Taxonomy Collections

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/Kismetkanceled/geniehelper/llms.txt

Use this file to discover all available pages before exploring further.

​

Overview

​

taxonomy_dimensions

​

Purpose

• Define classification schema for content tagging
• Store dimension names, descriptions, and allowed values
• Enable AI-powered content discovery and recommendations
• Support multi-dimensional content search

​

The 6 Dimensions

​

Key Fields

​

Example Queries

​

List All Dimensions

await use_mcp_tool({
  server_name: "directus",
  tool_name: "read-items",
  arguments: {
    collection: "taxonomy_dimensions",
    fields: ["id", "dimension_name", "display_name", "description"],
    sort: ["sort_order"]
  }
});

​

Get Dimension with Values

await use_mcp_tool({
  server_name: "directus",
  tool_name: "read-item",
  arguments: {
    collection: "taxonomy_dimensions",
    id: "dimension-uuid",
    fields: ["dimension_name", "display_name", "allowed_values", "is_multi_select"]
  }
});

​

taxonomy_mapping

​

Purpose

• Map platform-specific tags to taxonomy dimensions
• Enable fast AI-powered content classification
• Support content search and discovery
• Provide training data for taxonomy classifiers

​

Classification System

// Example: "yoga pants" tag mapping
{
  "tag": "yoga pants",
  "platform_source": "onlyfans",
  "dimension_mappings": {
    "attire": ["activewear", "casual"],
    "body_type": ["athletic", "fit"],
    "setting": ["gym", "home"]
  },
  "confidence_score": 0.92
}

​

Key Fields

​

Example Queries

​

Search for Tag

await use_mcp_tool({
  server_name: "directus",
  tool_name: "search-items",
  arguments: {
    collection: "taxonomy_mapping",
    query: "lingerie",
    fields: ["tag", "dimension_mappings", "confidence_score"]
  }
});

​

Get Tags by Dimension

// Find all tags with "athletic" in body_type dimension
await use_mcp_tool({
  server_name: "directus",
  tool_name: "read-items",
  arguments: {
    collection: "taxonomy_mapping",
    fields: ["tag", "dimension_mappings", "usage_count"],
    filter: {
      dimension_mappings: { _contains: "athletic" }
    },
    sort: ["-usage_count"],
    limit: 50
  }
});

​

Create New Mapping

await use_mcp_tool({
  server_name: "directus",
  tool_name: "create-item",
  arguments: {
    collection: "taxonomy_mapping",
    data: {
      tag: "beach photoshoot",
      platform_source: "onlyfans",
      dimension_mappings: {
        setting: ["outdoor", "beach"],
        production_quality: ["professional"],
        performance_style: ["artistic"]
      },
      confidence_score: 0.88
    }
  }
});

​

AI Classification

​

Action Flow

// Agent emits action tag in chat response
"[ACTION:taxonomy-tag:{\"media_id\":\"uuid-here\"}]"

// Action runner executes flow:
// 1. Fetch media item caption + metadata
// 2. Call ollama MCP with scout-fast-tag model
// 3. Match returned tags against taxonomy_mapping
// 4. Apply dimension_mappings to media.taxonomy_tags
// 5. Update scraped_media record

​

Custom Taxonomy Model

// Using ollama MCP to classify content
await use_mcp_tool({
  server_name: "ollama",
  tool_name: "generate",
  arguments: {
    model: "scout-fast-tag:latest",
    prompt: `Classify this content caption into taxonomy tags:\n\n"${caption}"`,
    stream: false
  }
});

​

Related Collections

• scraped_media - Content items tagged with taxonomy classifications
• action_flows - The taxonomy-tag flow that applies classifications
• agent_audits - Logs of taxonomy classification executions

​

Workflow Integration

​

Content Classification Flow

1. User uploads or scrapes new media with caption
2. AI chat interface or dashboard triggers classification
3. Agent emits [ACTION:taxonomy-tag:{"media_id":"..."}]
4. Action runner fetches media caption + existing tags
5. Calls Ollama scout-fast-tag model with caption
6. Model returns relevant tags from 3,208 mapping corpus
7. System looks up taxonomy_mapping for each tag
8. Aggregates dimension_mappings into final classification
9. Updates scraped_media.taxonomy_tags with result
10. Content now discoverable via dimension-based search

​

Search and Discovery Flow

1. User searches for “athletic outdoor content”
2. System queries taxonomy_mapping for matching tags
3. Finds tags with body_type: ["athletic"] AND setting: ["outdoor"]
4. Queries scraped_media where taxonomy_tags contains those values
5. Returns ranked results by engagement metrics

​

Best Practices

1. Normalize tags before lookup - Convert to lowercase, trim whitespace
2. Use confidence thresholds - Only apply mappings with confidence_score >= 0.7
3. Track usage - Increment usage_count when applying classifications
4. Handle multi-select - Check taxonomy_dimensions.is_multi_select before applying
5. Batch classify - Process multiple media items in single taxonomy flow execution
6. Update existing classifications - Re-run classification when captions are edited

​

Data Sources

• OnlyFans tag corpus (2,400+ tags)
• Fansly category system (600+ tags)
• Manual classification of top 200 industry terms
• Community-submitted classifications

​

Model Training

• Base model: SmolLM 135M parameters
• Training data: Nodes/Universe/taxonomy_graph.json (3,205 nodes)
• Training script: Nodes/Universe/apply_taxonomy_assignments.py
• Fine-tuning method: HITL (Human-in-the-loop) corrections
• Accuracy: 87% on validation set

​

See Also

• Media Collections - Content that receives classifications
• Ollama MCP Tools - AI model inference for classification
• Action Runner - Flow execution system