Stop Run
const url = 'https://example.com/v1/runs/example/stop';const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request POST \ --url https://example.com/v1/runs/example/stop \ --header 'Authorization: Bearer <token>'Stop after the calls in flight. The chunk in progress is redone on resume, for free.
Authorizations
Section titled “Authorizations”Parameters
Section titled “Parameters”Path Parameters
Section titled “Path Parameters”Responses
Section titled “Responses”Successful Response
object
The dataset it makes.
The query and tasks it was started with.
object
Which rows to ask about: a SELECT over data returning __row_id; all rows by default.
object
The prompt, e.g. “Is this review negative? {{review}}”.
Base name of the result columns. Defaults to one for the type.
Extraction editor: one scalar value or named, typed fields.
The choices for pick one and pick any; the levels, lowest first, for scale.
object
For extract: what to pull out. "amount:number" is short for {"name": "amount", "type": "number"}.
object
What to put in it, if the name doesn’t say.
Also write why, from LLMs, for classify and extract.
Decision models or LLMs; see GET /v1/utils/models. Defaults to one for the type.
The answer columns, each with a _proba column.
Per task and model, so far.
object
USD spent by this run; cached answers are free.
Rows without an answer.
Rows it asks about: the rows in its scope.
The first chunk of rows not yet written.
Model calls answered (or failed) so far.
Model calls the run makes.
USD spent so far; cached answers are free.
Example
{ "status": "queued", "config": { "sql": "SELECT * FROM data", "tasks": [ { "template": "", "type": "yes_no", "preset": "summarize", "column": "answer", "extraction_mode": "single", "options": [], "fields": [], "reason": false, "models": [ "typesafe/jev-1.14" ] } ] }}Validation Error
object
object
object
Example generated
{ "detail": [ { "loc": [ "example" ], "msg": "example", "type": "example", "input": "example", "ctx": {} } ]}