Tag: LLM
Found 3 related posts
-
Understand RAG in One Article: The Complete Technical Flow from Indexing to Retrieval-Augmented Generation
A plain-English guide to the two core pipelines of RAG: offline indexing and online retrieval-generation, including chunking, embeddings, vector databases, re-ranking, and prompt assembly
Read More -
OpenAI API Protocol Complete Guide - The Universal Standard for LLM Application Development
A detailed guide to OpenAI API protocol parameters, input/output formats, streaming vs non-streaming responses, and framework integrations like Spring AI and LangChain
Read More -
Transformer: The Brain of Large Language Models - Explained with a Library Analogy
Using a library search analogy to explain the core principles of the Transformer architecture in plain language, including attention mechanism, Q/K/V, multi-head attention, and positional encoding
Read More