Embeddings

Vector representations and semantic search.

Cross-Attention Fusion: Combining Text Embeddings with Structured Features

Concatenation is the default. Here's why cross-attention works better for combining text embeddings with tabular data—and how to implement it in PyTorch.

#multimodal #cross-attention #tabular

Open Seas 30 min read

Bi-Encoders: Fast Semantic Search at Scale

Learn how bi-encoders enable sub-millisecond semantic search over millions of documents. Build a complete search system with sentence-transformers, FAISS indexing, and production-ready Python code.

#sentence-transformers #semantic-search #faiss

Open Seas 25 min read

Cross-Encoders: Precision Reranking for Search

When bi-encoders aren't accurate enough, cross-encoders dramatically improve search relevance. Build a two-stage retrieval system with MS MARCO rerankers and sentence-transformers.

#cross-encoder #reranking #semantic-search

Deep Dive 45 min read

Visual Semantic Search with CLIP and AWS

Build a production image search system using OpenAI's CLIP model, Amazon OpenSearch Serverless for vector storage, and Claude on Bedrock for image descriptions. Complete Python implementation with real AWS outputs.

#clip #opensearch-serverless #bedrock

Calm Waters 25 min read

Sentence Embeddings from Scratch with PyTorch

Build a complete sentence encoder from the ground up. Learn tokenization, embedding layers, pooling strategies, and benchmark on semantic similarity.

#pytorch #nlp #embeddings