Axelered AI

Classify

AI taxonomy classification to categorize documents automatically.

The Classify module determines the category or class of a document out of a custom taxonomy list you define. It reads the document content and maps it to the most relevant class, enabling automated sorting and routing of incoming files.

 ┌─────────────────┐       ┌──────────────────────┐       ┌─────────────────┐
 │ Incoming File   │ ────► │  Taxonomy Engine     │ ────► │ documentType:   │
 │ (e.g. Scanned   │       │  [Invoice, Contract] │       │ "contract"      │
 │ legal form)     │       └──────────────────────┘       └─────────────────┘
 └─────────────────┘
  • Dynamic Taxonomy: Define your own categories using an enum-driven JSON Schema.
  • Semantic Reasoning: The AI understands the context and intent, correctly classifying files even without specific keyword matches.
  • Confidence Driven: Combine with custom instructions to handle "other" or "unknown" categories when a file doesn't fit the taxonomy.

🏗️ Configuration

The Classify module is defined within the classificationConfig block. It uses a JSON Schema to define the classification target (typically an enum).

Parameters

ParameterTypeRequiredDescription
jsonSchemaobjectYesA JSON Schema defining the taxonomy field (e.g., using enum).
llmIdUUIDNoReference to a pre-saved LLM configuration ID.
llmConfigobjectNoInline LLM configuration overrides.

🛠️ Classification Operations

Classification is typically performed as part of a stateless process run. For a detailed technical reference of every field and parameter, see the API Process Reference.

Execute a Classification Run

To categorize documents, submit a process request to your workspace with a classificationConfig.

curl -X POST "https://api.axelered.com/v1/w/{workspace_id}/process" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "config": {
      "classificationConfig": {
        "jsonSchema": {
          "type": "object",
          "properties": {
            "documentType": {
              "type": "string",
              "enum": ["invoice", "contract", "other"]
            }
          },
          "required": ["documentType"]
        }
      }
    },
    "files": [
      {
        "url": "https://example.com/legal_form.pdf"
      }
    ]
  }'

The classification result will be available via the classificationUrl returned in the task documents list once the run reaches a completed state.

Read & List Classifications

To retrieve classification results for your documents, use the following endpoints:

On this page