{"componentChunkName":"component---src-templates-tag-page-js","path":"/tags/embeddings/","result":{"data":{"site":{"siteMetadata":{"title":"M.Hassan Ahmed","author":"Hassan11196"}},"allMarkdownRemark":{"totalCount":5,"edges":[{"node":{"excerpt":"Contextual Retrieval for RAG, Step by Step Here is a chunk that once cost me an afternoon of debugging. It read, roughly, “The failure rate…","fields":{"slug":"/2026-08-28-contextual-retrieval-rag/"},"frontmatter":{"date":"2026-08-28T00:00:00.000Z","title":"Contextual Retrieval for RAG, Step by Step","description":"Vector search misses chunks that lost their document context. Contextual Retrieval prepends a short LLM-written summary to each chunk before you embed it.","tags":["AI","LLM","RAG","Embeddings","Search"],"thumbnail":null}}},{"node":{"excerpt":"Product Quantization for Vector Search The HNSW post ended on a bill I did not pay. HNSW makes the search fast, walking a graph in a handful…","fields":{"slug":"/2026-08-18-product-quantization-vector-search/"},"frontmatter":{"date":"2026-08-18T00:00:00.000Z","title":"Product Quantization for Vector Search","description":"HNSW makes vector search fast, but the embeddings still fill your RAM. Product quantization compresses them ~32x with a small recall hit. Here is how it works.","tags":["AI","RAG","VectorSearch","Embeddings","FAISS"],"thumbnail":null}}},{"node":{"excerpt":"Matryoshka Embeddings: Smaller Vectors for RAG Every vector you store in a RAG system costs you twice. Once on disk, and again in RAM…","fields":{"slug":"/2026-08-12-matryoshka-embeddings-rag/"},"frontmatter":{"date":"2026-08-12T00:00:00.000Z","title":"Matryoshka Embeddings: Smaller Vectors for RAG","description":"Matryoshka embeddings front-load meaning into a vector's first dimensions, so you can truncate them for cheaper, faster RAG search without losing much recall.","tags":["AI","RAG","Embeddings","Vector Search","LLM"],"thumbnail":null}}},{"node":{"excerpt":"How to Choose an Embedding Model for RAG Most RAG tuning happens on the wrong end of the pipeline. People spend a week on chunk sizes, bolt…","fields":{"slug":"/2026-07-28-choosing-embedding-model-rag/"},"frontmatter":{"date":"2026-07-28T00:00:00.000Z","title":"How to Choose an Embedding Model for RAG","description":"The embedding model sets the ceiling on RAG retrieval quality. How to choose one by task fit, sequence length, dimensions, and domain, plus the silent bugs.","tags":["AI","LLM","RAG","Embeddings","Search"],"thumbnail":null}}},{"node":{"excerpt":"How to Build a Semantic Cache for LLM Apps Two users ask your app the same thing an hour apart. One types “how do I reset the FNAL transfer…","fields":{"slug":"/2026-07-18-semantic-caching-llm-apps/"},"frontmatter":{"date":"2026-07-18T00:00:00.000Z","title":"How to Build a Semantic Cache for LLM Apps","description":"Exact-match caching misses paraphrases, so LLM bills stay high. Here is how to build a semantic cache with embeddings, a similarity threshold, and its traps.","tags":["AI","LLM","Caching","Embeddings","Python"],"thumbnail":null}}}]}},"pageContext":{"tag":"Embeddings"}},"staticQueryHashes":["32046230"]}