Skip to main content
POST
Alignment Generate
The alignment endpoints are deprecated. Use the data jobs endpoints instead.

Authorizations

Authorization
string
header
required

Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.

Body

application/json
instructions
string
required

Task description/instructions for the alignment task

files
string[]
required

List of file ids to use for alignment

system_prompt
string | null

Optional system prompt baked into the generated dataset's system role on every conversation. If omitted, one is generated from instructions and the recursive document summary.

type
enum<string>
default:principle

Type of alignment task (principle or context_data)

Available options:
principle,
context_data
vector_database_id
string | null

Optional vector database id to use for context retrieval during context_data alignment

Response

Success

id
string
required
created_at
string<date-time>
required
status
enum<string>
required
Available options:
pending,
queued,
running,
cancelled,
failed,
completed,
stopped
updated_at
string<date-time> | null
completed_at
string<date-time> | null
stopped_at
string<date-time> | null
current_step
string | null

The processing step the job is currently working on. null until the job starts running.

step_progress

Progress through the current step. null when no step is in progress.

progress
number | null

Overall completion of the job across all steps. null until progress can be calculated.

estimated_completion_at
string<date-time> | null

Projected completion timestamp (UTC). null until enough progress data is available to produce an estimate.

eta_minutes
integer | null

Estimated number of minutes remaining until the job completes. null until an estimate is available.

status_message
string | null

Human-readable description of the job's current state, suitable for display to end users.

output_files
AlignmentOutput · object[]
Last modified on August 10, 2026