OpenSearch 主栈:专用在线检索与独立 Catalog

OpenSearch BM25 + k-NN + efficient filters · PostgreSQL control plane · S3 source of truth

OpenSearch 主栈:专用在线检索与独立 CatalogOpenSearch serves online lexical, vector and hybrid retrieval. S3 retains original documents and parsed artifacts; a small PostgreSQL catalog controls versions, ACL and outbox state. Search API injects authorization filters before the OpenSearch query. OpenSearch 主栈:专用在线检索与独立 Catalog OpenSearch BM25 + k-NN + efficient filters · PostgreSQL control plane · S3 source of truth 01 · INGESTION / INDEX BUILD 02 · ONLINE QUERY / EVIDENCE 事件 解析 原件 投影 索引 请求 身份 查询构建 Hybrid 引用 INDEX QUERY SOURCE 来源系统 DB CDC · Vendor APIPDF · Office · Email · Audio INGEST Connectors Kafka / SQS / MSK增量水位 · Replay · DLQ WORKER 处理 Worker Parser · OCR · ASRNormalize · Chunk · Embed* DURABLE S3 Object Store 原件 · 版本 · 派生产物Snapshot · Manifest CATALOG Catalog / Control Document · Version · ACLPostgreSQL · Outbox INDEX OpenSearch Index BM25 · k-NN · MetadataAlias · ISM · Snapshot CALLER 用户 / Agent UI · SDK · MCP不直连集群 API Search API Auth · Rate limit · Audit统一查询契约 SECURITY 权限注入 Tenant · ACL principals来源 · 时间 · 市场 QUERY Hybrid Builder BM25 + k-NNFilter · RRF · rerank SERVE OpenSearch Query Query DSL · Search PipelineEfficient k-NN filtering EVIDENCE 证据回取 Chunk / metadata → Catalog原文 / 页码 → S3 * Embedding 是按评测决定的可选通道;OpenSearch 负责在线查询投影,不作为原始文档唯一事实来源。 REFERENCE ARCHITECTURE · LOGICAL VIEW