Node.js Lease PDF Search: Budget Embeddings, Rerank, and Final Summary

说明与用途

Node.js 版租赁 PDF 摘要服务通过提取、重新排序和生成的管道实现。新的监控记录每个阶段的候选数、选定片段和指标，能够在最终摘要前及时发现预算违规，避免过度使用令牌。

问题

On‑call engineers only see a property ID, document ID, and a rising total after a lease‑PDF summarization workflow, missing early signals that retrieval admitted too many chunks and the final summary inherited unnecessary context.

结果

The new instrumentation reduces downstream token exposure, makes provider portability an operational property, and provides actionable alerts on evidence budget violations rather than only cost totals.

工作流

• Index lease PDF into page‑aware chunks with embeddings
• Retrieve broadly based on semantic search
• Rerank candidate set to select top passages
• Generate final summary using selected passages
• Record metrics at each boundary (retrieval, rerank, generation)
• Alert on budget invariant violations

证据

The useful signal fired several steps earlier, when retrieval admitted too many chunks and the final summary inherited a context it never needed.

来源

Store stable application fields in Postgres: document_version, chunk_id, page range, text digest, embedding model identifier, and index timestamp.

来源

The final-generation record needs selected count and input-token count, plus the provider, latency, cost, and request ID where the provider supplies them.

来源