Skip to main content
POST
Create an evaluation

Authorizations

Authorization
string
header
required

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

Body

application/json

Create evaluation request

Request payload to create an evaluation.

The resource path (branch + file path) is specified in the URL after /evaluations/, for example: POST /api/repos/{namespace}/{repo}/evaluations/main/datasets/training.parquet.

input_type
enum<string>
required

Type of input data

Available options:
text,
image,
video
model_id
string<uuid>
required

ID of the model to run inference with

output_type
enum<string>
required

Type of output produced by the model

Available options:
text,
image,
video,
embeddings
prompt
string
required

Prompt template sent to the model. Use {column_name} placeholders to inject values from each row.

target_column
string
required

Column where the model output will be written

auto_commit
boolean
default:false

If true, automatically commit the results when the evaluation completes

batch_size
integer
default:10

Number of rows to process per inference batch

commit_message
string | null

Commit message used when auto_commit is true

is_sample
boolean
default:false

If true, only evaluate a subset of rows. If false, evaluate all rows.

name
string

Human-readable name for the evaluation

sample_count
integer
default:10

Number of rows to sample when is_sample is true

target_branch
string

Branch where evaluation results are committed

target_path
string

File path for the output data frame

Response

Evaluation created

Standard response wrapper for a single evaluation.

evaluation
Evaluation · object

Evaluation resource

status
string

High-level status string (for example, 'success').

status_message
string

Human-readable status message (for example, 'resource_found').