Skip to main content
POST
/
ai
/
prediction
/
part-number-detection
/
{CUSTOM_DEPLOYMENT_ID}
Part Number Detection use case
import requests

url = "https://application_id.applications.lucidworks.com/ai/prediction/part-number-detection/{CUSTOM_DEPLOYMENT_ID}"

payload = { "batch": [{ "text": "54956gf-98796v" }, { "text": "bright pink sprinkles" }] }
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

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

print(response.text)
{
  "predictions": [
    {
      "tokensUsed": {
        "inputTokens": 6,
        "labelsTokens": 2
      },
      "labels": {
        "true": 0.6388378143310547
      },
      "response": "true: 0.64"
    },
    {
      "tokensUsed": {
        "inputTokens": 4,
        "labelsTokens": 2
      },
      "labels": {
        "false": 0.6262129545211792
      },
      "response": "false: 0.63"
    }
  ]
}

Headers

Authorization
string
required

Bearer token used for authentication with machinelearning.predict scope.

Path Parameters

CUSTOM_DEPLOYMENT_ID
string
required

Unique deployment ID for the model. This use case is only supported with a custom-trained embedding model trained with the Part Number Classification data schema option.

Body

application/json
batch
object[]
required

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

Maximum array length: 32
modelConfig
ModelConfigPartNumber · object

Provides fields and values specific to part number detection prediction.

Response

200 - application/json

OK

predictions
object[]