@techNmak: A 30-question breakdown of how embeddings, vector search, and retrieval actually work - similarity metrics, contrastive…

A 30-question breakdown of how embeddings, vector search, and retrieval actually work - similarity metrics, contrastive training, BM25, hybrid search, ANN indexes (HNSW/IVF/PQ), reranking, and evaluation. Embeddings fundamentals → What it actually means for two texts to be "close" in embedding space → Pooling strategies, and why you can't change them at serving time → Cosine similarity vs. dot product vs. Euclidean distance, and when they rank the same → Why similarity scores aren't calibrated probabilities → Does more dimensions always mean better retrieval? (No) → Why search is often an asymmetric embedding problem Training embedding models → How contrastive learning teaches relevance → In-batch negatives, hard negatives, and the false-negative trap Lexical, dense, sparse & hybrid retrieval → How BM25 actually ranks documents → When lexical search still beats dense retrieval → Learned sparse retrieval and SPLADE → Hybrid retrieval, and why it's not automatically better → Reciprocal Rank Fusion, combining rankings on different scales Reranking → Bi-encoders vs. cross-encoders → Retrieve-then-rerank, and how to choose rerank depth → Late interaction and ColBERT Vector indexes & ANN search → Exact vs. approximate nearest-neighbor search → How HNSW actually works, and why it's not O(log N) in production → IVF and the speed/recall trade-off of probing → Product Quantization → Choosing between exact search, HNSW, IVF, and IVF+PQ Production systems → Why metadata filtering breaks ANN search in non-obvious ways → Inserts, deletes, and freshness in ANN indexes → What happens when you upgrade your embedding model → Estimating raw memory footprint before index overhead Evaluation → Precision@k, Recall@k, MRR, nDCG, what each one actually measures → Debugging: is the error in your embeddings or your index? → Why the top leaderboard model can be the wrong production model You can follow for more learning! Please share with your network!