complex documents, especially those having complicated t…

Thanks for your nice suggestion. We train the model using YOLO, but during inference, the model is converted into ONNX and we use ONNXRuntime for the model inference. As a result, …

We've used YOLOv8 as the object detection model, and use some public datasets, such as PubTable, CDLA, together with some private data to train the model. The model on Huggingface …

Hi, buddy, I'm sorry to make you feel like we don't take women's voices into account. We came up with this name because RAG is already a consensus, as an acronym for retrieval augm…

RAG requires at least both dense retrieval as well as sparse retrieval, vector search is used to serve as the former one.

Congratulations! Vespa is by far the best open source search engine even starts from more than twenty years before. The code base is complicated to support web scale search and rig…

What's the relationship between Fenzo and Titan, and when Titan will be made open source?