Unverified50% confidenceFactExact time
pgvector's README lists the HNSW default parameters: m is 16, ef_construction is 64, and hnsw.ef_search is 40, with higher values giving better recall but slower speed.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedParameter count does not reliably predict indexing speed: EmbeddingGemma-300M indexes more slowly than the larger BGE-M3 (315.0 vs 433.0 chunks per second).69% similarUnverifiedTypical HNSW parameters are M=16 and EF_CONSTRUCTION=200, and it is recommended to set EF_RUNTIME between 10 and 50 for production scenarios.69% similarUnverifiedThe same parameter name reasoning_effort behaves differently across models from different vendors: in gpt-5.4-mini the median output tokens rose from 18 at none to 254 at high (×14.1); gpt-oss-120b rose from refusal to 1,340 (×4.6); claude-haiku-5.5 rose from 150 to 298 (×2.0); gemini-3.7-flash rose from 453 to 1,013 (×2.2).63% similarUnverifiedThe Laya decision model responds up to 4.1 times faster for short requests, with a 3-question guardrail check on a B200 dropping from 11.6 ms to 2.8 ms.61% similarUnverifiedUnder an 18k character budget, anchored hybrid retrieval achieved 36.18% accuracy, BM25 achieved 35.98%, while the best direct planner-guided method reached only 34.19%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034897API
curl https://kongchang.com/api/v1/knowledge/claims/1034897MCP
get_claim(id=1034897)