Distance to Similarity Sorting

Real-World Use Cases for RAG

Common RAG Failure Modes

RAG vs Fine-Tuning Trade-offs

Vector Database Tools Landscape

Evaluating RAG Systems

Choosing an Embedding Model for Retrieval

Chunk Overlap and Context Windows

Reranking Retrieved Results

Context Injection and Prompt Augmentation

Metadata Filtering and Hybrid Search

Top-k Retrieval and Result Ranking

Vector Indexing: HNSW and IVF

Approximate Nearest Neighbor Search

Semantic Search vs Keyword Search

What a Vector Database Is

Generating and Storing Document Embeddings

Document Chunking Strategies

Indexing vs Query Phase in RAG

RAG: Retriever Plus Generator

Handling Empty Retrieval Results

Embedding Dimension Mismatch Bug

Context Assembly and Budget Truncation

Reranking with a Cross-Encoder

Chunk-to-Source Mapping for Citations

Retrieval Recall@K Evaluation

What a Vector Database Is

Chunk Size and Overlap

Core RAG Pipeline Stages

Retrieval Quality Metrics

Approximate Nearest Neighbor Search

Top-K Retrieval and Context

Indexing and Ingestion Pipeline

Embedding Dimensionality Trade-offs

Vector Quantization and Compression

RAG vs Fine-Tuning

Grounding and Citation

Embedding Model Selection

Common RAG Failure Modes

Query Transformation and Expansion

Multi-Vector Late-Interaction Retrieval

Re-Ranking Retrieved Results

Exact vs Approximate Trade-offs

Hybrid Search

Metadata Filtering in Search

Faithfulness and Answer Relevance

Document Chunking Strategies

ANN Index Structures

Deduplicating Retrieved Chunks

Reciprocal Rank Fusion

Similarity Score Threshold Filtering

Upserting Vectors with Metadata

Filtering Before vs After Search

HNSW efSearch vs topK

Maximal Marginal Relevance Selection

Combining BM25 and Vector Scores

Batch Similarity with Matmul

FAISS-style ANN Build & Query

Dot Product Ranking

Brute-Force Vector Search

Normalizing for Cosine Similarity

Euclidean (L2) Distance

Embedding a Query via API

Re-ranking Retrieved Results

Embedding Model Selection

Cost and Latency in RAG

Hybrid Search Basics

Evaluating RAG Systems

Retrieval Failure Modes

Grounding and Source Citation

Popular Vector Database Tools

Query Transformation and Expansion

Multi-Query and Fusion Retrieval

Indexing vs Query Phase

Exact vs Approximate Search

Metadata Filtering in Vector Search

Chunk Size and Overlap Tradeoffs

What is a Vector Database

HNSW Indexing

Document Chunking Strategies

IVF and Other ANN Index Types

Approximate Nearest Neighbor Search

Top-K Retrieval

Vector DB vs Traditional Database

RAG Pipeline Architecture