Get started with Laminar evaluations

This guide will walk you through running your first evaluation using Laminar’s evaluation system.

Laminar provides a structured approach to create, run, and track your AI system’s performance through these key components:

Executors - Functions that process inputs and produce outputs, such as prompt templates, LLM calls, or production logic
Evaluators - Functions that assess outputs against targets or quality criteria, producing numeric scores
Datasets - Collections of datapoints (test cases) with 3 key elements:
- data - Required JSON input sent to the executor
- target - Optional reference data sent to the evaluator, typically containing expected outputs
- metadata - Optional metadata. This can be used to filter evaluation results in the UI after the evaluation is run.
Visualization - Tools to track performance trends and detect regressions over time
Tracing - Automatic recording of execution flow and model invocations

Example datapoint:

{
  "data": {
    "question": "What is the capital of France? Respond in one word.",
  },
  "target": {
    "answer": "Paris"
  },
  "metadata": {
    "category": "geography"
  }
}

Evaluation Groups group related evaluations to assess one feature or component, with results aggregated for comparison.

Evaluation Lifecycle

For each datapoint in a dataset:

The executor receives the data as input
The executor runs and its output is stored
Both the executor output and target are passed to the evaluator
The evaluator produces either a numeric score or a JSON object with multiple numeric scores
Results are stored and can be visualized to track performance over time

This approach helps you continuously measure your AI system’s performance as you make changes, showing the impact of model updates, prompt revisions, and code changes.

Evaluation function types

Each executor takes in the data as it is defined in the datapoints. Evaluator accepts the output of the executor as its first argument, and target as it’s defined in the datapoints as the second argument.

This means that the type of the data fields in your datapoints must match the type of the first parameter of the executor function. Similarly, the type of the target fields in your datapoints must match the type of the second parameter of the evaluator function(s).

Python is a bit more permissive. If you see type errors in TypeScript, make sure the data types and the parameter types match.

For a more precise description, here’s the partial TypeScript type signature of the evaluate function:

evaluate<D, T, O>(
  data: {
    data: D,
    target?: T,
  },
  executor: (data: D, ...args: any[]) => O | Promise<O>;
  evaluators: {
    [key: string]: (output: O, target?: T, ...args: any[]) => 
      number | { [key: string]: number }
  },
  // ... other parameters
)

Create your first evaluation

Prerequisites

To get the project API key, go to the Laminar dashboard, click the project settings, and generate a project API key. This is available both in the cloud and in the self-hosted version of Laminar.

Specify the key at Laminar initialization. If not specified, Laminar will look for the key in the LMNR_PROJECT_API_KEY environment variable.

Create an evaluation file

Create a file named my-first-evaluation.ts and add the following code:

my-first-evaluation.ts
import { evaluate } from '@lmnr-ai/lmnr';
import { OpenAI } from 'openai';  

const client = new OpenAI();

const writePoem = async (data: {country: string}) => {
  // replace this with your LLM call or custom logic
  const response = await client.chat.completions.create({
    model: 'gpt-4.1-nano',
    messages: [
      {
        role: 'user',
        content: `Generate a poem about ${data['country']}. ` +
          'Answer only with the poem, no other text.'
      }
    ]
  });
  return response.choices[0].message.content || '';
}

const accuracy = (output: string, target: string | undefined): number => {
  if (!target) return 0;
  return output.includes(target) ? 1 : 0;
}

evaluate({
  data: [
    {
      data: { country: 'France' },
      target: 'Paris',
    },
    {
      data: { country: 'Germany' },
      target: 'Berlin',
    },
  ],
  executor: writePoem,
  evaluators: { 'accuracy': accuracy },
  config: { 
    instrumentModules: {
      openAI: OpenAI
    }
  }
})

It is important to pass the config object with instrumentModules to evaluate to ensure that the OpenAI client and any other instrumented modules are instrumented.

Create a file named my-first-evaluation.ts and add the following code:

my-first-evaluation.ts
import { evaluate } from '@lmnr-ai/lmnr';
import { OpenAI } from 'openai';  

const client = new OpenAI();

const writePoem = async (data: {country: string}) => {
  // replace this with your LLM call or custom logic
  const response = await client.chat.completions.create({
    model: 'gpt-4.1-nano',
    messages: [
      {
        role: 'user',
        content: `Generate a poem about ${data['country']}. ` +
          'Answer only with the poem, no other text.'
      }
    ]
  });
  return response.choices[0].message.content || '';
}

const accuracy = (output: string, target: string | undefined): number => {
  if (!target) return 0;
  return output.includes(target) ? 1 : 0;
}

evaluate({
  data: [
    {
      data: { country: 'France' },
      target: 'Paris',
    },
    {
      data: { country: 'Germany' },
      target: 'Berlin',
    },
  ],
  executor: writePoem,
  evaluators: { 'accuracy': accuracy },
  config: { 
    instrumentModules: {
      openAI: OpenAI
    }
  }
})

It is important to pass the config object with instrumentModules to evaluate to ensure that the OpenAI client and any other instrumented modules are instrumented.

