embeddings
8 lessons tagged embeddings: free, quiz-checked micro-lessons.
RAG Evaluation in Production: Metrics, Tools, and Cadence
Learn how to systematically evaluate Retrieval-Augmented Generation systems in production using RAGAS, TruLens, and Phoenix — covering golden sets, retrieval drift, embedding drift, and cost-aware eval scheduling.
HippoRAG and RAPTOR: Hierarchical and Memory-Style RAG
Deep dive into two advanced RAG architectures — HippoRAG's hippocampal-inspired knowledge graph indexing and RAPTOR's recursive summarization tree — and why both dramatically outperform flat vector retrieval on multi-hop questions.
RAG Query Rewriting: HyDE, Multi-Query, Decomposition, and Step-Back
Master four advanced query rewriting techniques that dramatically improve RAG retrieval quality: Hypothetical Document Embeddings, multi-query expansion, query decomposition, and step-back prompting. Learn when to reach for each and how to implement them.
Hybrid Retrieval for RAG: BM25, Dense Vectors, and Cross-Encoder Reranking
Build a production-grade retrieval pipeline combining BM25 keyword search with dense vector search, then sharpen precision with cross-encoder rerankers (Cohere Rerank, Voyage rerank-2, BGE). Learn when each layer matters and how to wire them together.
RAG Chunking Strategies: From Fixed-Size to Late Chunking
A deep dive into how you split documents for retrieval-augmented generation — fixed-size, recursive, semantic, hierarchical, and late chunking — with concrete trade-offs and code for each approach.
OpenCLIP: the open-source CLIP that everyone actually uses
OpenAI released CLIP. LAION and friends released OpenCLIP — a reproducible, openly-trained re-implementation that has quietly become the default vision-language embedding backbone. Here's what it is, why it won, and how to drop it into a project.
Vision-Language Models (VLMs): how machines read images
How models like CLIP, GPT-4V, and Claude visual learn to talk about pictures. Cover the contrastive trick behind CLIP, the difference between embedding models and generative VLMs, and where each one shines.
Vector Databases and Similarity Search: Unlocking Semantic Understanding
Dive into the world of vector databases, specialized systems designed to store and query high-dimensional vector embeddings efficiently. Learn how these databases power semantic search, recommendation systems, and large language model applications by finding semantically similar data points at scale.