Skip to main content
POST
/
ai
/
prediction
/
standalone-query-rewriter
/
{MODEL_ID}
Standalone query rewriter
import requests

url = "https://application_id.applications.lucidworks.com/ai/prediction/standalone-query-rewriter/{MODEL_ID}"

payload = {
    "batch": [{ "text": "Is it a framework?" }],
    "useCaseConfig": { "memoryUuid": "27a887fe-3d7c-4ef0-9597-e2dfc054c20e" },
    "modelConfig": {
        "temperature": 0.8,
        "topP": 1,
        "topK": -1,
        "presencePenalty": 2,
        "frequencyPenalty": 1,
        "maxTokens": 1,
        "apiKey": "API key specific to use case and model",
        "azureDeployment": "DEPLOYMENT_NAME",
        "azureEndpoint": "https://azure.endpoint.com",
        "googleProjectId": "[GOOGLE_PROJECT_ID]",
        "googleRegion": "[GOOGLE_PROJECT_REGION_OF_MODEL_ACCESS]"
    }
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
{
  "predictions": [
    {
      "response": "Is RAG a framework?",
      "tokensUsed": {
        "promptTokens": 148,
        "completionTokens": 27,
        "totalTokens": 175
      }
    }
  ]
}

Headers

Authorization: Bearer ACCESS_TOKEN
string

The authentication and authorization access token.

Content-Type
string

application/json

Example:

"application/json"

Path Parameters

MODEL_ID
string
required

Unique identifier for the model.

Example:

"6a092bd4-5098-466c-94aa-40bf6829430\""

Body

application/json
batch
object[]

The batch of key:value pairs used as inputs in the prediction. Up to 32 inputs per request are allowed.

Maximum length: 32
useCaseConfig
object
modelConfig
object

Provides fields and values that specify ranges for tokens. Fields used for specific use cases and models are specified. The default values are used if other values are not specified.

Response

200 - application/json

OK

predictions
object[]