/tags/rag/ Recent content in Rag on 4sh.dev /images/Ash-Drawing.jpg /images/Ash-Drawing.jpg Hugo -- 0.148.1 en-us Mon, 28 Oct 2024 00:00:00 +0000 /posts/2024/an-opinionated-rag-agent/ Mon, 28 Oct 2024 00:00:00 +0000 /posts/2024/an-opinionated-rag-agent/ <p><a href="https://arxiv.org/abs/2310.11511">Self-RAG</a> (Self-Reflective Retrieval-Augmented Generation) is a framework that combines the benefits of retrieval-augmented generation (RAG) with self-reflection, allowing large language models (LLMs) to adaptively retrieve passages on-demand and generate more accurate responses.</p> <p>Langgraph recently published a <a href="https://langchain-ai.github.io/langgraph/tutorials/rag/langgraph_self_rag_local/">blog post</a> on <em>Self-RAG</em> with their own implementation.</p> <p>I really like the idea of validating the retrieved information. In that past I have noticed that, while vector databases will return documents that usually match the input query string, some may contain irrelevant content. Having the ability to validate and correct this is a great feature for any RAG setup.</p>