Category archive
Retrieval is an evidence pipeline, not a similarity score.
Most retrieval failures are read as model failures. These articles stay on the retrieval side of that line: how candidates are generated, how they are ranked before generation sees them, how an index drifts away from the corpus it was built from, and how the evidence a model is handed decides what it can honestly say.
Articles in Retrieval
-
Production RAG Is an Evidence Pipeline, Not a Vector Search
Designing retrieval-augmented generation around ingestion quality, query planning, evidence assembly, and verifiable answers.
-
Hybrid Lexical and Vector Search
A practical design for candidate generation, score normalization, rank fusion, metadata filters, and retrieval evaluation.
-
Rerankers: The Quality Layer Between Search and Generation
How cross-encoders, late interaction, listwise ranking, and calibration turn noisy candidates into usable evidence.
-
Embedding Systems: Models, Indexes, and Semantic Drift
Selecting representations, constructing embedding inputs, migrating indexes, and detecting when semantic neighborhoods stop serving the product.
-
AI Data Flywheels Without Feedback Pollution
Turning product use into better data through instrumentation, review, provenance, counterfactuals, and controlled training loops.
Apply the category
Put this against a real system.
If a decision in Retrieval is in front of you right now, the fastest version of this is a call: bring the architecture, the failure you are seeing, and the constraint you cannot move.
Discuss the system
