InGenerative AIbySweety Tripathi·Aug 6Inside the Final Layer: Logits, Sampling, and Structured Outputs in LLMsHow raw model scores become words, valid JSON, and filtered responses one token at a time.A response icon1A response icon1
InGoPenAIbySweety Tripathi·Aug 3Your RAG Pipeline Has No Idea If It’s Working : Here’s How to Fix ThatRAG Evaluation Guide
InGoPenAIbySweety Tripathi·Aug 1Hybrid Search : Combining BM25, Dense, and Sparse VectorsWe have already covered keyword search and contextual retrieval in this series, and if you read both, you already know where this is…
InGenerative AIbySweety Tripathi·Jul 14Building Your Own Tokenizer for Medical and Legal DocumentsToday I want to talk about a part of the LLM pipeline that most people never check, but it breaks a lot of domain specific apps: The…A response icon1A response icon1
InCoinmonksbySweety Tripathi·Jul 13Contextual Retrieval: Anthropic’s Method for Cutting RAG FailuresIntroduction
In𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨bySweety Tripathi·Jun 1TurboVec: Fit 10 Million Vectors in 4 GB : The RAG Index That Changes EverythingHi Everyone 👋
InGenerative AIbySweety Tripathi·Apr 13I Stopped Using Vector Databases for RAG : PageIndex Vectorless RAGIf you have been building RAG systems for a while, you know the frustration. You spend hours setting up embeddings, tuning chunk sizes…A response icon3A response icon3
InArtificial Intelligence in Plain EnglishbySweety Tripathi·Feb 7Parameter Efficient Fine Tuning with LoRA: A Complete Guide (Part 1)Introduction
InGoPenAIbySweety Tripathi·Jan 19RAG — Complete Tutorial: PART 07Chunking Strategies in RAG with LangChain