Create a file named my-first-evaluation.py and add the following code:

my-first-evaluation.py
from lmnr import evaluate
from openai import OpenAI

client = OpenAI()

def write_poem(data: dict) -> str:
    # replace this with your LLM call or custom logic
    return client.chat.completions.create(
        model="gpt-4.1-nano",
        messages=[
            {
                "role": "user",
                "content": f"Generate a poem about {data['country']}. " +
                    "Answer only with the poem, no other text."
            }
        ]
    ).choices[0].message.content

def accuracy(output: str, target: str) -> int:
    return 1 if target in output else 0

evaluate(
    data=[
        {
            "data": {"country": "France"},
            "target": "Paris"
        },
        {
            "data": {"country": "Germany"},
            "target": "Berlin"
        },
    ],
    executor=write_poem,
    evaluators={"accuracy": accuracy}
)

Run the evaluation

You can run evaluations in two ways: using the lmnr eval CLI or directly executing the evaluation file.

Using the CLI

The Laminar CLI automatically detects top-level evaluate function calls in your files - you don’t need to wrap them in a main function or any special structure.

export LMNR_PROJECT_API_KEY=<YOUR_PROJECT_API_KEY>
npx lmnr eval my-first-evaluation.ts

To run multiple evaluations, place them in an evals directory with the naming pattern *.eval.{ts,js}:

├─ src/
├─ evals/
│  ├── my-first-evaluation.eval.ts
│  ├── my-second-evaluation.eval.ts
│  ├── ...

Then run all evaluations with a single command:

npx lmnr eval

export LMNR_PROJECT_API_KEY=<YOUR_PROJECT_API_KEY>
npx lmnr eval my-first-evaluation.ts

To run multiple evaluations, place them in an evals directory with the naming pattern *.eval.{ts,js}:

├─ src/
├─ evals/
│  ├── my-first-evaluation.eval.ts
│  ├── my-second-evaluation.eval.ts
│  ├── ...

Then run all evaluations with a single command:

npx lmnr eval

# 1. Make sure `lmnr` is installed in a virtual environment
# lmnr --help
# 2. Run the evaluation
export LMNR_PROJECT_API_KEY=<YOUR_PROJECT_API_KEY>
lmnr eval my-first-evaluation.py

To run multiple evaluations, place them in an evals directory with the naming pattern eval_*.py or *_eval.py:

├─ src/
├─ evals/
│  ├── eval_first.py
│  ├── second_eval.py
│  ├── ...

Then run all evaluations with a single command:

lmnr eval

Running as a standalone script

You can also import and call evaluate directly from your application code:

ts-node my-first-evaluation.ts
# or
npx tsx my-first-evaluation.ts

The evaluate function is flexible and can be used both in standalone scripts processed by the CLI and integrated directly into your application code.

Evaluator functions must return either a single numeric score or a JSON object where each key is a score name and the value is a numeric score.

No need to initialize Laminar - evaluate automatically initializes Laminar behind the scenes. All instrumented function calls and model invocations are traced without any additional setup.

View evaluation results

When you run an evaluation from the CLI, Laminar will output the link to the dashboard where you can view the evaluation results.

Laminar stores every evaluation result. A run for every datapoint is represented as a trace. You can view the results and corresponding traces in the evaluations page.

Tracking evaluation progress

To track the score progression over time or compare evaluations side-by-side, you need to group them together. This can be achieved by passing the groupName parameter to the evaluate function.

import { evaluate, LaminarDataset } from '@lmnr-ai/lmnr';

evaluate({
    data: new LaminarDataset("name_of_your_dataset"),
    executor: yourExecutorFunction,
    evaluators: {evaluatorName: yourEvaluator},
    groupName: "evals_group_1",
});

import { evaluate, LaminarDataset } from '@lmnr-ai/lmnr';

evaluate({
    data: new LaminarDataset("name_of_your_dataset"),
    executor: yourExecutorFunction,
    evaluators: {evaluatorName: yourEvaluator},
    groupName: "evals_group_1",
});

from lmnr import evaluate, LaminarDataset
import os

evaluate(
    data=LaminarDataset("name_of_your_dataset"),
    executor=your_executor_function,
    evaluators={"evaluator_name": your_evaluator},
    project_api_key=os.environ["LMNR_PROJECT_API_KEY"],
    group_name="evals_group_1",
    # ... other optional parameters
)

Overview

Tracing

Evaluations

Tagging

Datasets

Get started with Laminar evaluations

Evaluation Lifecycle

Evaluation function types

Create your first evaluation

Prerequisites

Create an evaluation file

Run the evaluation

Using the CLI

Running as a standalone script

View evaluation results

Tracking evaluation progress

Overview

Tracing

Evaluations

Tagging

Datasets

​Evaluation Lifecycle

​Evaluation function types

​Create your first evaluation

​Prerequisites

​Create an evaluation file

​Run the evaluation

​Using the CLI

​Running as a standalone script

​View evaluation results

​Tracking evaluation progress

Evaluation Lifecycle

Evaluation function types

Create your first evaluation

Prerequisites

Create an evaluation file

Run the evaluation

Using the CLI

Running as a standalone script

View evaluation results

Tracking evaluation progress