Creative DNA for Ad Archives

# creative-dna: one manifest spins up the namespace.
# Platform manifest schema (GET /v1/discovery/schema). Validate with POST /v1/manifest/validate,
# apply with POST /v1/manifest/apply or the Deploy button. Wiring comes from the flow diagram:
# edges are bucket -> collection sources, collection -> retriever scope, retriever -> view.
# Applying a SECOND time, over a namespace this template already created: use
# POST /v1/manifest/apply?mode=create_missing, which creates what is missing and leaves
# what exists alone. The default, create_only, fails the WHOLE apply and rolls it back if
# any resource already exists, so an upgrade looks like a dead end without this. Use
# mode=upsert to also patch resources that exist but have drifted from this file.
version: '1.0'
metadata:
  name: creative-dna
  description: "Namespace template creative-dna. Generated from the flow diagram on mixpeek.com/templates/creative-dna."
namespaces:
  - name: creative-dna
    description: "Everything below lives in this namespace."
    feature_extractors:
      - name: multimodal_extractor
        version: v1
      - name: text_extractor
        version: v1

# Data sources. A storage connection carries credentials, so it is created in Studio
# (or POST /v1/organizations/storage-connections) and synced into the bucket named here.
#   ad-library-pull: manual, one-shot, your ad creatives and their copy -> bucket ad-creatives
buckets:
  - name: ad-creatives
    namespace: creative-dna
    description: "Meant to be fed by ad-library-pull (manual, one-shot): upload files here or write them through the API. Nothing arrives until you do."
    schema:
      properties:
        ad_id:
          type: string
          required: true
        brand_slug:
          type: string
          required: true
        brand_name:
          type: string
        source:
          type: string
        source_url:
          type: string
        headline:
          type: string
        primary_text:
          type: string
          required: true
        ad_type:
          type: string
        creative_asset_url:
          type: video
          required: true
        published_at:
          type: string
collections:
  - name: ads-scenes
    namespace: creative-dna
    description: "multimodal_extractor@v1 over bucket ad-creatives. Feeds brand-scenes."
    source:
      type: bucket
      bucket: ad-creatives
    feature_extractor:
      name: multimodal_extractor
      version: v1
      input_mappings:
        video: creative_asset_url
      field_passthrough:
        - source_path: ad_id
          required: true
        - source_path: brand_slug
          required: true
        - source_path: brand_name
          required: true
        - source_path: ad_type
        - source_path: source
        - source_path: source_url
        - source_path: headline
        - source_path: primary_text
        - source_path: published_at
    enabled: true
  - name: ads-text
    namespace: creative-dna
    description: "text_extractor@v1 over bucket ad-creatives. Feeds copy-search."
    source:
      type: bucket
      bucket: ad-creatives
    feature_extractor:
      name: text_extractor
      version: v1
      input_mappings:
        text: primary_text
      field_passthrough:
        - source_path: ad_id
          required: true
        - source_path: brand_slug
          required: true
        - source_path: brand_name
          required: true
        - source_path: ad_type
        - source_path: source
        - source_path: source_url
        - source_path: headline
        - source_path: primary_text
        - source_path: published_at
    enabled: true

# NOT APPLIED. Face recognition is turned off on Mixpeek Cloud, so this face step does not deploy. It runs on a dedicated or customer-hosted deployment, where face_identity_extractor is served.
# The block below is correct and is emitted commented out so the rest of this
# manifest applies; an apply is all-or-nothing and would otherwise roll back.
#   - name: ads-faces
#     namespace: creative-dna
#     description: "face_identity_extractor@v1 over bucket ad-creatives. Feeds cast-identification."
#     source:
#       type: bucket
#       bucket: ad-creatives
#     feature_extractor:
#       name: face_identity_extractor
#       version: v1
#       input_mappings:
#         video: creative_asset_url
#       field_passthrough:
#         - source_path: ad_id
#           required: true
#         - source_path: brand_slug
#           required: true
#         - source_path: brand_name
#           required: true
#         - source_path: ad_type
#         - source_path: source
#         - source_path: source_url
#         - source_path: headline
#         - source_path: primary_text
#         - source_path: published_at
#     enabled: true
retrievers:
  - name: brand-scenes
    namespace: creative-dna
    description: "Searches ads-scenes across 1 feature index."
    collections:
      - ads-scenes
    input_schema:
      query:
        type: text
        required: true
        description: "What to look for; searched across every index below"
    stages:
      - stage_name: search
        stage_id: feature_search
        parameters:
          searches:
            - feature_uri: "mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding"
              query:
                input_mode: text
                value: "{{INPUT.query}}"
              top_k: 100
          fusion: rrf
          final_top_k: 100
    tags:
      - template:creative-dna
  # NOT APPLIED. Face recognition is turned off on Mixpeek Cloud, so this face step does not deploy. It runs on a dedicated or customer-hosted deployment, where face_identity_extractor is served.
  # - name: cast-identification
  #   namespace: creative-dna
  #   description: "Searches ads-faces across 1 feature index."
  #   collections:
  #     - ads-faces
  #   input_schema:
  #     query:
  #       type: text
  #       required: true
  #       description: "URL of the image or frame to match; encoded by the index below and compared against it"
  #   stages:
  #     - stage_name: search
  #       stage_id: feature_search
  #       parameters:
  #         searches:
  #           - feature_uri: "mixpeek://face_identity_extractor@v1/insightface__arcface"
  #             query:
  #               input_mode: content
  #               value: "{{INPUT.query}}"
  #             top_k: 50
  #         fusion: rrf
  #         final_top_k: 50
  #   tags:
  #     - template:creative-dna
  - name: copy-search
    namespace: creative-dna
    description: "Searches ads-text across 1 feature index."
    collections:
      - ads-text
    input_schema:
      query:
        type: text
        required: true
        description: "What to look for; searched across every index below"
    stages:
      - stage_name: search
        stage_id: feature_search
        parameters:
          searches:
            - feature_uri: "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1"
              query:
                input_mode: text
                value: "{{INPUT.query}}"
              top_k: 50
          fusion: rrf
          final_top_k: 50
    tags:
      - template:creative-dna