Studying AI (4) 썸네일형 리스트형 RAG from scratch (4) 자료 : https://www.youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x Indexing(Indexing techniques for vectorstores) (1) Multi-representation Indexingmake a good summary style indexing to fetch the full documenti.e. distill documents idea from "Proposition Indexing" (https://arxiv.org/pdf/2312.06648) - decouple raw documents and retrieval unit document → split → (via LLMs) make proposit.. RAG from scratch (3) 자료 : https://www.youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x Routing (Logical Routing + Semantic Routing)routing the question (possibily decomposed in th previous step) to the relevant DBs or prompts. 1. Logical Routing(DBs could be Graph DB, Relational DB, Vectorstore)feed the LLM with the knowledge of available DBs → make the LLM to reason and choose which DB to retrieve fromc.. RAG from scratch (2) 자료 : https://www.youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x Query Translationtranslate user's query to improve retrievalwhy? user query is ambiguous → if query is poorly written proper document cannot be retrieved (higher level)step-back question↑Quesiton → re-writing (Multi-query, RAG-fusion)↓sub-question 출처 : https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from.. RAG from scratch (1) 참고자료 :https://www.youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0xhttps://wikidocs.net/book/14314https://docs.smith.langchain.com/Part 1 - Part 4.★ Connecting LLMs to external data ★ - LLMs haven't seen your data- private and recent data are not included RAG : Retrieval Augmented GenerationRAG pipeline : Indexing → Retrieval → Generation stage 1: IndexingIndex external documents into.. 이전 1 다음
