Skip to content

Contents:

  • Overview of RAG and the Two-Stage Pipeline
  • Building RAG Pipelines: A Practical Guide
  • Computational Complexity Analysis of RAG Systems
  • Overview
  • The Hard Negative Problem
  • Expert Perspectives: Architectures, Applications, and Trade-offs
  • Benchmarks and Datasets for Retrieval and Re-ranking
  • Comprehensive Comparison of Retrieval, Reranking, and RAG Libraries
  • Literature Overview
  • Stage 1: Retrieval Methods
    • Sparse Retrieval Methods
    • Dense Baselines & Fixed Embeddings
    • Hard Negative Mining
    • Late Interaction (ColBERT)
    • Hybrid Dense-Sparse Methods
    • Pre-training Methods for Dense Retrievers
    • Joint Learning of Retrieval and Indexing
    • Literature Survey: Retrieval Methods
      • Hard Negative Mining: A Deep Dive for Building a Unified Mining Library
  • Stage 2: Re-ranking Methods
    • Cross-Encoders for Re-ranking
    • LLM-Based Re-rankers
    • Reranker Survey: Models, Libraries, and Frameworks
    • Literature Survey: Re-ranking Methods
      • MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings
      • zELO: ELO-inspired Training Method for Rerankers and Embedding Models
  • Contributing
  1. Docs
  2. Search
  • GitHub
© Copyright 2025, Abhijeet Pendyala
Created using Sphinx Wagtail Theme and Sphinx 8.1.3