Skip to main content
Evaluations help you iterate and improve your applications by testing them against a set of examples after you make changes. Weave provides first-class support for tracking evaluations with Model and Evaluation classes. The APIs are designed with minimal assumptions, allowing flexibility for a wide array of use cases. Evals hero The guide walks you through how to:
  • Set up a Model
  • Create a dataset to test an LLM’s responses against
  • Define a scoring function to compare model output to expected outputs
  • Run an evaluation that tests the model against dataset using the scoring function and an additional built-in scorer
  • View the results of the evaluation in the Weave UI
You can open this quickstart as an interactive notebook:

​
Prerequisites

Before starting this tutorial, ensure you have:
  • A W&B account
  • Python 3.8+ or Node.js 18+
  • Required packages installed:
    • Python: pip install weave openai
    • TypeScript: npm install weave openai
  • An OpenAI API key set as an environment variable

​
Import the necessary libraries and functions

Import the following libraries into your script:
  • Python
  • TypeScript
import json
import openai
import asyncio
import weave
from weave.scorers import MultiTaskBinaryClassificationF1

​
Build a Model

In Weave, Models are objects that capture both the behavior of your model/agent (logic, prompt, parameters) and its versioned metadata (parameters, code, micro-config) so you can track, compare, evaluate and iterate reliably. When you instantiate a Model, Weave automatically captures its configuration and behaviors and updates the version when there are changes. This allows you to track its performance over time as you iterate on it. Models are declared by subclassing Model and implementing a predict function definition, which takes one example and returns the response. The following example model uses OpenAI to extract the names, colors, and flavors of alien fruits from sentences sent to it.
  • Python
  • TypeScript
class ExtractFruitsModel(weave.Model):
    model_name: str
    prompt_template: str

    @weave.op()
    async def predict(self, sentence: str) -> dict:
        client = openai.AsyncClient()

        response = await client.chat.completions.create(
            model=self.model_name,
            messages=[
                {"role": "user", "content": self.prompt_template.format(sentence=sentence)}
            ],
        )
        result = response.choices[0].message.content
        if result is None:
            raise ValueError("No response from model")
        parsed = json.loads(result)
        return parsed
The ExtractFruitsModel class inherits from (or subclasses) weave.Model so that Weave can track the instantiated object. @weave.op decorates the predict function to track its inputs and outputs. You can instantiate Model objects like this:
  • Python
  • TypeScript
weave.init('eval_pipeline_quickstart')

model = ExtractFruitsModel(
    model_name='gpt-3.5-turbo-1106',
    prompt_template='Extract fields ("fruit": <str>, "color": <str>, "flavor": <str>) from the following text, as json: {sentence}'
)

sentence = "There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy."

print(asyncio.run(model.predict(sentence)))
# if you're in a Jupyter Notebook, run:
# await model.predict(sentence)

​
Create a dataset

Next, you need a dataset to evaluate your model on. A Dataset is a collection of examples stored as a Weave object. The following example dataset defines three example input sentences and their correct answers (labels), and then formats them in a JSON table table format that scoring functions can read. This example builds a list of examples in code, but you can also log them one at a time from your running application.
  • Python
  • TypeScript
sentences = ["There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy.",
"Pounits are a bright green color and are more savory than sweet.",
"Finally, there are fruits called glowls, which have a very sour and bitter taste which is acidic and caustic, and a pale orange tinge to them."]
labels = [
    {'fruit': 'neoskizzles', 'color': 'purple', 'flavor': 'candy'},
    {'fruit': 'pounits', 'color': 'bright green', 'flavor': 'savory'},
    {'fruit': 'glowls', 'color': 'pale orange', 'flavor': 'sour and bitter'}
]
examples = [
    {'id': '0', 'sentence': sentences[0], 'target': labels[0]},
    {'id': '1', 'sentence': sentences[1], 'target': labels[1]},
    {'id': '2', 'sentence': sentences[2], 'target': labels[2]}
]
Then create your dataset using the weave.Dataset() class and publish it:
  • Python
  • TypeScript
weave.init('eval_pipeline_quickstart')
dataset = weave.Dataset(name='fruits', rows=examples)
weave.publish(dataset)

