Python
for row in client.batches.results("batch_3k9x2m"):
if row.answers["safety"].probs["yes"] > 0.9:
flag_for_review(row.custom_id)
for await (const row of client.batches.results("batch_3k9x2m")) {
if (row.answers.safety.probs.yes > 0.9) flagForReview(row.custom_id);
}
curl https://api.tacetai.com/v1/batches/batch_3k9x2m/results \
-H "Authorization: Bearer $TACET_API_KEY" \
-o results.jsonl
"{\"custom_id\": \"ticket-88213\", \"answers\": {\"safety\": {\"type\": \"noul\", \"probs\": {\"no\": 0.04, \"yes\": 0.96}, \"top\": \"yes\", \"confidence\": 0.96}}}\n"{
"code": "invalid_question",
"message": "<string>"
}{
"code": "invalid_question",
"message": "<string>"
}Batches
Get batch results
Download results as JSONL, one line per record, once the job has finished.
GET
/
v1
/
batches
/
{id}
/
results
Python
for row in client.batches.results("batch_3k9x2m"):
if row.answers["safety"].probs["yes"] > 0.9:
flag_for_review(row.custom_id)
for await (const row of client.batches.results("batch_3k9x2m")) {
if (row.answers.safety.probs.yes > 0.9) flagForReview(row.custom_id);
}
curl https://api.tacetai.com/v1/batches/batch_3k9x2m/results \
-H "Authorization: Bearer $TACET_API_KEY" \
-o results.jsonl
"{\"custom_id\": \"ticket-88213\", \"answers\": {\"safety\": {\"type\": \"noul\", \"probs\": {\"no\": 0.04, \"yes\": 0.96}, \"top\": \"yes\", \"confidence\": 0.96}}}\n"{
"code": "invalid_question",
"message": "<string>"
}{
"code": "invalid_question",
"message": "<string>"
}Authorizations
Create a key in the Tacet console. Keep it on your server; never ship it in a browser or app.
Path Parameters
The batch id returned when the job was created.
Example:
"batch_3k9x2m"