# Reranker — BAAI/bge-reranker-base, on CPU via HuggingFace TEI.
#
# Second stage of retrieval: the embedding model fetches a coarse top-k by
# vector similarity, this cross-encoder re-scores those candidates against the
# query directly. That is what fixes the "semantic dilution" problem in Plan 1 —
# a single embedding vector cannot represent a large chunk faithfully, so
# ranking by cosine alone surfaces near-misses.
#
# CPU for the same reason as the embedding service: all 4 GPUs are claimed and
# the device plugin allocates whole cards. A 568M cross-encoder scoring ~20-50
# candidates per query is well within CPU budget.
#
# Arch is XLMRobertaForSequenceClassification, which TEI serves as /rerank.
# 278M params — smaller than v2-m3 (568M) and English/Chinese rather than
# multilingual, which suits code+docs retrieval and is faster on CPU.
apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  name: reranker
  labels:
    app.kubernetes.io/name: llm-reranker
    app.kubernetes.io/part-of: llm-serving
spec:
  predictor:
    minReplicas: 1
    maxReplicas: 1
    # Same worker-1 pin as the embedding service, to share the RWO models PVC.
    nodeSelector:
      kubernetes.io/hostname: worker-1
    containers:
      - name: kserve-container
        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.8.2@sha256:4d632b76bd14cb57044a1ffb0ad48ab0ba4939e705a9a615ccc740658575c26e
        args:
          # bge-reranker-base, NOT v2-m3. TEI's CPU image starts the ONNX
          # Runtime backend and v2-m3 ships no ONNX files, so it dies with
          # "Model ONNX files not found in the repository". This build does.
          - --model-id=BAAI/bge-reranker-base
          - --port=8080
          - --hostname=0.0.0.0
          - --auto-truncate
        env:
          - name: HUGGINGFACE_HUB_CACHE
            value: /mnt/models
        ports:
          - containerPort: 8080
            protocol: TCP
        resources:
          requests:
            cpu: "8"
            memory: 4Gi
          limits:
            cpu: "16"
            memory: 8Gi
        volumeMounts:
          - name: models
            mountPath: /mnt/models
        startupProbe:
          httpGet:
            path: /health
            port: 8080
          periodSeconds: 10
          failureThreshold: 60
        readinessProbe:
          httpGet:
            path: /health
            port: 8080
          periodSeconds: 10
    volumes:
      - name: models
        persistentVolumeClaim:
          claimName: llm-models