Technology Radar
Published : Nov 05, 2025
NOT ON THE CURRENT EDITION
This blip is not on the current edition of the Radar. If it was on one of the last few editions, it is likely that it is still relevant. If the blip is older, it might no longer be relevant and our assessment might be different today. Unfortunately, we simply don't have the bandwidth to continuously review blips from previous editions of the Radar.
Understand more
Nov 2025
Assess
设备端信息检索 是一种使搜索、上下文感知和检索增强生成（RAG）能够完全在用户设备上运行——譬如移动设备、桌面设备或边缘设备，并优先考虑隐私和计算效率的技术。它将轻量级本地数据库与针对设备端推理优化的模型相结合。一个有前景的实现是将 sqlite-vec（一个支持嵌入式数据库内向量搜索的 SQLite 扩展）与 EmbeddingGemma（一个基于 Gemma 3 架构构建的 3 亿参数嵌入模型）进行配对。这种组合针对效率和资源受限环境进行了优化，将数据保持在边缘附近，从而减少对云 API 的依赖，并改善延迟和隐私。我们建议团队评估这种技术用于本地优先应用和其他数据主权、低延迟和隐私至关重要的场景。
