embeddings - Abrarqasim Blogs

Fine-Tuning a ColBERT Model on One GPU Just Got Practical

Sentence Transformers v6 makes ColBERT-style retrieval trainable on one consumer GPU. The numbers, two traps in the fine print, and when it beats dense embeddings.

Rayyan | August 31, 2026 | 6 min

AI

Embedding Models for RAG: What Late Interaction Actually Costs

Late interaction embedding models beat dense retrieval by one NDCG point and cost 42x the index. Here is where that trade actually pays off in…

Rayyan | August 23, 2026 | 9 min

AI

Zero Shot Classification: Let the Model Make It Up

Instead of shipping a 600-item enum to the model, let it invent a fake category and snap it to a real one with embeddings. Cheaper,…

Rayyan | August 17, 2026 | 10 min

AI

pgvector in 2026: Why I Deleted Pinecone From Half My Side Projects

pgvector plus HNSW replaced Pinecone on half my side projects. The schema, the index picks, hybrid search with FTS, and where I still reach for…

Rayyan | July 10, 2026 | 10 min

AI

RAG Chunking Strategies in 2026: What I Actually Use

After two years of running RAG in production, here are the chunking strategies I actually use, the ones I dropped, and why chunk size is…

Rayyan | May 4, 2026 | 8 min