feat(rag): connect bp_compliance_ce vector corpus to SDK

- Switch LegalRAGClient from empty bp_legal_corpus to bp_compliance_ce
  collection (3,734 chunks across 14 regulations)
- Replace embedding-service (384-dim MiniLM) with Ollama bge-m3 (1024-dim)
- Add standalone RAG search endpoint: POST /sdk/v1/rag/search
- Add regulations list endpoint: GET /sdk/v1/rag/regulations
- Add QDRANT_HOST/PORT env vars to docker-compose.yml
- Update regulation ID mapping to match actual Qdrant payload schema
- Update determineRelevantRegulations for CE corpus regulation IDs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

ai-compliance-sdk/cmd/server/main.go

@@ -135,6 +135,10 @@ func main() {
 	ttsClient := training.NewTTSClient(cfg.TTSServiceURL)
 	contentGenerator := training.NewContentGenerator(providerRegistry, piiDetector, trainingStore, ttsClient)
 	trainingHandlers := handlers.NewTrainingHandlers(trainingStore, contentGenerator)
+
+	// Initialize RAG handlers
+	ragHandlers := handlers.NewRAGHandlers()
+
 	// Initialize middleware
 	rbacMiddleware := rbac.NewMiddleware(rbacService, policyEngine)
 
@@ -743,6 +747,13 @@ func main() {
 			trainingRoutes.GET("/stats", trainingHandlers.GetStats)
 			trainingRoutes.GET("/certificates/:id/verify", trainingHandlers.VerifyCertificate)
 		}
+
+		// RAG Search routes - Compliance Regulation Corpus
+		ragRoutes := v1.Group("/rag")
+		{
+			ragRoutes.POST("/search", ragHandlers.Search)
+			ragRoutes.GET("/regulations", ragHandlers.ListRegulations)
+		}
 	}
 
 	// Create HTTP server