---
# The embedding endpoint, for RAG and semantic search.
#
# Deliberately separate from llama-server and deliberately not behind the
# ingress: an embedding model has no generative training, and when it shares a
# port with the chat model the built-in WebUI lists it as a choice. Selecting it
# returns fluent nonsense rather than an error, because `--embeddings` does not
# actually refuse chat completions. Keeping it on its own ClusterIP-only Service
# is what makes it unselectable, since llama.cpp has no way to hide a model from
# the picker.
#
# Reachable in-cluster at http://llama-embed.ai.svc.cluster.local:8080/v1/embeddings.
apiVersion: apps/v1
kind: Deployment
metadata:
  name: llama-embed
  namespace: ai
  labels:
    app.kubernetes.io/name: llama-embed
spec:
  replicas: 1
  # Same reasoning as llama-server: the startupProbe budget (600s) must stay
  # below progressDeadlineSeconds, whose default is also 600 — exactly equal, so
  # any cold download that uses most of its budget trips
  # KubeDeploymentRolloutStuck on a rollout that is still progressing normally.
  progressDeadlineSeconds: 900
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app.kubernetes.io/name: llama-embed
  template:
    metadata:
      labels:
        app.kubernetes.io/name: llama-embed
    spec:
      # Runs only where the node patch declares the Intel iGPU.
      nodeSelector:
        hardware.renner.uno/intel-gpu: "true"
      securityContext:
        runAsNonRoot: true
        runAsUser: 1000
        runAsGroup: 1000
        fsGroup: 1000
        seccompProfile:
          type: RuntimeDefault
      containers:
        - name: llama-embed
          image: ghcr.io/ggml-org/llama.cpp:server-vulkan-b10731@sha256:0262343f64f030e8efff15ec05ee8180b69b7f6745de2caa3af5148e0dcb8aba
          args:
            - --hf-repo
            - gpustack/bge-m3-GGUF:Q8_0
            # Serves POST /v1/embeddings.
            - --embeddings
            # A short, stable id for consumers. Without it the model is
            # advertised as the whole --hf-repo string, which would end up
            # verbatim in Paperless's config and break on the next model swap.
            # One name only: llama-server keeps aliases in a sorted set and
            # reports the first as the id, so a second name can steal it.
            - --alias
            - bge-m3
            # bge-m3 is trained for CLS pooling — a different type from the
            # Qwen family this replaces, which uses last-token. Left unspecified
            # llama-server takes the GGUF default, which is not visible from
            # outside and would silently produce vectors the model was not
            # trained to emit. Read from the model's own 1_Pooling/config.json
            # rather than assumed; of the candidates measured, three different
            # pooling types were needed.
            - --pooling
            - cls
            - --n-gpu-layers
            - "99"
            - --threads
            - "2"
            # Paperless chunks at 1024 tokens, but counts them with its own
            # tokenizer while this server measures the batch in bge-m3's.
            # Those disagree: XLM-RoBERTa splits German into more pieces than
            # llama_index's counter does, so a chunk Paperless considers full
            # at 1024 arrived here as 1069 and the request failed outright —
            # "input (1069 tokens) is too large to process".
            #
            # The headroom therefore has to absorb a tokenizer ratio, not just
            # a rounding error, and 1.5x covers far more than the 1.044 that
            # broke it. The defaults are batch 2048 / ubatch 512, and with
            # --embeddings llama-server clamps both to the smaller rather than
            # run them mismatched, so both are set.
            #
            # 2048 stays avoided: that is where the chat model met
            # ErrorDeviceLost on this Vulkan stack. That failure came under a
            # 20 GB model's memory pressure and may not bind a 600 MB one, but
            # this does not need to find out.
            - --batch-size
            - "1536"
            - --ubatch-size
            - "1536"
            # Room for a full chunk plus overhead rather than exactly one.
            - --ctx-size
            - "4096"
            # No browser ever talks to this Service, so the WebUI is dead weight
            # and one more unauthenticated surface.
            - --no-webui
          env:
            # Same cache as llama-server, so the two share one copy of anything
            # they have in common and neither re-downloads the other's weights.
            - name: LLAMA_CACHE
              value: /models
          ports:
            - name: http
              containerPort: 8080
          securityContext:
            allowPrivilegeEscalation: false
            capabilities:
              drop:
                - ALL
          # Measured, not estimated: embedding 400 real documents peaked at
          # 1.6 GiB (Prometheus max_over_time on the working set). The limit is
          # well above that because the footprint is dominated by the four slots
          # at 4096 context and the Vulkan working set rather than by the
          # weights — the Qwen model this replaces peaked at 10.6 GiB on the
          # same settings for the same 600 MiB of weights, and several
          # candidates were OOMKilled at limits that looked generous against
          # their model size.
          resources:
            requests:
              cpu: 250m
              memory: 2Gi
              gpu.intel.com/i915: "1"
            limits:
              cpu: "2"
              memory: 8Gi
              gpu.intel.com/i915: "1"
          # ~600 MiB rather than ~5 GiB, so a much shorter budget than the chat
          # model needs, but still sized for a cold download.
          startupProbe:
            httpGet:
              path: /health
              port: http
            periodSeconds: 10
            failureThreshold: 60
          readinessProbe:
            httpGet:
              path: /health
              port: http
            periodSeconds: 10
          livenessProbe:
            httpGet:
              path: /health
              port: http
            periodSeconds: 30
            timeoutSeconds: 10
            failureThreshold: 6
          volumeMounts:
            - name: models
              mountPath: /models
      volumes:
        - name: models
          persistentVolumeClaim:
            claimName: llama-server-models
---
apiVersion: v1
kind: Service
metadata:
  name: llama-embed
  namespace: ai
  labels:
    app.kubernetes.io/name: llama-embed
spec:
  selector:
    app.kubernetes.io/name: llama-embed
  ports:
    - name: http
      port: 8080
      targetPort: http