Custom evaluation metrics in LangChain - Mini Project: Build & Apply

Custom Evaluation Metrics with Langchain

📖 Scenario: You are building a language model evaluation tool using Langchain. You want to create a custom metric to measure how well the model's answers match expected answers.

🎯 Goal: Build a simple custom evaluation metric function and integrate it with Langchain's evaluation framework.

📋 What You'll Learn

Create a list of model answers and expected answers

Define a threshold for exact match score

Write a function to calculate exact match accuracy

Use the function as a custom metric in Langchain evaluation

💡 Why This Matters

🌍 Real World

Custom evaluation metrics help you measure how well AI models perform on your specific tasks, beyond generic scores.

💼 Career

Knowing how to create and use custom metrics is valuable for AI engineers and data scientists working on model evaluation and improvement.

1

Data Setup: Create model and expected answers

Create a list called model_answers with these exact strings: 'Paris', 'Berlin', 'Tokyo'. Also create a list called expected_answers with these exact strings: 'Paris', 'Berlin', 'Kyoto'.

LangChain

# Your code here

Hint

Use Python lists with exact string values as shown.

2

Configuration: Define exact match threshold

Create a variable called exact_match_threshold and set it to 1.0 to represent a perfect match score.

LangChain

model_answers = ['Paris', 'Berlin', 'Tokyo']
expected_answers = ['Paris', 'Berlin', 'Kyoto']
# Your code here

Hint

Use a float value 1.0 to represent exact match threshold.

3

Core Logic: Write exact match accuracy function

Define a function called exact_match_accuracy that takes two lists: predictions and references. It should return the fraction of items where prediction equals reference exactly.

LangChain

model_answers = ['Paris', 'Berlin', 'Tokyo']
expected_answers = ['Paris', 'Berlin', 'Kyoto']
exact_match_threshold = 1.0
# Define exact_match_accuracy function here

Hint

Use zip to pair predictions and references, then count exact matches.

4

Completion: Use the custom metric in Langchain evaluation

Import EvaluationChain from langchain.evaluation. Create an eval_chain instance using EvaluationChain.from_llm with a dummy llm=None and pass exact_match_accuracy as the metric argument.

LangChain

model_answers = ['Paris', 'Berlin', 'Tokyo']
expected_answers = ['Paris', 'Berlin', 'Kyoto']
exact_match_threshold = 1.0

def exact_match_accuracy(predictions, references):
    matches = sum(p == r for p, r in zip(predictions, references))
    return matches / len(references)

# Import EvaluationChain and create eval_chain with exact_match_accuracy metric

Hint

Use from langchain.evaluation import EvaluationChain and pass your function as metric.

Practice

1. What is the main purpose of creating a custom evaluation metric in Langchain?

easy

A. To speed up the AI model training process

B. To measure AI results in a way that fits your specific needs

C. To automatically fix errors in AI outputs

D. To replace the AI model with a simpler one

Solution

1. Step 1: Understand the role of evaluation metrics

   Evaluation metrics measure how well an AI model performs its task.

2. Step 2: Identify why custom metrics are used

   Custom metrics let you measure results in ways that standard metrics might not cover, fitting your unique needs.

3. Final Answer:

   To measure AI results in a way that fits your specific needs -> Option B

4. Quick Check:

   Custom metrics = tailored measurement [OK]

Hint: Custom metrics tailor scoring to your AI task [OK]

Common Mistakes:

• Thinking custom metrics speed training
• Believing they fix AI errors automatically
• Confusing metrics with model replacement

2. Which of the following is the correct way to start defining a custom evaluation metric class in Langchain?

easy

A. class MyMetric(Evaluation):

B. def MyMetric():

C. class MyMetric():

D. function MyMetric extends Evaluation {}

Solution

1. Step 1: Recall Langchain class inheritance syntax

   Custom metrics inherit from the Evaluation base class using Python class syntax.

2. Step 2: Identify correct class definition

   class MyMetric(Evaluation): correctly defines a class inheriting from Evaluation, matching Langchain patterns.

3. Final Answer:

   class MyMetric(Evaluation): -> Option A

4. Quick Check:

   Class inherits Evaluation = correct syntax [OK]

Hint: Use class inheritance with Evaluation base [OK]

Common Mistakes:

• Defining a function instead of a class
• Missing inheritance from Evaluation
• Using JavaScript syntax in Python

3. Given this custom metric class, what will metric.evaluate(['hello'], ['hello']) return?

class ExactMatch(Evaluation):
    def evaluate(self, predictions, references):
        return sum(p == r for p, r in zip(predictions, references)) / len(references)

medium

A. 1.0

B. 0.0

C. Error due to missing method

D. None

Solution

1. Step 1: Understand the evaluate method logic

   It compares each prediction to the reference and counts matches, then divides by total references.

2. Step 2: Apply inputs to the method

   With predictions=['hello'] and references=['hello'], the single pair matches, so sum is 1 and length is 1, result is 1/1 = 1.0.

3. Final Answer:

   1.0 -> Option A

4. Quick Check:

   Exact match count / total = 1.0 [OK]

Hint: Check if predictions equal references, then divide [OK]

Common Mistakes:

• Forgetting to divide by length
• Confusing sum with boolean values
• Expecting method to return a list

4. What is wrong with this custom metric class that causes an error?

class LengthDiff(Evaluation):
    def evaluate(self, predictions, references):
        return abs(len(predictions) - len(references)) / len(references)

medium

A. It returns a number instead of a score between 0 and 1

B. It does not implement the evaluate method

C. It uses abs() incorrectly causing a syntax error

D. It does not handle empty lists causing runtime error

Solution

1. Step 1: Analyze the evaluate method with empty references

   If references=[], len(references)=0 causes ZeroDivisionError in the division.

2. Step 2: Identify the runtime error cause

   The code divides by len(references) without checking if references is empty, causing runtime error.

3. Final Answer:

   It does not handle empty lists causing runtime error -> Option D

4. Quick Check:

   len(references)==0 -> ZeroDivisionError [OK]

Hint: Check how method handles empty input lists [OK]

Common Mistakes:

• Assuming abs() causes syntax error
• Thinking evaluate method is missing
• Ignoring empty list edge cases

5. You want to create a custom metric that scores AI answers higher if they contain more keywords from a reference list. Which approach fits best?

hard

A. Calculate the difference in length between prediction and reference

B. Check if prediction exactly matches the reference string

C. Count how many keywords appear in the prediction, divide by total keywords

D. Return a fixed score regardless of prediction content

Solution

1. Step 1: Understand the goal of keyword-based scoring

   The metric should reward predictions containing more keywords from the reference list.

2. Step 2: Identify the approach that measures keyword presence proportionally

   Counting keywords in prediction and dividing by total keywords gives a score reflecting keyword coverage.

3. Final Answer:

   Count how many keywords appear in the prediction, divide by total keywords -> Option C

4. Quick Check:

   Keyword coverage scoring = Count how many keywords appear in the prediction, divide by total keywords [OK]

Hint: Score by keyword matches divided by total keywords [OK]

Common Mistakes:

• Using exact match instead of keyword count
• Measuring length difference unrelated to keywords
• Returning fixed scores ignoring content