Evaluations
SDK methods for the Evaluations module, accessed via soat.evaluations. See the Evaluations module docs for permissions and data model, and each method's REST page for the full request/response schema.
soat.evaluations.listDatasets()
List datasets
- Method:
GET - Path:
/api/v1/datasets
await soat.evaluations.listDatasets({
query: { /* + optional */ },
});
soat.evaluations.createDataset()
Create a dataset
- Method:
POST - Path:
/api/v1/datasets
await soat.evaluations.createDataset({
body: { name, /* + optional */ },
});
soat.evaluations.getDataset()
Get a dataset
- Method:
GET - Path:
/api/v1/datasets/{dataset_id}
await soat.evaluations.getDataset({
path: { dataset_id },
});
soat.evaluations.updateDataset()
Update a dataset
- Method:
PUT - Path:
/api/v1/datasets/{dataset_id}
await soat.evaluations.updateDataset({
path: { dataset_id },
body: { /* + optional */ },
});
soat.evaluations.deleteDataset()
Delete a dataset
- Method:
DELETE - Path:
/api/v1/datasets/{dataset_id}
await soat.evaluations.deleteDataset({
path: { dataset_id },
});
soat.evaluations.listDatasetItems()
List dataset items
- Method:
GET - Path:
/api/v1/datasets/{dataset_id}/items
await soat.evaluations.listDatasetItems({
path: { dataset_id },
query: { /* + optional */ },
});
soat.evaluations.createDatasetItem()
Add a dataset item
- Method:
POST - Path:
/api/v1/datasets/{dataset_id}/items
await soat.evaluations.createDatasetItem({
path: { dataset_id },
body: { input, /* + optional */ },
});
soat.evaluations.createDatasetItemFromGeneration()
Curate a dataset item from a generation
- Method:
POST - Path:
/api/v1/datasets/{dataset_id}/items/from-generation
await soat.evaluations.createDatasetItemFromGeneration({
path: { dataset_id },
body: { generation_id, /* + optional */ },
});
soat.evaluations.updateDatasetItem()
Update a dataset item
- Method:
PUT - Path:
/api/v1/datasets/{dataset_id}/items/{item_id}
await soat.evaluations.updateDatasetItem({
path: { dataset_id, item_id },
body: { /* + optional */ },
});
soat.evaluations.deleteDatasetItem()
Delete a dataset item
- Method:
DELETE - Path:
/api/v1/datasets/{dataset_id}/items/{item_id}
await soat.evaluations.deleteDatasetItem({
path: { dataset_id, item_id },
});
soat.evaluations.listEvals()
List evals
- Method:
GET - Path:
/api/v1/evals
await soat.evaluations.listEvals({
query: { /* + optional */ },
});
soat.evaluations.createEval()
Create an eval
- Method:
POST - Path:
/api/v1/evals
await soat.evaluations.createEval({
body: { name, agent_id, dataset_id, scorers, /* + optional */ },
});
soat.evaluations.getEval()
Get an eval
- Method:
GET - Path:
/api/v1/evals/{eval_id}
await soat.evaluations.getEval({
path: { eval_id },
});
soat.evaluations.updateEval()
Update an eval
- Method:
PUT - Path:
/api/v1/evals/{eval_id}
await soat.evaluations.updateEval({
path: { eval_id },
body: { /* + optional */ },
});
soat.evaluations.deleteEval()
Delete an eval
- Method:
DELETE - Path:
/api/v1/evals/{eval_id}
await soat.evaluations.deleteEval({
path: { eval_id },
});
soat.evaluations.listEvalRuns()
List eval runs
- Method:
GET - Path:
/api/v1/evals/{eval_id}/runs
await soat.evaluations.listEvalRuns({
path: { eval_id },
query: { /* + optional */ },
});
soat.evaluations.startEvalRun()
Start an eval run
- Method:
POST - Path:
/api/v1/evals/{eval_id}/runs
await soat.evaluations.startEvalRun({
path: { eval_id },
body: { /* + optional */ },
});
soat.evaluations.getEvalRun()
Get an eval run
- Method:
GET - Path:
/api/v1/evals/{eval_id}/runs/{eval_run_id}
await soat.evaluations.getEvalRun({
path: { eval_id, eval_run_id },
});
soat.evaluations.listEvalResults()
List eval run results
- Method:
GET - Path:
/api/v1/evals/{eval_id}/runs/{eval_run_id}/results
await soat.evaluations.listEvalResults({
path: { eval_id, eval_run_id },
query: { /* + optional */ },
});
soat.evaluations.cancelEvalRun()
Cancel an eval run
- Method:
POST - Path:
/api/v1/evals/{eval_id}/runs/{eval_run_id}/cancel
await soat.evaluations.cancelEvalRun({
path: { eval_id, eval_run_id },
});