https://sinimite.work/tags/evaluation/Recent content in Evaluation on SiBloghttps://sinimite.work/images/og-default.svg?v=20260525-210321https://sinimite.work/images/og-default.svg?v=20260525-210321Hugo -- 0.156.0zh-cnSat, 01 Aug 2026 00:00:00 +0900https://sinimite.work/posts/rag-evaluation-metrics-cheat-sheet/Sat, 01 Aug 2026 00:00:00 +0900https://sinimite.work/posts/rag-evaluation-metrics-cheat-sheet/一份 RAG 评测指标速查表，覆盖 Recall、nDCG、Context Precision、Faithfulness、Citation、拒答、安全、延迟与成本等指标，帮助 AI Application Engineer 建立可落地的评测门禁。https://sinimite.work/posts/rag-reranking-best-practices-2026/Wed, 29 Jul 2026 00:00:00 +0900https://sinimite.work/posts/rag-reranking-best-practices-2026/系统讲解 RRF、Cross-Encoder、Pairwise、Listwise、Late Interaction、Learning-to-Rank、MMR 与 Set-wise Selection，并说明如何在候选召回、质量、延迟、成本和 Token Budget 之间设计生产级 RAG Rerank 模块。https://sinimite.work/posts/ai-engineer-job-market-2026/Tue, 28 Jul 2026 00:00:00 +0000https://sinimite.work/posts/ai-engineer-job-market-2026/一份面向东京、中国大陆和美国市场 AI Application Engineer 求职者的技术栈调研：Python、RAG、Agent、评测、云部署、安全与作品集。https://sinimite.work/posts/robust-multi-agent-subagent-design-2026/Mon, 27 Jul 2026 00:00:00 +0000https://sinimite.work/posts/robust-multi-agent-subagent-design-2026/面向普通程序员的 Multi-Agent 与 Sub-Agent 架构、指令设计、协调机制、可靠性、安全、评测与生产落地指南https://sinimite.work/posts/rag-retrieval-engineering-guide/Fri, 17 Jul 2026 15:40:44 +0900https://sinimite.work/posts/rag-retrieval-engineering-guide/一篇关于 RAG 检索层设计与落地的技术报告，涵盖 BM25、Embedding、ANN、RRF、重排、查询理解、访问控制、评测和部署实践。https://sinimite.work/posts/rag-observability-evaluation-design/Fri, 17 Jul 2026 15:06:18 +0900https://sinimite.work/posts/rag-observability-evaluation-design/系统讲解 RAG 可观测性与评估体系的设计方法，包括分阶段 Trace、运行指标、评测数据集、质量评分、实验对比、隐私边界和故障降级。https://sinimite.work/posts/opentelemetry-ai-agent-observability-guide/Thu, 16 Jul 2026 21:08:52 +0900https://sinimite.work/posts/opentelemetry-ai-agent-observability-guide/面向 AI 应用开发者的 OpenTelemetry 入门指南，涵盖 Trace、Metric、Log、Profile、Context Propagation、Collector、GenAI 语义约定和生产实践。https://sinimite.work/posts/rag-chunking-strategies-evaluation/Wed, 15 Jul 2026 18:05:16 +0900https://sinimite.work/posts/rag-chunking-strategies-evaluation/一篇关于 RAG Chunking 策略、参数选择、上下文保留与评估流程的技术参考。https://sinimite.work/posts/rag-rrf-retrieval-fusion/Wed, 15 Jul 2026 17:37:44 +0900https://sinimite.work/posts/rag-rrf-retrieval-fusion/一篇关于 Reciprocal Rank Fusion 原理、工程位置、融合选择和生产评估方法的技术参考。https://sinimite.work/posts/rag-dense-sparse-hybrid-search/Wed, 15 Jul 2026 17:25:30 +0900https://sinimite.work/posts/rag-dense-sparse-hybrid-search/一篇关于 Dense + Sparse Hybrid Search 原理、融合方式、适用场景和评估方法的技术参考。https://sinimite.work/posts/enterprise-rag-system-building-guide/Wed, 15 Jul 2026 16:35:23 +0900https://sinimite.work/posts/enterprise-rag-system-building-guide/介绍企业级 RAG 系统的数据摄取、混合检索、权限控制、生成、评估与可观测架构。https://sinimite.work/posts/points-of-the-podcast-language-agents-from-reasoning-to-acting/Sun, 24 May 2026 16:05:10 +0900https://sinimite.work/posts/points-of-the-podcast-language-agents-from-reasoning-to-acting/一篇关于 Language Agents: From Reasoning to Acting podcast 的观后感，从 ReAct、Reflexion、Tree of Thoughts、memory、benchmark 和 ACI 出发，解释 LLM agent 为什么是模型、工具、记忆、环境、评估和 UX 共同构成的工程系统。https://sinimite.work/posts/ai-engineer-skill-value-map-2026/Sun, 03 May 2026 20:09:15 +0900https://sinimite.work/posts/ai-engineer-skill-value-map-2026/一篇面向 AI 应用工程师转型的技能价值地图，说明基础 RAG、prompt engineering 与框架 API 的价值变化，并解释 eval、governance 和 agentic workflow 为什么更值得投入。https://sinimite.work/posts/llm-training-for-ai-engineers/Sat, 04 Apr 2026 12:00:00 +0900https://sinimite.work/posts/llm-training-for-ai-engineers/一篇面向 AI 应用工程师的大模型训练全景指南，覆盖预训练、后训练、蒸馏、Reward 设计、Agent 训练与 Harness Engineering，帮助你理解模型能力从何而来，以及这些训练决策如何影响真实应用落地。https://sinimite.work/posts/rag-system-complete-guide/Fri, 27 Mar 2026 15:06:20 +0900https://sinimite.work/posts/rag-system-complete-guide/面向 AI 应用工程学习者的 RAG 全景指南，系统讲清数据摄入、分块、检索、重排序、生成、评估与生产运维，并给出从 0 到上线的实现路径。https://sinimite.work/posts/rag-chunking-best-practices/Wed, 18 Mar 2026 20:40:55 +0900https://sinimite.work/posts/rag-chunking-best-practices/一份面向 AI Application Engineer 的 RAG chunking 实战指南，覆盖默认参数、主流切分策略、评估流程与生产实践。https://sinimite.work/posts/prompt-engineering-best-practices-guide/Wed, 11 Mar 2026 11:00:00 +0900https://sinimite.work/posts/prompt-engineering-best-practices-guide/系统梳理 2025-2026 年 Prompt Engineering 与 Context Engineering 的生产级最佳实践，涵盖 Claude、GPT、长上下文、Prompt Chaining、Tool Use 与 Eval 工作流。https://sinimite.work/posts/anthropic-contextual-retrieval-reading-notes/Wed, 11 Mar 2026 09:00:00 +0900https://sinimite.work/posts/anthropic-contextual-retrieval-reading-notes/一篇围绕 Anthropic Contextual Retrieval 的阅读笔记，覆盖 chunk 语义丢失问题、实验 benchmark、ground truth 评估方法与工程化 RAG 最佳实践。https://sinimite.work/posts/contextual-retrieval-rag-reading-list/Mon, 09 Mar 2026 08:30:00 +0900https://sinimite.work/posts/contextual-retrieval-rag-reading-list/一份面向 AI Application Engineer 的 Contextual Retrieval + RAG 阅读清单：从 Anthropic 官方资料到开源实现、评估方法与行业趋势。