# Embeddings — Nomic Embed Text v2 (MoE), on CPU via HuggingFace TEI.
#
# CPU, not GPU, deliberately. All 4 V100s are claimed by the generation models,
# and the device plugin hands out WHOLE GPUs — a 5th GPU-requesting pod is
# unschedulable no matter how much VRAM is free. Sharing would need global
# time-slicing, which on a single node cannot be scoped to one card and would let
# the scheduler co-locate two ~20GB models and OOM both.
#
# worker-1 has 96 cores with ~250m requested, and this is a 475M-param encoder
# (305M active). Retrieval runs once per agent-loop iteration, not per token, so
# CPU latency here is immaterial. This is also what Plan 1 originally specified.
#
# TEI (not vLLM) because it is purpose-built for encoders and explicitly lists
# nomic-embed-text-v2-moe as supported.
#
# NOTE: Nomic v2 requires task prefixes on the CLIENT side —
#   documents: "search_document: <text>"
#   queries:   "search_query: <text>"
# Embedding without the prefix silently degrades retrieval quality.
apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  name: embeddings
  labels:
    app.kubernetes.io/name: llm-embeddings
    app.kubernetes.io/part-of: llm-serving
spec:
  predictor:
    minReplicas: 1
    maxReplicas: 1
    # Pinned to worker-1 only so it can share the RWO models PVC with the GPU
    # pods (RWO = single node, any number of pods on it).
    nodeSelector:
      kubernetes.io/hostname: worker-1
    containers:
      - name: kserve-container
        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.8.2@sha256:4d632b76bd14cb57044a1ffb0ad48ab0ba4939e705a9a615ccc740658575c26e
        args:
          - --model-id=nomic-ai/nomic-embed-text-v2-moe
          - --port=8080
          - --hostname=0.0.0.0
          # Truncate rather than 413 on over-long input.
          - --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