feat: RAG service health check (#704)

**Reason for Change**:
Health check of RAG Service

**Requirements**

- [ ] added unit tests and e2e tests (if applicable).

**Issue Fixed**:
<!-- If this PR fixes GitHub issue 4321, add "Fixes #4321" to the next
line. -->

**Notes for Reviewers**:

Signed-off-by: Bangqi Zhu <bangqizhu@microsoft.com>
Co-authored-by: Bangqi Zhu <bangqizhu@microsoft.com>

pkg/ragengine/controllers/preset-rag.go

@@ -20,19 +20,19 @@ import (
 
 const (
 	ProbePath = "/health"
-	Port5000  = int32(5000)
+	Port5000  = 5000
 )
 
 var (
 	containerPorts = []corev1.ContainerPort{{
-		ContainerPort: Port5000,
+		ContainerPort: int32(Port5000),
 	},
 	}
 
 	livenessProbe = &corev1.Probe{
 		ProbeHandler: corev1.ProbeHandler{
 			HTTPGet: &corev1.HTTPGetAction{
-				Port: intstr.FromInt(5000),
+				Port: intstr.FromInt(Port5000),
 				Path: ProbePath,
 			},
 		},
@@ -43,7 +43,7 @@ var (
 	readinessProbe = &corev1.Probe{
 		ProbeHandler: corev1.ProbeHandler{
 			HTTPGet: &corev1.HTTPGetAction{
-				Port: intstr.FromInt(5000),
+				Port: intstr.FromInt(Port5000),
 				Path: ProbePath,
 			},
 		},
@@ -100,6 +100,7 @@ func CreatePresetRAG(ctx context.Context, ragEngineObj *kaitov1alpha1.RAGEngine,
 	commands := utils.ShellCmd("python3 main.py")
 	// TODO: provide this image
 	image := "mcr.microsoft.com/aks/kaito/kaito-rag-service:0.0.1"
+
 	imagePullSecretRefs := []corev1.LocalObjectReference{}
 
 	depObj := manifests.GenerateRAGDeploymentManifest(ctx, ragEngineObj, revisionNum, image, imagePullSecretRefs, *ragEngineObj.Spec.Compute.Count, commands,

pkg/ragengine/services/main.py

@@ -7,7 +7,7 @@
 from embedding.huggingface_remote import RemoteHuggingFaceEmbedding
 from fastapi import FastAPI, HTTPException
 from models import (IndexRequest, ListDocumentsResponse,
-                    QueryRequest, QueryResponse, DocumentResponse)
+                    QueryRequest, QueryResponse, DocumentResponse, HealthStatus)
 from vector_store.faiss_store import FaissVectorStoreHandler
 
 from services.config import ACCESS_SECRET, EMBEDDING_TYPE, MODEL_ID
@@ -29,6 +29,21 @@
 # Initialize RAG operations
 rag_ops = VectorStoreManager(vector_store_handler)
 
+@app.get("/health", response_model=HealthStatus)
+async def health_check():
+    try:
+
+        if embedding_manager is None:
+            raise HTTPException(status_code=500, detail="Embedding manager not initialized")
+
+        if rag_ops is None:
+            raise HTTPException(status_code=500, detail="RAG operations not initialized")
+
+        return HealthStatus(status="Healthy")
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
 @app.post("/index", response_model=List[DocumentResponse])
 async def index_documents(request: IndexRequest): # TODO: Research async/sync what to use (inference is calling)
     try:
@@ -59,4 +74,4 @@ async def list_all_indexed_documents():
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=5000)

pkg/ragengine/services/models.py

@@ -37,4 +37,8 @@ class NodeWithScore(BaseModel):
 class QueryResponse(BaseModel):
     response: str
     source_nodes: List[NodeWithScore]
-    metadata: Optional[dict] = None
+    metadata: Optional[dict] = None
+
+class HealthStatus(BaseModel):
+    status: str
+    detail: Optional[str] = None 

pkg/workspace/inference/preset-inferences.go

@@ -24,20 +24,20 @@ import (
 
 const (
 	ProbePath     = "/healthz"
-	Port5000      = int32(5000)
+	Port5000      = 5000
 	InferenceFile = "inference_api.py"
 )
 
 var (
 	containerPorts = []corev1.ContainerPort{{
-		ContainerPort: Port5000,
+		ContainerPort: int32(Port5000),
 	},
 	}
 
 	livenessProbe = &corev1.Probe{
 		ProbeHandler: corev1.ProbeHandler{
 			HTTPGet: &corev1.HTTPGetAction{
-				Port: intstr.FromInt(5000),
+				Port: intstr.FromInt(Port5000),
 				Path: ProbePath,
 			},
 		},
@@ -48,7 +48,7 @@ var (
 	readinessProbe = &corev1.Probe{
 		ProbeHandler: corev1.ProbeHandler{
 			HTTPGet: &corev1.HTTPGetAction{
-				Port: intstr.FromInt(5000),
+				Port: intstr.FromInt(Port5000),
 				Path: ProbePath,
 			},
 		},