Create Classify Job

POST/api/v2/classify

Create a classify job.

Classifies a document against a set of rules. Set file_input to a file ID (dfl-...) or parse job ID (pjb-...), and provide either inline configuration with rules or a configuration_id referencing a saved preset.

Each rule has a type (the label to assign) and a description (natural language criteria). The classifier returns the best matching rule with a confidence score.

The job runs asynchronously. Poll GET /classify/{job_id} to check status and retrieve results.

Query ParametersExpand Collapse

organization_id: optional string

project_id: optional string

Cookie ParametersExpand Collapse

session: optional string

Body ParametersJSONExpand Collapse

configuration: optional ClassifyConfiguration { rules, mode, parsing_configuration }

Configuration for a classify job.

rules: array of object { description, type }

Classify rules to evaluate against the document (at least one required)

description: string

Natural language criteria for matching this rule

maxLength500

minLength10

type: string

Document type to assign when rule matches

maxLength50

minLength1

mode: optional "FAST"

Classify execution mode

parsing_configuration: optional object { lang, max_pages, target_pages }

Parsing configuration for classify jobs.

lang: optional string

ISO 639-1 language code for the document

max_pages: optional number

Maximum number of pages to process. Omit for no limit.

minimum1

target_pages: optional string

Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.

configuration_id: optional string

Saved configuration ID

Deprecatedfile_id: optional string

Deprecated: use file_input instead

file_input: optional string

File ID or parse job ID to classify

maxLength200

Deprecatedparse_job_id: optional string

Deprecated: use file_input instead

transaction_id: optional string

Idempotency key scoped to the project

webhook_configurations: optional array of object { webhook_events, webhook_headers, webhook_output_format, webhook_url }

Outbound webhook endpoints to notify on job status changes

webhook_events: optional array of "extract.pending" or "extract.success" or "extract.error" or 20 more

Events to subscribe to (e.g. ‘parse.success’, ‘extract.error’). If null, all events are delivered.

One of the following:

"extract.pending"

"extract.success"

"extract.error"

"extract.partial_success"

"extract.cancelled"

"parse.pending"

"parse.running"

"parse.success"

"parse.error"

"parse.partial_success"

"parse.cancelled"

"classify.pending"

"classify.running"

"classify.success"

"classify.error"

"classify.partial_success"

"classify.cancelled"

"sheets.pending"

"sheets.success"

"sheets.error"

"sheets.partial_success"

"sheets.cancelled"

"unmapped_event"

webhook_headers: optional map[string]

Custom HTTP headers sent with each webhook request (e.g. auth tokens)

webhook_output_format: optional string

Response format sent to the webhook: ‘string’ (default) or ‘json’

webhook_url: optional string

URL to receive webhook POST notifications

ReturnsExpand Collapse

id: string

Unique identifier

configuration: ClassifyConfiguration { rules, mode, parsing_configuration }

Classify configuration used for this job

rules: array of object { description, type }

Classify rules to evaluate against the document (at least one required)

description: string

Natural language criteria for matching this rule

maxLength500

minLength10

type: string

Document type to assign when rule matches

maxLength50

minLength1

mode: optional "FAST"

Classify execution mode

parsing_configuration: optional object { lang, max_pages, target_pages }

Parsing configuration for classify jobs.

lang: optional string

ISO 639-1 language code for the document

max_pages: optional number

Maximum number of pages to process. Omit for no limit.

minimum1

target_pages: optional string

Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.

document_input_type: "url" or "file_id" or "parse_job_id"

Whether the input was a file or parse job (FILE or PARSE_JOB)

One of the following:

"url"

"file_id"

"parse_job_id"

file_input: string

ID of the input file or parse job

project_id: string

Project this job belongs to

status: "PENDING" or "RUNNING" or "COMPLETED" or "FAILED"

Current job status: PENDING, RUNNING, COMPLETED, or FAILED

One of the following:

"PENDING"

"RUNNING"

"COMPLETED"

"FAILED"

user_id: string

User who created this job

configuration_id: optional string

Product configuration ID

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if job failed

parse_job_id: optional string

Associated parse job ID

result: optional ClassifyResult { confidence, reasoning, type }

Result of classifying a document.

confidence: number

Confidence score between 0.0 and 1.0

maximum1

minimum0

reasoning: string

Why the document matched (or didn’t match) the returned rule

type: string

Matched rule type, or null if no rule matched

transaction_id: optional string

Idempotency key

updated_at: optional string

Update datetime

formatdate-time

Create Classify Job

curl https://api.cloud.llamaindex.ai/api/v2/classify \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
    -d '{}'

{
  "id": "id",
  "configuration": {
    "rules": [
      {
        "description": "contains invoice number, line items, and total amount",
        "type": "invoice"
      }
    ],
    "mode": "FAST",
    "parsing_configuration": {
      "lang": "en",
      "max_pages": 10,
      "target_pages": "1,3,5-7"
    }
  },
  "document_input_type": "url",
  "file_input": "file_input",
  "project_id": "project_id",
  "status": "PENDING",
  "user_id": "user_id",
  "configuration_id": "configuration_id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "error_message": "error_message",
  "parse_job_id": "parse_job_id",
  "result": {
    "confidence": 0,
    "reasoning": "reasoning",
    "type": "type"
  },
  "transaction_id": "transaction_id",
  "updated_at": "2019-12-27T18:11:19.117Z"
}

Returns Examples

{
  "id": "id",
  "configuration": {
    "rules": [
      {
        "description": "contains invoice number, line items, and total amount",
        "type": "invoice"
      }
    ],
    "mode": "FAST",
    "parsing_configuration": {
      "lang": "en",
      "max_pages": 10,
      "target_pages": "1,3,5-7"
    }
  },
  "document_input_type": "url",
  "file_input": "file_input",
  "project_id": "project_id",
  "status": "PENDING",
  "user_id": "user_id",
  "configuration_id": "configuration_id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "error_message": "error_message",
  "parse_job_id": "parse_job_id",
  "result": {
    "confidence": 0,
    "reasoning": "reasoning",
    "type": "type"
  },
  "transaction_id": "transaction_id",
  "updated_at": "2019-12-27T18:11:19.117Z"
}