The Taxonomy Enrich stage classifies documents against predefined taxonomies, adding structured category labels and hierarchical classifications to your search results.
Stage Category : APPLY (Enriches documents with classifications)Transformation : N documents → N documents (with taxonomy labels added)
When to Use Use Case Description Content categorization Auto-classify documents into topics Faceted search Add filterable category facets Compliance tagging Apply regulatory classifications Product taxonomy Classify into product hierarchies
When NOT to Use Scenario Recommended Alternative Free-form tagging llm_enrichmentPre-classified content Skip this stage Custom classification logic api_call to custom service
Parameters Parameter Type Default Description taxonomy_idstring Required ID of the taxonomy to use content_fieldstring contentField to classify result_fieldstring taxonomyField for classification results max_depthinteger nullMaximum hierarchy depth top_kinteger 3Number of top classifications min_confidencefloat 0.5Minimum confidence threshold include_ancestorsboolean trueInclude parent categories
Configuration Examples Basic Classification
High-Confidence Only
Hierarchical with Ancestors
Multiple Classifications
{ "stage_type" : "apply" , "stage_id" : "taxonomy_enrich" , "parameters" : { "taxonomy_id" : "product_categories" , "content_field" : "content" , "result_field" : "categories" } }
Output Schema Basic Classification { "document_id" : "doc_123" , "content" : "Latest smartphone with 5G connectivity..." , "categories" : { "primary" : { "id" : "electronics.mobile.smartphones" , "name" : "Smartphones" , "confidence" : 0.95 }, "all" : [ { "id" : "electronics.mobile.smartphones" , "name" : "Smartphones" , "confidence" : 0.95 }, { "id" : "electronics.mobile" , "name" : "Mobile Devices" , "confidence" : 0.82 }, { "id" : "electronics" , "name" : "Electronics" , "confidence" : 0.78 } ] } }
With Ancestors { "document_id" : "doc_456" , "content" : "Investment banking services..." , "industry" : { "primary" : { "id" : "finance.banking.investment" , "name" : "Investment Banking" , "confidence" : 0.91 }, "ancestors" : [ { "id" : "finance.banking" , "name" : "Banking" , "level" : 2 }, { "id" : "finance" , "name" : "Finance" , "level" : 1 } ], "path" : "Finance > Banking > Investment Banking" } }
Low Confidence (No Match) { "document_id" : "doc_789" , "content" : "Random unrelated content..." , "categories" : { "primary" : null , "all" : [], "message" : "No classifications above confidence threshold" } }
Taxonomy Structure Taxonomies are hierarchical classification systems:
Electronics ├── Mobile Devices │ ├── Smartphones │ ├── Tablets │ └── Wearables ├── Computers │ ├── Laptops │ ├── Desktops │ └── Components └── Audio ├── Headphones └── Speakers
Each node has:
ID : Dot-notation path (e.g., electronics.mobile.smartphones)Name : Human-readable labelLevel : Depth in hierarchy (1 = root)
Metric Value Latency 10-50ms per document Batch processing Automatic Model type Embedding-based classification Parallel execution Up to 20 concurrent
Pre-compute taxonomy embeddings for faster classification. Use top_k: 1 and higher min_confidence when you only need the best match.
Common Pipeline Patterns Search + Classify + Filter [ { "stage_type" : "filter" , "stage_id" : "semantic_search" , "parameters" : { "query" : "{{INPUT.query}}" , "vector_index" : "text_extractor_v1_embedding" , "top_k" : 100 } }, { "stage_type" : "apply" , "stage_id" : "taxonomy_enrich" , "parameters" : { "taxonomy_id" : "product_categories" , "result_field" : "category" , "top_k" : 1 , "min_confidence" : 0.7 } }, { "stage_type" : "filter" , "stage_id" : "structured_filter" , "parameters" : { "conditions" : { "field" : "category.primary.id" , "operator" : "starts_with" , "value" : "{{INPUT.category_filter}}" } } } ]
Multi-Taxonomy Classification [ { "stage_type" : "filter" , "stage_id" : "semantic_search" , "parameters" : { "query" : "{{INPUT.query}}" , "vector_index" : "text_extractor_v1_embedding" , "top_k" : 50 } }, { "stage_type" : "apply" , "stage_id" : "taxonomy_enrich" , "parameters" : { "taxonomy_id" : "topics" , "result_field" : "topic" } }, { "stage_type" : "apply" , "stage_id" : "taxonomy_enrich" , "parameters" : { "taxonomy_id" : "sentiment" , "result_field" : "sentiment" } } ]
Faceted Search Results [ { "stage_type" : "filter" , "stage_id" : "hybrid_search" , "parameters" : { "query" : "{{INPUT.query}}" , "vector_index" : "text_extractor_v1_embedding" , "top_k" : 100 } }, { "stage_type" : "apply" , "stage_id" : "taxonomy_enrich" , "parameters" : { "taxonomy_id" : "categories" , "result_field" : "facets" , "top_k" : 3 , "include_ancestors" : true } } ]
Error Handling Error Behavior Unknown taxonomy_id Stage fails No match found Empty classification, continues Invalid content_field Stage fails Low confidence Filtered by min_confidence
