search

Analysis

Search Assets & Models

Search for assets, models, or workflows by text, visual similarity, or filters. Args: - target: required — "assets", "models", or "workflows" - query: text search query - image: single image URL or asset ID for visual similarity (mutually exclusive with images) - images: {like: [...], unlike: [...]} — multi-image similarity with positive and negative examples (mutually exclusive with image) - query_semantic_ratio: 0 = keyword only (default), 0.5–0.8 = hybrid, 1 = pure semantic - image_semantic_ratio: 0 = feature matching, 1 = semantic embedding (default) - filters: structured filters — kind, model_id, type, tags, created_after, created_before, status, privacy, mime_type, collection_ids - filter: raw Meilisearch filter expression for advanced queries - sort_by: e.g. ["createdAt:desc"] — NOT compatible with semantic search (query_semantic_ratio > 0), ignored when semantic is active - public: true = search public, false/omitted = search private Returns: matching results with metadata. To view an asset, call display_asset with the asset ID — do NOT try to render asset URLs directly (they are too large for inline display). Examples: - "Find 3D voxel assets" -> target="assets", query="voxel", filters={kind: "3d"} - "Find my videos" -> target="assets", filters={kind: "video"} - "Find cinematic videos tagged hero" -> target="assets", filters={kind: "video", tags: ["cinematic", "hero"]} - "Find audio assets" -> target="assets", filters={kind: "audio"} - "Search for dark medieval mood" -> target="assets", query="dark medieval atmosphere", query_semantic_ratio=0.8 - "Find assets similar to this one" -> target="assets", image="<asset_id>" - "Find assets like these but not like that" -> target="assets", images={like: ["<good_id_1>", "<good_id_2>"], unlike: ["<bad_id>"]} - "Find similar assets but more stylized" -> target="assets", images={like: ["<ref_id>"], unlike: ["<unwanted_id>"]}, query_semantic_ratio=0.5, query="stylized" - "Search public anime models" -> target="models", query="anime style", public=true - "Find utility tools" -> target="models", query="tool" - "Recent large 3D assets" -> target="assets", filters={kind: "3d"}, filter='width > 512', sort_by=["createdAt:desc"] - "Assets from January 2025" -> target="assets", filters={created_after: "2025-01-01", created_before: "2025-02-01"} Don't use when: You already know the exact asset_id or model_id and need details, display, or mutations. Prefer manage_assets, manage_models, or display_asset instead.

read-onlyidempotentopen-world

Parameters

Name	Type	Required	Description
target	enum(assets \| models \| workflows)	✓	What to search: assets, models, or workflows.
query	string	—	Text search query.
image	string	—	Single image URL or asset ID for visual similarity. Mutually exclusive with images.
images	unknown	—	Multi-image similarity with positive (like) and negative (unlike) examples. Mutually exclusive with image.
public	boolean	—	Whether to include public results. true searches public, false or omitted searches private.
filters	unknown	—	Structured filter criteria — converted to Meilisearch filter syntax. Only the listed fields are valid. Use "kind" for asset type (not "modality").
filter	string	—	Raw Meilisearch filter expression for advanced filtering (e.g. 'kind = "3d" AND width > 512'). Combined with filters using AND.
query_semantic_ratio	number	—	Balance between keyword (0) and semantic (1) text search. Default 0 (keyword only).
image_semantic_ratio	number	—	Image similarity method: 0 = feature matching, 1 = semantic embedding. Default 1.
sort_by	array	—	Sort attributes, e.g. ["createdAt:desc"].
limit	number	20	Results per page (1-100).
offset	number	0	Pagination offset.
team_id	string	—	Team ID. Required if user belongs to multiple teams.
project_id	string	—	Project ID to scope the operation to.
response_format	enum(json \| markdown)	json	Output format: 'json' for structured data, 'markdown' for human-readable text.

Example Request

JSON

{
  "target": "assets",
  "query": "dragon concept art",
  "filters": {
    "modality": "image",
    "tags": [
      "dragon",
      "fantasy"
    ]
  },
  "limit": 10,
  "team_id": "team_abc123",
  "project_id": "proj_xyz789"
}

Example Response

JSON

{
  "target": "assets",
  "assets": [
    {
      "id": "asset_img001",
      "name": "dragon_sunset.png",
      "tags": [
        "dragon",
        "fantasy",
        "sunset"
      ],
      "mimeType": "image/png"
    },
    {
      "id": "asset_img002",
      "name": "dragon_cave.png",
      "tags": [
        "dragon",
        "fantasy",
        "cave"
      ],
      "mimeType": "image/png"
    }
  ],
  "estimatedTotalHits": 47
}

Common Use Cases

Find previously generated assets matching a concept to avoid regenerating
Search models by modality (image, video, 3d, audio) to discover available generators
Run visual similarity search by passing a reference image instead of a text query
Filter assets by tag or model to review the output of a specific generation run