SKSatvik Kharbindecodeai.hashnode.dev·Apr 21, 2025 · 2 min readQuery Translation Patterns: Advanced RAG“Imagine Google Search but on your personal information” RAG or Retrieval-Augmented Generation is the method of optimizing a vanilla LLM to generate responses based on the personal data it has Retrieved. Parallel Query Retrieval (Fan Out): He...00
SKSatvik Kharbindecodeai.hashnode.dev·Apr 8, 2025 · 7 min readDecoding AI JargonsdEncoder- Encoder in AI terms is a component of the Transformer Architecture which was introduced by the Google Brain team in the year 2017 in their research paper, “ Attention is all you need”. But here we are trying to decode it in simple term usin...00