vector search

4 articles tagged with this topic

ByteDance Open-Sources Vector Search: Faster, 90% Cheaper — And a Product Ad

ByteDance open-sources DiskANN+RaBitQ: claims 5.5x faster vector search and 90% memory savings vs HNSW. Notable engineering—but underneath it's a Qixi

Aug 202 min read

Simon WillisonDoug Turnbull

1,856 tags won't fit in a prompt? Let AI hallucinate, then vector-match

Tag library too big for a prompt? Let the LLM hallucinate, then vector-match. LLMs generate, vector search constrains.

Aug 152 min read

ElasticsearchElastic

Elasticsearch 9.4 Turns Search into Agent Infrastructure — Data Foundation Power Is Shifting

ES 9.4 upgrades search from "tool for humans" to Agent's memory and action layer: DiskBBQ vector search hits 7x Qdrant throughput, Agent Builder and M

Aug 142 min read

LightRAGcodebase-memory-mcp

Codebase-Memory Turns Git History Into a Fourth Retrieval Path for Code AI

Vector search, call graphs, and symbol indexes tell you "what" code is; answering "why it's written this way" requires digging through Git history. An

Aug 102 min read