Upload Benchmark File

curl --request POST \
  --url https://api.nugen.in/api/v3/benchmark/upload \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'name=<string>' \
  --form 'document_id=<string>' \
  --form 'description=<string>'

{
  "benchmark_id": "benchmark-abc123",
  "benchmark_name": "My Benchmark",
  "status": "PROCESSING",
  "num_questions": 10,
  "questions": [
    {
      "question_num": 123,
      "question": "<string>",
      "answer": "<string>"
    }
  ]
}

Benchmark

Upload Benchmark File

Upload a pre-prepared benchmark file with questions and answers.

This endpoint allows you to upload a JSON file containing benchmark questions and answers, associating it with a specific document for evaluation purposes.

Request Body (multipart/form-data):

file: JSON file containing benchmark questions and answers (required)
name: Display name for the benchmark (required)
document_id: Document ID that this benchmark is based on (required)
description (optional): Description of the benchmark

File Format:

The uploaded JSON file should contain an array of question objects. Each question should have:

[
  {
    "question_num": 1,
    "question": "What is...",
    "answer": "The answer is..."
  }
]

Returns:

id: Unique identifier for the uploaded benchmark
name: Name of the benchmark
status: Upload status (PROCESSING, READY, FAILED)
questions: List of benchmark question objects, each containing:
- question_num: Question number
- question: Question text
- answer: Expected answer text
num_questions: Total number of questions in the benchmark

Raises:

400: If file format is invalid, JSON structure is incorrect, or document_id is not found
413: If file size exceeds limit

Example Request:

POST /api/v3/benchmark/upload
Headers: {"Authorization": "Bearer <api_key>"}
Content-Type: multipart/form-data

Form Data:
  file: benchmark_questions.json
  name: "Customer Support Q&A"
  document_id: "doc-abc123"
  description: "Benchmark for customer support documentation"

Example Response:

{
  "id": "benchmark-xyz789",
  "name": "Customer Support Q&A",
  "status": "READY",
  "questions": [
    {
      "question_num": 1,
      "question": "How do I reset my password?",
      "answer": "You can reset your password by clicking the 'Forgot Password' link on the login page."
    },
    {
      "question_num": 2,
      "question": "What are the system requirements?",
      "answer": "The system requires a modern web browser with JavaScript enabled."
    }
  ],
  "num_questions": 2
}

Notes:

File must be in valid JSON format with proper question structure
Each question must include question_num, question, and answer fields
The benchmark is immediately available for use in evaluations after upload
The document_id provided in the request is stored internally and will appear as a single-element documents array (e.g., ["doc-abc123"]) when retrieving the benchmark via /benchmark/list or /benchmark/{id}/data endpoints

POST

api

benchmark

upload

Upload Benchmark File

curl --request POST \
  --url https://api.nugen.in/api/v3/benchmark/upload \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'name=<string>' \
  --form 'document_id=<string>' \
  --form 'description=<string>'

{
  "benchmark_id": "benchmark-abc123",
  "benchmark_name": "My Benchmark",
  "status": "PROCESSING",
  "num_questions": 10,
  "questions": [
    {
      "question_num": 123,
      "question": "<string>",
      "answer": "<string>"
    }
  ]
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data

file

required

JSON file containing benchmark questions

name

string

required

Benchmark name

document_id

string

required

Document ID that this benchmark is based on

description

string | null

Benchmark description

Response

Returns the details of the uploaded benchmark including its unique identifier, name, status, and the list of questions with expected answers

benchmark_id

string

required

Unique identifier for the benchmark

Example:

"benchmark-abc123"

benchmark_name

string

required

Name of the benchmark

Example:

"My Benchmark"

status

enum<string>

required

Status of the benchmark

Available options:

PROCESSING,

READY,

FAILED,

DEPLOYING,

EVALUATING,

UNDEPLOYED,

EVALUATED,

STOPPED

Example:

"PROCESSING"

num_questions

integer

required

Number of questions in the benchmark

Example:

10

questions

BenchmarkQuestion · object[]

List of uploaded benchmark questions

Show child attributes

Create Benchmark Task Get Benchmark Status