Topic
Combining keyword and embedding search branches so exact identifiers and paraphrases are both recoverable.
A dev.to post by Rijul argues that semantic similarity is the wrong tool for error codes, part numbers and filenames, and sketches a retrieval pipeline that runs keyword and vector search side by side. It reports no measurements.
Reality
A dev.to post argues that IBM's chunkless RAG only helps on documents whose structure a parser can actually recover, and that on scanned PDFs and one-table wikis the agent ends up walking a tree the parser invented.
Reality
An Apache-2.0 memory layer for coding agents returns a candidate only when several signals agree, and it labels every answer STRONG, WEAK or MISS so the calling agent has to branch on confidence before reusing an old fix.
Reality
Argus had already fetched, parsed and embedded the page naming Daniel Lurie as San Francisco's 46th mayor, then reported it could not find him, because Postgres term-frequency ranking preferred a 20,000-character department catalogue.
Reality
The FAISS-plus-BM25 retrieval in this writeup does address vocabulary mismatch, but the agent loop around it ran at over 213 seconds a step on CPU, and that figure decided the deployment, not the retrieval design.
Reality
A dev.to walkthrough argues code review pipelines should merge lexical and vector candidates by rank, rerank a bounded pool, and withhold findings whose cited policy passage is stale or unreadable.
Reality