Skip to main content
GET
Get Alignment Project

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

id
string
required

Response

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

alignment_id
string
required

Unique identifier for the alignment project

Examples:

"alignment-abc123"

"alignment-xyz789"

alignment_name
string
required

Human-readable name for the alignment project

Examples:

"Customer Support Model"

"Legal Document Assistant"

"Medical Q&A Bot"

base_model
string
required

ID of the base model used for alignment training

Examples:

"qwen-v2p5-0p5b-instruct"

"model-20240229"

status
enum<string>
required

Current status of the alignment project (PROCESSING, READY, FAILED)

Available options:
PROCESSING,
READY,
FAILED,
DEPLOYING,
EVALUATING,
UNDEPLOYED,
EVALUATED,
STOPPED,
QUEUED
created_date
string
required

ISO 8601 timestamp when the project was created

Examples:

"2024-01-15T10:30:00Z"

"2024-02-01T09:15:00Z"

document_ids
string[]
required

List of document IDs used for alignment training

Examples:
document_count
integer
required

Total number of documents used for training

Required range: x >= 0
Examples:

5

12

3

creator
string
required

Email/username of the user who created this project

Examples:

"user@example.com"

"admin@company.com"

queue_position
integer | null

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

completed_date
string | null

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

Example:

"2024-01-15T12:45:00Z"

performance_metrics
AlignmentProjectPerformanceMetrics · object | null

Performance comparison metrics showing before/after alignment improvements (available after evaluation)

progress
integer | null

Training progress percentage (0-100). Null if not started or completed.

Required range: 0 <= x <= 100
Example:

0

estimated_completion
string | null

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

Example:

"2024-01-15T14:00:00Z"

error
string | null

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

Example:

"Training failed: insufficient data"

evaluation_id
string | null

Latest evaluation ID for this alignment

Example:

"eval-def456"

model_id
string | null

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

Example:

"alignment-xyz789-deployed"

gpu_training_completed
boolean | null

Whether GPU training completed successfully. True if completed, False if failed/cancelled, null if still in progress.

Example:

true

is_adapter_available
boolean | null

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:

true