Skip to main content

Documentation Index

Fetch the complete documentation index at: https://narev.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

​
File upload

Upload your test data directly as files. Ideal for analyzing historical data or running experiments with pre-collected datasets. Key Feature: Test with existing data
Supported Formats: CSV, JSON, and JSONL

​
Field Requirements

Regardless of your file format, your file must contain the following fields:
  • messages (required): An array of message objects, each with:
    • role: the role of the message sender (for example, user, assistant, or system)
    • content: the message content
  • expected_output (optional): the expected response for evaluation purposes

​
Format examples

messages,expected_output
"[{""role"":""user"",""content"":""What is the capital of France?""}]","Paris"
"[{""role"":""user"",""content"":""Explain quantum computing""}]","Quantum computing uses quantum mechanics..."

[
  {
    "messages": [{ "role": "user", "content": "What is the capital of France?" }],
    "expected_output": "Paris"
  },
  {
    "messages": [{ "role": "user", "content": "Explain quantum computing" }],
    "expected_output": "Quantum computing uses quantum mechanics..."
  }
]

{"messages": [{"role": "user", "content": "What is the capital of France?"}], "expected_output": "Paris"}
{"messages": [{"role": "user", "content": "Explain quantum computing"}], "expected_output": "Quantum computing uses quantum mechanics..."}
The expected_output field is optional. If provided, it enables quality metrics and evaluation features for your A/B tests.