​
Define custom scoring functions

When using Weave evaluations, Weave expects a target to compare output against. The following scoring function takes two dictionaries (target and output) and returns a dictionary of boolean values indicating whether the output matches the target. The @weave.op() decorator enables Weave to track the scoring function’s execution.
  • Python
  • TypeScript
@weave.op()
def fruit_name_score(target: dict, output: dict) -> dict:
    return {'correct': target['fruit'] == output['fruit']}
To make your own scoring function, learn more in the Scorers guide. In some applications, you may want to create custom Scorer classes. For example, you might create a standardized LLMJudge class with specific parameters (such as chat model or prompt), specific row scoring, and aggregate score calculation. See the tutorial on defining a Scorer class in the next chapter on Model-Based Evaluation of RAG applications for more information.

​
Use a built-in scorer and run the evaluation

Along with custom scoring functions, you can also use Weave’s built-in scorers. In the following evaluation, weave.Evaluation() uses the fruit_name_score function defined in the previous section and the built-in MultiTaskBinaryClassificationF1 scorer, which computes F1 scores. The following example runs an evaluation of ExtractFruitsModel on the fruits dataset using the scoring the two functions and logs the results to Weave.
  • Python
  • TypeScript
weave.init('eval_pipeline_quickstart')

evaluation = weave.Evaluation(
    name='fruit_eval',
    dataset=dataset, 
    scorers=[
        MultiTaskBinaryClassificationF1(class_names=["fruit", "color", "flavor"]), 
        fruit_name_score
    ],
)
print(asyncio.run(evaluation.evaluate(model)))
# if you're in a Jupyter Notebook, run:
# await evaluation.evaluate(model)
If you’re running from a python script, you’ll need to use asyncio.run. However, if you’re running from a Jupyter notebook, you can use await directly.

​
Complete Example

  • Python
  • TypeScript
import json
import asyncio
import openai
import weave
from weave.scorers import MultiTaskBinaryClassificationF1

# Initialize Weave once
weave.init('eval_pipeline_quickstart')

# 1. Define Model
class ExtractFruitsModel(weave.Model):
    model_name: str
    prompt_template: str

    @weave.op()
    async def predict(self, sentence: str) -> dict:
        client = openai.AsyncClient()
        response = await client.chat.completions.create(
            model=self.model_name,
            messages=[{"role": "user", "content": self.prompt_template.format(sentence=sentence)}],
        )
        result = response.choices[0].message.content
        if result is None:
            raise ValueError("No response from model")
        return json.loads(result)

# 2. Instantiate model
model = ExtractFruitsModel(
    model_name='gpt-3.5-turbo-1106',
    prompt_template='Extract fields ("fruit": <str>, "color": <str>, "flavor": <str>) from the following text, as json: {sentence}'
)

# 3. Create dataset
sentences = ["There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy.",
"Pounits are a bright green color and are more savory than sweet.",
"Finally, there are fruits called glowls, which have a very sour and bitter taste which is acidic and caustic, and a pale orange tinge to them."]
labels = [
    {'fruit': 'neoskizzles', 'color': 'purple', 'flavor': 'candy'},
    {'fruit': 'pounits', 'color': 'bright green', 'flavor': 'savory'},
    {'fruit': 'glowls', 'color': 'pale orange', 'flavor': 'sour and bitter'}
]
examples = [
    {'id': '0', 'sentence': sentences[0], 'target': labels[0]},
    {'id': '1', 'sentence': sentences[1], 'target': labels[1]},
    {'id': '2', 'sentence': sentences[2], 'target': labels[2]}
]

dataset = weave.Dataset(name='fruits', rows=examples)
weave.publish(dataset)

# 4. Define scoring function
@weave.op()
def fruit_name_score(target: dict, output: dict) -> dict:
    return {'correct': target['fruit'] == output['fruit']}

# 5. Run evaluation
evaluation = weave.Evaluation(
    name='fruit_eval',
    dataset=dataset,
    scorers=[
        MultiTaskBinaryClassificationF1(class_names=["fruit", "color", "flavor"]),
        fruit_name_score
    ],
)
print(asyncio.run(evaluation.evaluate(model)))

​
View your evaluation results

Weave automatically captures traces of each prediction and score. Click on the link printed by the evaluation to view the results in the Weave UI. Evaluation results

​
Learn more about Weave evaluations

​
Next Steps

Build a RAG application to learn about evaluating retrieval-augmented generation.