Skip to main content
POST
/
api
/
v1
/
llm
/
classify
Typescript (SDK)
import { SDK } from "@meetkai/mka1";

const sdk = new SDK({
  bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await sdk.llm.classify.classify({
    classificationRequest: {
      model: "meetkai:functionary-urdu-mini-pak",
      text: "I absolutely love this product! Best purchase ever.",
      labels: [
        "positive",
        "negative",
        "neutral",
      ],
    },
  });

  console.log(result);
}

run();
{
  "success": true,
  "data": {
    "label": "positive",
    "confidence": 0.92,
    "reasoning": "The text expresses strong enthusiasm with phrases like 'absolutely love' and 'best purchase ever'."
  },
  "metadata": {
    "model": "meetkai:functionary-urdu-mini-pak",
    "labels": [
      "positive",
      "negative",
      "neutral"
    ],
    "classifiedAt": "2024-01-15T10:30:00Z"
  }
}

Authorizations

​
Authorization
string
header
required

Authenticate with your MKA1 API key at the API gateway: Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, also send X-On-Behalf-Of to identify the end user making the request.

Headers

​
X-On-Behalf-Of
string

Optional external user identifier for multi-user server-side integrations. Use this when acting on behalf of one of your end users.

Body

application/json

Request parameters for text classification. The model will analyze the text and assign it to one of the provided labels.

​
model
string
required

ID of the model to use for classification. You can use provider:model format or just the model name with a default provider.

Minimum string length: 1
​
text
string
required

The text content to classify. Must not be empty.

Minimum string length: 1
​
labels
string[]
required

Array of possible classification labels. Must contain at least 2 labels. The model will choose one of these labels to assign to the text.

Minimum array length: 2
Minimum string length: 1
​
prompt
string

Optional custom system prompt to guide the classification. Use this to provide additional context or instructions to the model about how to perform the classification.

Response

200 - application/json

OK

Response from the text classification endpoint containing the classification result, confidence, and metadata.

​
success
boolean
required

Indicates whether the classification request was successful

​
data
object
required

The classification result data

​
metadata
object
required

Metadata about the classification request and execution