loco-operator/config/crd/bases/locostack.com_documents.yaml

---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
  annotations:
    controller-gen.kubebuilder.io/version: v0.20.1
  name: documents.locostack.com
spec:
  group: locostack.com
  names:
    kind: Document
    listKind: DocumentList
    plural: documents
    shortNames:
    - doc
    singular: document
  scope: Namespaced
  versions:
  - additionalPrinterColumns:
    - jsonPath: .status.phase
      name: Phase
      type: string
    name: v1alpha1
    schema:
      openAPIV3Schema:
        description: Document is the Schema for the documents API
        properties:
          apiVersion:
            description: |-
              APIVersion defines the versioned schema of this representation of an object.
              Servers should convert recognized schemas to the latest internal value, and
              may reject unrecognized values.
              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
            type: string
          kind:
            description: |-
              Kind is a string value representing the REST resource this object represents.
              Servers may infer this from the endpoint the client submits requests to.
              Cannot be updated.
              In CamelCase.
              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
            type: string
          metadata:
            type: object
          spec:
            description: spec defines the desired state of Document
            properties:
              chunkingStrategy:
                description: chunkingStrategy configures how the document content
                  is split into chunks before embedding.
                properties:
                  chunkOverlap:
                    default: 64
                    description: |-
                      chunkOverlap is the number of tokens carried over from the previous chunk
                      to preserve context at boundaries.
                    format: int32
                    minimum: 0
                    type: integer
                  chunkSize:
                    default: 512
                    description: chunkSize is the target chunk size in tokens.
                    format: int32
                    minimum: 1
                    type: integer
                  separators:
                    description: separators is an ordered list of separator strings
                      for the recursive strategy.
                    items:
                      type: string
                    type: array
                  strategy:
                    default: recursive
                    description: |-
                      strategy selects the chunking algorithm.
                      fixed: split at exact token boundaries.
                      recursive: split on separators, respecting document structure (default).
                      semantic: split at semantic boundaries using the embedding model.
                      sentence, markdown, html: structure-aware strategies for specific formats.
                    enum:
                    - fixed
                    - recursive
                    - markdown
                    type: string
                type: object
              knowledgeBaseRef:
                description: knowledgeBaseRef references the target knowledge base.
                properties:
                  apiVersion:
                    description: API version of the referent.
                    type: string
                  fieldPath:
                    description: |-
                      If referring to a piece of an object instead of an entire object, this string
                      should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2].
                      For example, if the object reference is to a container within a pod, this would take on a value like:
                      "spec.containers{name}" (where "name" refers to the name of the container that triggered
                      the event) or if no container name is specified "spec.containers[2]" (container with
                      index 2 in this pod). This syntax is chosen only to have some well-defined way of
                      referencing a part of an object.
                    type: string
                  kind:
                    description: |-
                      Kind of the referent.
                      More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
                    type: string
                  name:
                    description: |-
                      Name of the referent.
                      More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
                    type: string
                  namespace:
                    description: |-
                      Namespace of the referent.
                      More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/
                    type: string
                  resourceVersion:
                    description: |-
                      Specific resourceVersion to which this reference is made, if any.
                      More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency
                    type: string
                  uid:
                    description: |-
                      UID of the referent.
                      More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids
                    type: string
                type: object
                x-kubernetes-map-type: atomic
              source:
                description: source describes the origin of the document content and
                  metadata.
                properties:
                  huggingFace:
                    description: |-
                      huggingFace pulls artifacts from HuggingFace Hub.
                      The operator creates a managed PVC and a one-off download Job.
                    properties:
                      endpoint:
                        description: |-
                          endpoint is the base URL for HuggingFace API requests.
                          Defaults to "https://huggingface.co" if not specified.
                        type: string
                      fileName:
                        description: fileName is the specific file to pull from the
                          repo (e.g. a single GGUF for llama.cpp).
                        type: string
                      repo:
                        description: |-
                          repo is the HuggingFace repository id (e.g. meta-llama/Llama-3.1-8B-Instruct).
                          Defaults from modelClassRef.baseModelId when omitted.
                        type: string
                      revision:
                        description: revision is the branch, tag, or commit to pull.
                          Defaults to "main".
                        type: string
                      tokenSecretRef:
                        description: |-
                          tokenSecretRef references a Secret key holding an HF token for gated or private repos.
                          Injected into the download Job only; inference pods do not receive the token.
                        properties:
                          key:
                            description: The key of the secret to select from.  Must
                              be a valid secret key.
                            type: string
                          name:
                            default: ""
                            description: |-
                              Name of the referent.
                              This field is effectively required, but due to backwards compatibility is
                              allowed to be empty. Instances of this type with an empty value here are
                              almost certainly wrong.
                              More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
                            type: string
                          optional:
                            description: Specify whether the Secret or its key must
                              be defined
                            type: boolean
                        required:
                        - key
                        type: object
                        x-kubernetes-map-type: atomic
                    required:
                    - repo
                    type: object
                  pvc:
                    description: |-
                      pvc mounts artifacts from a PersistentVolumeClaim.
                      The user is responsible for populating the volume before referencing it.
                    properties:
                      claimName:
                        description: claimName is the name of an existing PVC in the
                          same namespace.
                        type: string
                      filePath:
                        description: filePath is the path inside the PVC where the
                          artifact is located.
                        type: string
                    required:
                    - claimName
                    type: object
                  url:
                    description: |-
                      url downloads artifacts from an arbitrary HTTP/HTTPS URL.
                      The operator creates a managed PVC and a one-off download Job.
                    properties:
                      authSecretRef:
                        description: |-
                          authSecretRef references a Secret whose key-value pairs are injected as HTTP
                          request headers into the download Job. Not mounted in inference pods.
                        properties:
                          name:
                            default: ""
                            description: |-
                              Name of the referent.
                              This field is effectively required, but due to backwards compatibility is
                              allowed to be empty. Instances of this type with an empty value here are
                              almost certainly wrong.
                              More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
                            type: string
                        type: object
                        x-kubernetes-map-type: atomic
                      checksum:
                        description: 'checksum is the expected checksum of the downloaded
                          file (format: sha256:<hex>).'
                        type: string
                      fileName:
                        description: |-
                          fileName is the filename to write inside the PVC.
                          Defaults to the last path segment of the URL.
                        type: string
                      url:
                        description: url is the HTTP or HTTPS URL to download the
                          artifacts from.
                        type: string
                    required:
                    - url
                    type: object
                type: object
            required:
            - chunkingStrategy
            - knowledgeBaseRef
            - source
            type: object
          status:
            description: status defines the observed state of Document
            properties:
              conditions:
                description: |-
                  conditions represent the current state of the Document resource.
                  Each condition has a unique type and reflects the status of a specific aspect of the resource.

