[yingfeng]

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 right now it could provide both full text search as well as vector search. As a long term memory for LLMs, vector search alone is evidently not enough, while sparse retrieval is also a MUST to be added. That's why Vespa could attract such funding even under current situation.

[jojoba91]

Is vector database/engine the only partner of LLM? I also heard of RAG and Agent such as LangChain.

[yingfeng]

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