SuperBizAgent-java/openspec/changes/archive/2026-07-04-rag-spring-ai-vectorstore-sidecar/proposal.md

Why

The current RAG retrieval path talks to Milvus through the raw Java SDK, so framework-level retrieval behavior cannot be compared safely. Before replacing the main path, we need a Spring AI VectorStore sidecar that can run the same golden cases and expose differences without affecting lookup_knowledge.

What Changes

• Add a disabled-by-default Spring AI VectorStore sidecar retrieval path.
• Keep the current VectorSearchService as the production path for Chat and AIOps.
• Add an adapter/reporting surface that can run golden retrieval cases against both current and sidecar paths.
• Record comparable fields: result id/source, title, breadcrumb, score/distance, category, and metadata.
• Document incompatibilities between the current Milvus schema and Spring AI VectorStore behavior.
• No breaking changes.

Capabilities

New Capabilities

• None.

Modified Capabilities

• rag-knowledge-retrieval: Add requirements for sidecar Spring AI retrieval comparison while preserving the explicit lookup_knowledge tool boundary.
• rag-retrieval-evaluation: Add requirements for comparing baseline retrieval with the sidecar retriever on the golden case set.

Impact

• Affects retrieval service wiring, configuration, and evaluation scripts.
• May add Spring AI VectorStore dependency/configuration if the current dependency set does not already expose it.
• Does not change document upload, chunking, Milvus collection schema, Agent prompts, AIOps diagnosis flow, or the default lookup_knowledge runtime path.