                  Standard condition types include:
                  - "Available": the resource is fully functional
                  - "Progressing": the resource is being created or updated
                  - "Degraded": the resource failed to reach or maintain its desired state

                  The status of each condition is one of True, False, or Unknown.
                items:
                  description: Condition contains details for one aspect of the current
                    state of this API Resource.
                  properties:
                    lastTransitionTime:
                      description: |-
                        lastTransitionTime is the last time the condition transitioned from one status to another.
                        This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
                      format: date-time
                      type: string
                    message:
                      description: |-
                        message is a human readable message indicating details about the transition.
                        This may be an empty string.
                      maxLength: 32768
                      type: string
                    observedGeneration:
                      description: |-
                        observedGeneration represents the .metadata.generation that the condition was set based upon.
                        For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
                        with respect to the current state of the instance.
                      format: int64
                      minimum: 0
                      type: integer
                    reason:
                      description: |-
                        reason contains a programmatic identifier indicating the reason for the condition's last transition.
                        Producers of specific condition types may define expected values and meanings for this field,
                        and whether the values are considered a guaranteed API.
                        The value should be a CamelCase string.
                        This field may not be empty.
                      maxLength: 1024
                      minLength: 1
                      pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
                      type: string
                    status:
                      description: status of the condition, one of True, False, Unknown.
                      enum:
                      - "True"
                      - "False"
                      - Unknown
                      type: string
                    type:
                      description: type of condition in CamelCase or in foo.example.com/CamelCase.
                      maxLength: 316
                      pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
                      type: string
                  required:
                  - lastTransitionTime
                  - message
                  - reason
                  - status
                  - type
                  type: object
                type: array
                x-kubernetes-list-map-keys:
                - type
                x-kubernetes-list-type: map
              ingestedAt:
                description: ingestedAt is the timestamp of the last successful ingestion.
                format: date-time
                type: string
              jobName:
                description: jobName is the name of the active or most-recently-completed
                  ingestor Job.
                type: string
              observedGeneration:
                description: observedGeneration is the .metadata.generation last reconciled.
                format: int64
                type: integer
              phase:
                description: 'phase is the current ingestion phase: Pending, Ingesting,
                  Ready, Failed, or Egesting.'
                enum:
                - Pending
                - Ingesting
                - Ready
                - Failed
                - Egesting
                type: string
            type: object
        required:
        - spec
        type: object
    served: true
    storage: true
    subresources:
      status: {}