curl --request POST \
--url https://api.bespokelabs.ai/v1/systemone \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "nimble-latest",
"state": "The customer was charged twice and asks for a refund. The service still works.",
"questions": {
"refund": {
"type": "noul",
"instructions": "Does the customer request a refund?"
},
"department": {
"type": "choice",
"instructions": "Which department should handle this request?",
"criteria": {
"billing": "Charges, payments and refunds",
"technical": "Software bugs and outages"
}
},
"urgency": {
"type": "score",
"instructions": "How urgent is this request?",
"criteria": [
"Routine billing request; service works",
"Some functionality unavailable",
"Complete service outage"
]
}
}
}
'System One
Send a state and questions about it to any Nimble model. The model field picks the model. Fact check models take the document as a string state and one noul question for each claim. Code search models take a query and a list of items in the state. The path /v1/nimble/systemone takes the same requests.
curl --request POST \
--url https://api.bespokelabs.ai/v1/systemone \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "nimble-latest",
"state": "The customer was charged twice and asks for a refund. The service still works.",
"questions": {
"refund": {
"type": "noul",
"instructions": "Does the customer request a refund?"
},
"department": {
"type": "choice",
"instructions": "Which department should handle this request?",
"criteria": {
"billing": "Charges, payments and refunds",
"technical": "Software bugs and outages"
}
},
"urgency": {
"type": "score",
"instructions": "How urgent is this request?",
"criteria": [
"Routine billing request; service works",
"Some functionality unavailable",
"Complete service outage"
]
}
}
}
'Authorizations
Your Bespoke Labs API key.
Body
- General models
- Fact check
- Code search
The model field picks the model, and the model decides what the state and the questions must look like.
The text or JSON to ask about. Nimble reads a JSON state as JSON text.
Your question IDs mapped to questions. The answers use the same IDs.
Show child attributes
Show child attributes
nimble-latest is the newest general model, which is nimble-v3 now. nimble-v3 and bespokelabs/Bespoke-Nimble-9B-v3 stay on this model, and bespokelabs/Bespoke-Nimble-9B is the previous model. The response repeats this name.
nimble-latest, nimble-v3, bespokelabs/Bespoke-Nimble-9B-v3, bespokelabs/Bespoke-Nimble-9B Response
The answers, keyed by question ID.
The model name from the request.
Question IDs mapped to answers.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Fact check and code search only. The same ID as the x-request-id header.
Code search only. low for nimble-codegrep-lite, medium for nimble-codegrep, and high for nimble-codegrep-max.
low, medium, high Code search only. Question IDs mapped to details about how each item was scored.
Show child attributes
Show child attributes
Code search only. Always false in a 200 response.