The Material KAI Vision Platform provides powerful search capabilities to help you find exactly the materials you need. The search system understands natural language, recognizes visual patterns, and can filter by specific material properties.
When you search for materials, the platform analyzes your query in multiple ways simultaneously:
All 7 dimensions are combined intelligently to give you the most relevant results.
The Understanding embedding enables searching by technical specifications:
This works because the platform embeds Qwen3-VL's structured analysis of each image (material type, dimensions, finishes, properties) via Voyage AI.
Simply describe what you're looking for in plain language:
The system automatically understands your requirements and finds matching materials.
Search using descriptions, product names, or material properties:
Upload an image to find similar materials:
Refine your search with specific material properties:
Results are ranked by how well they match your search:
Each search result includes:
Finding Alternatives:
Exploring Collections:
Specific Requirements:
The search system is optimized for speed and accuracy:
The system automatically understands complex queries:
The 7-vector fusion search dynamically adjusts embedding weights based on what the query is about. Instead of using fixed weights for every search, the system analyzes the parsed query fields and selects the optimal weight profile.
How It Works:
_select_weight_profile() examines which fields are present and selects the best profileAvailable Profiles:
| Profile | Trigger | Text | Visual | Understanding | Color | Texture | Style | Material |
|---|---|---|---|---|---|---|---|---|
| product_name | Product name or brand detected | 40% | 25% | 15% | 5% | 5% | 5% | 5% |
| color_finish | Colors or finish terms present | 10% | 20% | 15% | 30% | 5% | 15% | 5% |
| specification | Dimensions detected (e.g., 60x120cm) | 25% | 10% | 40% | 5% | 5% | 5% | 10% |
| texture_pattern | Pattern terms present | 10% | 25% | 15% | 5% | 30% | 10% | 5% |
| style_aesthetic | Style or application terms | 10% | 25% | 15% | 10% | 10% | 25% | 5% |
| material_search | Explicit material type | 15% | 15% | 25% | 5% | 10% | 5% | 25% |
| balanced | No specific signal (default) | 15% | 15% | 20% | 12.5% | 12.5% | 12.5% | 12.5% |
Selection Priority: dimensions → colors/finish → pattern → material → style/application → balanced
Examples:
"MAISON by ONSET" → product_name (text weight 40%, find by name)"matte beige tiles" → color_finish (color weight 30%, match the beige)"60x120cm porcelain R10" → specification (understanding weight 40%, match specs)"wood grain pattern ceramic" → texture_pattern (texture weight 30%, match the grain)"minimalist bathroom design" → style_aesthetic (style weight 25%, match the aesthetic)Monitoring:
ai_call_logs for every querysearch_query_tracking table records weight_profile, dynamic_weights, and weight_profile_sourceImplementation: unified_search_service.py → WEIGHT_PROFILES dict + _select_weight_profile() method
Search results include variety while maintaining relevance:
When the KAI agent calls material_search, it now provides a structured search specification that decomposes the user's query across all 7 embedding dimensions. This spec is displayed as a collapsible SearchSpecCard above the product results in the chat.
Fields in the search spec:
intent — brief description of what the user is looking forcolor_keywords / color_hex — extracted color terms and approximate hex codesmaterial_types — detected material types (e.g., porcelain, marble, wood)style_keywords — aesthetic/style terms (e.g., minimalist, japandi, industrial)texture_finish — texture or surface finish descriptionspecifications — technical specs if mentioned (e.g., R11 slip-resistant, outdoor-rated)The spec is generated by the LLM as part of its tool call (no extra API call) and emitted via onChunk with type search_spec for real-time display in the frontend.
Why it matters: Architects and specifiers need to justify material choices to clients. The search spec shows why each result was selected — turning a black-box search into an explainable recommendation.
Users can paste any design URL (Houzz, Pinterest, Dezeen, ArchDaily, manufacturer sites) and the analyze_inspiration_url tool will:
InspirationCard (color swatches, material/style tags, source thumbnail) followed by matched productsAccessible to all users via the Globe icon button in the chat toolbar, which opens a modal for URL input with an optional surface focus selector (floors, walls, countertops, etc.).
Credit cost: 1 credit for the Firecrawl scrape + Haiku token cost for extraction.