Alignment Projects

Get Alignment Project

Retrieve detailed information about a specific alignment project.

This endpoint fetches comprehensive details about an alignment project including metadata, associated documents, train-time alignment progress, status, performance metrics, and evaluation information.

Path Parameters:

alignment_id: Unique identifier of the alignment project

Returns:

alignment_id: Alignment project identifier
alignment_name: Project name
base_model_id: Base model identifier used for alignment
status: Project status (QUEUED, PROCESSING, READY, FAILED, STOPPED)
queue_position, stop_requested_at, early_deployable: run qualifiers, same as the status endpoint
created_at: ISO timestamp when project was created
completed_at (optional): ISO timestamp when project completed
updated_at: Last update timestamp
eta_seconds (optional): not wired up yet, always null
document_ids: List of document IDs the synthetic training dataset was generated from
document_count: Number of documents used
creator: Username or ID of the project creator
performance_metrics (optional): Train-time alignment metrics (loss, accuracy, etc.)
progress (optional): Train-time alignment progress percentage (0-100)
estimated_completion (optional): Estimated completion time
error (optional): Error message if project failed
degraded (optional): True when the run reached READY but a stage failed on the way
stage_failures (optional): Stage failures on the way, if any
evaluation_id (optional): Auto-evaluation ID if triggered
model_id (optional): Deployed model ID for evaluation

Raises:

404: If alignment project not found or doesn't belong to user

Example Request:

GET /api/v3/alignment/alignment_01k4x9m2p7q3r8c1
Headers: {"Authorization": "Bearer <api_key>"}

Example Response (Completed):

{
  "alignment_id":"alignment_01k4x9m2p7q3r8c1",
  "alignment_name": "Contract Risk Domain Alignment",
  "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
  "status": "READY",
  "created_at": "2024-01-15T10:30:00Z",
  "completed_at": "2024-01-15T14:45:00Z",
  "document_ids": ["document_01k4x9m2p7q3r5s8", "document_01k4x9m2p7q3r5sc", "document_01k4x9m2p7q3r5sd"],
  "document_count": 3,
  "creator": "user-123",
  "performance_metrics": {
    "final_loss": 0.15,
    "accuracy": 0.92,
    "perplexity": 2.3
  },
  "evaluation_id": "evaluation_01k4x9m2p7q3r7b1",
  "model_id": "alignment_01k4x9m2p7q3r8c1-deployed"
}

Example Response (In Progress):

{
  "alignment_id":"alignment_01k4x9m2p7q3r8c2",
  "alignment_name": "Technical Documentation Alignment",
  "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
  "status": "PROCESSING",
  "created_at": "2024-01-16T09:00:00Z",
  "document_ids": ["document_01k4x9m2p7q3r5sh", "document_01k4x9m2p7q3r5sj"],
  "document_count": 2,
  "creator": "user-123",
  "progress": 45,
  "estimated_completion": "2024-01-16T11:30:00Z"
}

Notes:

Returns full project details including train-time alignment progress and performance
model_id is only available for projects that have been deployed for evaluation
evaluation_id is the evaluation created from benchmark_id, present once train-time alignment finishes
performance_metrics are populated after train-time alignment completes
progress and estimated_completion are available during train-time alignment
error field contains failure details if status is FAILED

get/api/v3/alignment-projects/{alignment_id}

Request

Base URL
https://api.nugen.in
Auth
HTTP bearer

Path parameters

alignment_idstring required

ID of the alignment project, returned when it was created

Response

Returns detailed information about a specific alignment project, including metadata, associated documents, train-time alignment progress, status, performance metrics, and evaluation information

alignment_idstring required

Unique identifier for the alignment project

alignment_namestring required

Human-readable name for the alignment project

base_model_idstring required

ID of the base model used for train-time alignment

status'QUEUED' | 'PROCESSING' | 'READY' | 'FAILED' | 'STOPPED' required

Lifecycle status of a resource that runs asynchronously. Stored as is and returned as is, with no translation in between.

QUEUED: accepted and waiting for its workflow to start
PROCESSING: running
READY: finished successfully
FAILED: failed at any stage
STOPPED: stopped by the user before completion

queue_positioninteger nullable

Place in the queue while status is QUEUED, 1 meaning next to start. Null once execution has begun.

stop_requested_atstring nullable

Set once a stop was requested; the run ends STOPPED.

early_deployableboolean

True once train-time alignment has written a checkpoint, so POST /models/{model_id}/deployment?early=true will succeed. Only meaningful while status is still PROCESSING; false once train-time alignment has finished, since a normal deploy applies then.

created_atstring date-time required

ISO 8601 timestamp when the project was created

completed_atstring nullable

ISO 8601 timestamp when the project completed (null if still in progress or failed)

updated_atstring nullable

Last update timestamp.

eta_secondsinteger nullable

Estimated time remaining in seconds. Not wired up yet, always null.

document_idsstring[] required

List of document IDs used for train-time alignment

document_countinteger required

Total number of documents used for train-time alignment

creatorstring required

Email/username of the user who created this project

progressinteger nullable

Train-time alignment progress percentage (0-100). Null if not started or completed.

estimated_completionstring nullable

Estimated completion time (ISO 8601 timestamp). Null if not available or completed.

errorstring nullable

Error message if the alignment project failed. Null if no error.

degradedboolean nullable

True when the run reached its end state but a stage failed on the way.

evaluation_idstring nullable

Latest evaluation ID for this alignment

model_idstring nullable

Deployed model ID if the aligned model was automatically deployed for evaluation

gpu_training_completedboolean nullable

Whether train-time alignment completed successfully. True if completed, False if failed/cancelled, null if still in progress.

is_adapter_availableboolean nullable

True when an adapter checkpoint is live on the inference server and the model is ready for inference. Use model_id from this response to call the inference endpoint.

Example response

{
  "alignment_id": "alignment_01k4x9m2p7q3r8c1",
  "alignment_name": "Contract Risk Model",
  "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
  "completed_at": "2024-01-15T12:45:00Z",
  "created_at": "2024-01-15T10:30:00Z",
  "creator": "user@example.com",
  "document_count": 3,
  "document_ids": [
    "document_01k4x9m2p7q3r5s8",
    "document_01k4x9m2p7q3r5s9",
    "document_01k4x9m2p7q3r5sb"
  ],
  "evaluation_id": "evaluation_01k4x9m2p7q3r7b1",
  "model_id": "alignment_01k4x9m2p7q3r8c1-deployed",
  "performance_metrics": {
    "accuracy_after": 0.92,
    "accuracy_before": 0.75,
    "domain_violations_after": 2,
    "domain_violations_before": 12,
    "uncertainty_after": 0.15,
    "uncertainty_before": 0.35
  },
  "progress": 100,
  "status": "READY"
}

Changes

No recorded changes to this operation across all 1 revision of this API.