Uploading Dataset

To assess or improve your models, your dataset needs to follow a specific structure. We support two input formats: JSON and CSV, with optional fields for ground_truth and context.

​

✅ Supported Formats

​

1. JSON Format

Each entry should be a dictionary with the following keys:

• conv_prefix — A list of message objects (with role and content) representing the conversation history.
• response — A dictionary with the assistant’s reply.
• ground_truth (optional) — Integer rating (e.g., 1–5) for the response quality.
• context (optional) — A string providing additional context.

Here is a sample JSON

[
  {
    "conv_prefix": [{"role": "user", "content": "Hello"}],
    "response": {"role": "assistant", "content": "Hey there!"},
    "ground_truth": 4,
    "context": "Greeting conversation"
  },
  {
    "conv_prefix": [{"role": "user", "content": "Tell me a joke"}],
    "response": {"role": "assistant", "content": "Why did the chicken join a band? Because it had the drumsticks!"}
  }
]

​

2. CSV Format

Each row represents one example and should contain:

Download a sample CSV file here.

Note :

• conv_prefix should be a plain string version of the user message.

• The CSV format is flattened — it does not store role metadata. It assumes all conv_prefix entries are from the user role.