Skip to main content
POST
/
ai
/
prompt
/
passthrough
/
{MODEL_ID}
Passthrough prompt
import requests

url = "https://application_id.applications.lucidworks.com/ai/prompt/passthrough/{MODEL_ID}"

payload = {
    "batch": [{ "text": "[{\"role\": \"system\", \"content\": \"You are a helpful utility program instructed to accomplish a product classififcation task. Please, classify the provided product name into one of the following categories:\nGROCERIES, FURNITURE, UNKNOWN\"}, {\"role\": \"user\", \"content\": \"chocolate milk\"}, {\"role\": \"assistant\", \"content\": \"GROCERIES\"}, {\"role\": \"user\", \"content\": \"chocolate table\"}, {\"role\": \"assistant\", \"content\": \"FURNITURE\"}, {\"role\": \"user\", \"content\": \"stone baked pizza\"}]" }],
    "useCaseConfig": { "dataType": "json_prompt" }
}
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

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

print(response.text)
{
  "predictions": [
    {
      "tokensUsed": {
        "promptTokens": 95
      },
      "prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful utility program instructed to accomplish a product classififcation task. Please, classify the provided product name into one of the following categories:\nGROCERIES, FURNITURE, UNKNOWN<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nchocolate milk<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nGROCERIES<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nchocolate table<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nFURNITURE<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nstone baked pizza<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
    }
  ]
}

Headers

​
Authorization
string
required

Bearer token used for authentication. Format: Authorization: Bearer ACCESS_TOKEN.

​
Content-Type
string

application/json

Example:

"application/json"

Path Parameters

​
MODEL_ID
string
required

The generative AI (GenAI) model name.

Example:

"llama-3-8b-instruct"

Body

application/json
​
batch
object[]

The content sent in the request.

​
useCaseConfig
UseCaseConfigPassthrough · object

NOTE: If both useSystemPrompt and dataType are present, the value in dataType is used.

​
modelConfig
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

​
tokensUsed
object
​
prompt
string

The Llama3 model response from the request, formatted for the model.

Example:

"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\\n\\nYou are a helpful utility program instructed to accomplish a product classififcation task. Please, classify the provided product name into one of the following categories:\\nGROCERIES, FURNITURE, UNKNOWN<|eot_id|><|start_header_id|>user<|end_header_id|>\\n\\nchocolate milk<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\nGROCERIES<|eot_id|><|start_header_id|>user<|end_header_id|>\\n\\nchocolate table<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\nFURNITURE<|eot_id|><|start_header_id|>user<|end_header_id|>\\n\\nstone baked pizza<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n"