Amazon Bedrock 查询感知压缩降低 RAG 成本
原标题：Reduce RAG costs on Amazon Bedrock with query-aware compression
AI 摘要
AWS 机器学习博客介绍了一种在 Amazon Bedrock 上通过查询感知压缩降低 RAG 成本的方法。该方法在检索后、最终回答前，使用较小的模型（如 Claude Haiku）过滤检索到的文本块，仅保留与查询相关的部分，再交由主模型（如 Claude Sonnet）生成答案，从而减少输入 token 数量，节省成本并降低幻觉风险。文章还讨论了架构、成本模型、延迟权衡及与提示缓存等功能的结合。
正文节选
Reduce RAG costs on Amazon Bedrock with query-aware compression Input tokens sent to the foundation model (FM) on every call are often a meaningful part of the cost of running Retrieval Augmented Generation (RAG) at scale. Query-aware compression offers one way to reduce how many of them reach the model. Amazon Bedrock provides the foundation models and features to build RAG applications. RAG retrieval usually tunes for high recall, returning a broad set of potentially relevant chunks so the pri