解决多租户大模型系统中检索成本归属不清的问题，实现端到端精准计费。
Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems
- 采用无码本向量索引与多租户网关结合，统一追踪每租户的检索与生成成本。
- 在100个租户（1000万向量）下实现99.96%的成本归因准确率，延迟开销低于0.04%。
- 相比托管向量服务，检索基础设施成本降低3.1至9.0倍，适合企业级RAG部署。
企业级检索增强生成（RAG）部署面临关键治理缺口：尽管大模型生成成本按令牌计量，但检索层——向量内存、相似度计算和嵌入API调用——仍为未归属的共享成本，导致租户间隐性补贴。我们提出Cost-Governed RAG架构，将无码本向量索引（TurboVec）与多租户大模型治理网关结合，构建统一可观测性体系，使嵌入、检索与生成成本可按租户联合归因。该架构利用TurboVec的确定性闭式内存公式，实现近精确的每租户检索成本计算——这是基于图的索引因非线性内存开销所不具备的特性。在云数据平台治理边界内的Snowpark Container Services上部署，系统在100个模拟租户（1000万向量，对数正态分布）下达到99.96%的端到端成本归因准确率，遥测开销低于查询延迟的0.04%。在第四节所述定价假设下，该架构使检索基础设施成本降低3.1至9.0倍。我们形式化了三层成本模型，并表明无码本量化不仅支持确定性租户级成本归因，还消除了训练量化器中的共享码本泄漏面——后一发现为探索性，受限于第七节所述局限。
原文摘要 · Abstract (English)
Enterprise Retrieval-Augmented Generation (RAG) deployments face a critical governance gap: while LLM generation cost is metered per token, the retrieval layer - vector memory, similarity compute, and embedding API calls - remains an unattributed shared cost, enabling invisible cross-subsidization among tenants. We present Cost-Governed RAG, an architecture that integrates a codebook-oblivious vector index (TurboVec) with a multi-tenant LLM governance gateway, creating a unified observability stack where embedding, retrieval, and generation costs are jointly attributable per tenant. The architecture exploits TurboVec's deterministic, closed-form memory formula to enable near-exact per-tenant retrieval cost calculation - a property unavailable in graph-based indexes with non-linear memory overhead. Deployed on Snowpark Container Services within a cloud data platform's governance boundary, the system achieves 99.96% end-to-end cost attribution accuracy across 100 simulated tenants (10M vectors, log-normal size distribution) with telemetry overhead below 0.04% of query latency. The architecture reduces retrieval infrastructure cost by 3.1-9.0x compared to managed vector database services under the pricing assumptions detailed in Section IV. We formalize a three-layer cost model and demonstrate that codebook-oblivious quantization enables deterministic per-tenant cost attribution while also removing the shared-codebook leakage surface present in trained quantizers - the latter observation being exploratory and subject to the limitations described in Section VII.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。