Update to Pixeltable

{
  "canonical_app_id": null,
  "connector_id": null,
  "created_at": "2026-09-15T21:54:55.041594Z",
  "discoverability": "LISTED",
  "id": "plugins_6aa9bce6481c81918d73be74740eed28",
  "is_template": false,
  "name": "pixeltable",
  "release": {
    "app_ids": [],
    "app_manifest": null,
    "app_templates": [],
    "description": "Build multimodal AI applications with Pixeltable.",
    "display_name": "Pixeltable",
    "id": "pluginrel_021d2b9ad4908191b843531755a56c57",
    "interface": {
      "brand_color": "#2563EB",
      "capabilities": [
        "Read",
        "Write"
      ],
      "category": "Developer Tools",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_00000000c41481fda28305568e9194a2",
      "default_prompt": "Build a RAG app over my documents, images, and videos",
      "default_prompts": [
        "Build a RAG app over my documents, images, and videos",
        "Turn this AI pipeline into one declarative Pixeltable app",
        "Take this Pixeltable app from local development to Cloud"
      ],
      "developer_name": "Pixeltable",
      "logo_url": "https://files.openai.com/content?id=file_00000000a91081fd8b0a640e2bd7c278",
      "logo_url_dark": null,
      "long_description": "Build multimodal AI backends in one Python file. Pixeltable combines database, orchestration, indexing, and serving for images, video, audio, documents, and model outputs. Define transformations as computed columns in the schema; insert a row and the dependent pipeline runs incrementally. Run the same declarative app locally or on Pixeltable Cloud.",
      "plugin_category_id": "developer tools",
      "privacy_policy_url": "https://www.pixeltable.com/privacy",
      "screenshot_urls": [],
      "short_description": "Unified multimodal backend",
      "terms_of_service_url": "https://www.pixeltable.com/terms",
      "website_url": "https://docs.pixeltable.com/"
    },
    "keywords": [
      "pixeltable",
      "multimodal",
      "rag",
      "embeddings",
      "agents",
      "computed-columns"
    ],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Build multimodal AI apps with Pixeltable. One application file (app.py) declares TableModel tables and FastAPIRouter routes. Create tables with pxt schema update. Start HTTP with pxt service update. Insert a row or POST to try the app. Use computed columns instead of LangChain, pandas-as-store, or a separate vector DB. Use when building RAG, processing images/video/audio/documents, or serving an API. Do NOT use for general Python or direct PostgreSQL administration.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $pixeltable to build or debug this Pixeltable application.",
          "display_name": "Pixeltable",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Build multimodal apps with declarative Pixeltable tables"
        },
        "name": "pixeltable",
        "plugin_release_skill_id": "pluginrsk_6aa9bce928588191b9b06b8e3fb97efe"
      }
    ],
    "version": "2.10.2"
  },
  "scope": "GLOBAL",
  "status": "ENABLED"
}