embeddings
5 posts — newest first.
-
Your Semantic Cache Is Answering the Wrong Question
Quora and PAWS sweeps: at 0.90 cosine with 5% repeat traffic, 78% of cache hits served the wrong answer, and thresholds do not transfer between models.
-
Your Chunking Benchmark Is Measuring Chunk Size
14 chunking strategies on SQuAD with answer-span ground truth. Semantic chunking lost to every alternative, and fixed-k scoring hid the thing that mattered.
-
Vector Index Trade-offs: Flat vs IVF vs HNSW, and When Quantization Pays
Exact search is O(n) and always right. Every ANN index buys speed with recall, memory, or build time. The arithmetic, compared.
-
What are vector embeddings?
A primer on vector embeddings — how meaning becomes something you can search, cluster, and compare, and the failure modes you only see in evaluation.
-
What is Retrieval-Augmented Generation (RAG)?
A primer on Retrieval-Augmented Generation — grounding an LLM's answer in documents you trust. Indexing, serving, and the failure modes that bite.