Why dense and sparse retrieval disagree, why fusing ranks beats blending scores, and what a 20-question evaluation set revealed about a B2B sales-intelligence prototype. This is a set of notes from a retrieval prototype, the B2B Sales Intelligence RAG repository. It is…
Qdrant 1.20 ranks keyword matches with BM25 straight from the full-text index, computes its own scoring statistics, adds a code tokenizer, and splits the upgrade into two memory-tier changes Keyword search inside a vector database used to be a sidecar. Teams that…
Every "add vector search" proposal comes with the same promise: users phrase questions their own way, keyword search misses, and embeddings fix it. A feature request on Synthadoc made that case for us (issue #411): Synthadoc uses BM25 exclusively. For wikis under…
Qdrant with.NET Browse articles ▾• Create your first collection• Index documents• Query the collection• Chunk documents→ Model payload and filter You are here• Assemble model context• Evaluate retrieval quality A draft runbook can have the same shutdown procedure as the…
A query can find the right runbook and still miss the condition that makes its instructions safe to follow. Choose chunk boundaries so retrieval can preserve those conditions. Check the returned evidence before you start tuning the generated answer. The…
In Embeddings in.NET, I stopped at the vector-store boundary. The article generated embeddings and treated the model, dimensions, distance, and input preparation as one contract. It did not create an index for those vectors. This article picks up there…
Eliminating Sparse Embedding Overhead: Qdrant 1.20 Native BM25, Code Tokenization, and TurboQuant Hybrid search—combining semantic dense embeddings with exact keyword relevance—has become standard for modern retrieval-augmented generation (RAG) and GraphRAG architectures. However, the production infrastructure required to support hybrid search…
Independent LLM benchmark, pricing, speed, context-window, and provenance data with model comparisons and published methodology. Jevfire vs DeBERTa v2 xlarge / Fine-tuned on span identification Hendrycks et al. (2021) (ContractNLI) Updated October 6, 2026. We do not rank this pair: at least one has no…
Embeddings, retrieval strategies, chunking, and hybrid search patterns.
An article joins this feed when it matches these terms. Each one is also a search of its own.