- OpenSearch k-NN cheat sheet: vector mappings, bulk loads, filtered and hybrid queries, aliases and health checksAI & GenAI · 12 Nov 2026
- Redis vector search cheat sheet: FT.CREATE vector indexes, KNN and range queries, filters, aliases and index healthAI & GenAI · 10 Nov 2026
- Cosine, dot product or Euclidean: choosing a vector distance metric without the math headacheAI & GenAI · 7 Nov 2026
- RAG keeps answering from outdated documents: metadata filters, time decay and supersessionAI & GenAI · 7 Nov 2026
- Measure RAG retrieval properly: recall@k, MRR and a golden set that catches regressionsAI & GenAI · 6 Nov 2026
- RAG citations point to the wrong document or page: fix chunk IDs, metadata and citation checkingAI & GenAI · 3 Nov 2026
- Embedding ingestion job fails: input too long, batch token limits, 429s and empty vectors when indexing thousands of documentsAI & GenAI · 2 Nov 2026
- Sev1: OpenSearch k-NN cluster is red and vector search is down — shard allocation and k-NN memory circuit breakerAI & GenAI · 31 Oct 2026
- Sev1: pgvector search went from 50 ms to seconds — HNSW index not used, filters and ef_searchAI & GenAI · 31 Oct 2026
- Sev1: the RAG index stopped updating and the assistant answers from old documentsAI & GenAI · 31 Oct 2026
- Embeddings and vector search basics: what they are, how similarity works, and a small working exampleAI & GenAI · 29 Oct 2026
- Permission-aware RAG: document-level security trimming with ACL metadata and identity filtersAI & GenAI · 29 Oct 2026
- Filtered vector search returns too few or wrong results: pre-filtering vs post-filtering, HNSW and iterative scansAI & GenAI · 28 Oct 2026
- pgvector cheat sheet: vector types, distance operators, index operator classes and the settings that matterAI & GenAI · 28 Oct 2026
- Re-embedding a vector index when the embedding model retires - a zero-downtime switch with dual indexes and a recall checkAI & GenAI · 27 Oct 2026
- Azure AI Search relevance tuning for RAG - hybrid queries, semantic ranker, scoring profiles and measuring the resultAI & GenAI · 26 Oct 2026
- Advisory: choosing a vector store - pgvector, Azure AI Search, OpenSearch, Qdrant, Milvus or a managed vector databaseAI & GenAI · 25 Oct 2026
- Advisory: choosing an embedding model - quality on your data, languages, dimensions, cost and lock-inAI & GenAI · 25 Oct 2026
- Advisory: retrieval for RAG on lakehouse data - Databricks Vector Search or Azure AI SearchDatabricks on Azure · 25 Oct 2026
- Optimization: shrinking vector indexes - fewer dimensions, int8 and binary quantization, and rescoringAI & GenAI · 25 Oct 2026
- Sev1: RAG answers got much worse after a re-index. Finding what changed and rolling backAI & GenAI · 25 Oct 2026
- Sev1: vector search fails or returns nonsense after an embedding model changeAI & GenAI · 25 Oct 2026
- Transformation: from keyword search to hybrid search with a semantic rerankerAI & GenAI · 25 Oct 2026
- Migrating to a new embedding model without breaking searchAI & GenAI · 22 Oct 2026
- Vector index operations: HNSW tuning, memory sizing and measuring recallAI & GenAI · 22 Oct 2026
- Running a RAG pipeline in production: an operations checklistAI & GenAI · 10 Oct 2026