Curious builder0 XP earned · 300 to level 2

0 daysFinish a lesson to begin

Badge collection0 of 6 unlocked

34 small wins to finish your pathNext lesson →

Contextual relevancy

ContextualRelevancyMetric is a DeepEval RAG metric that scores how much of the retrieved context is about the question: the judge splits each chunk into statements and counts the share that are relevant to the input.

Last updated: 05 Oct, 2026 · DeepEval 4.2.8

Contextual recall asks whether everything the answer needs came back. Contextual relevancy asks the opposite: how much of what came back is noise. It needs no expected answer, only the question and the chunks.

Retrieval relevance · from the Complete Agentic AI Course In 10 Hours · 10:24:18 to 10:25:25

Retrieved documents versus the input

The video reaches the fourth evaluator in its diagram, retrieval relevance: the retrieved documents compared with the input. It is another grader LLM with its own prompt: the grader gets a question and a set of facts, and its goal is to identify facts that are completely unrelated to the question.

The video writes this grader by hand and runs it in LangSmith; this page uses DeepEval's ContextualRelevancyMetric, which runs the same kind of check: the judge extracts the statements in each chunk of retrieval_context, marks each one relevant or not to input, and the score is relevant statements over all statements.

The ContextualRelevancyMetric API

python

from deepeval.metrics import ContextualRelevancyMetric

metric = ContextualRelevancyMetric(model=judge, threshold=0.5)
metric.measure(LLMTestCase(input=..., retrieval_context=[...]))  # no answer, no expected answer
metric.score          # relevant statements / all statements
metric.verdicts_list  # one entry per chunk, each with a yes or no per statement

The judge reads one chunk at a time, so verdicts_list has one entry per chunk, and each entry holds the statements found in that chunk with their verdicts.

A narrow question

The return-policy question needs one catalog entry. The search also returns the shipping and warranty policies, which share the word policy with it.

python

question = "What is TechNest's return policy?"

Three chunks, then one

python

for top_k in [3, 1]:
    contexts = retrieve(question, top_k=top_k)
    metric.measure(LLMTestCase(input=question, retrieval_context=contexts))

Counting the verdicts per chunk

python

for number, node in enumerate(metric.verdicts_list, 1):
    verdicts = [v.verdict for v in node.verdicts]
    print(f"chunk {number}: {verdicts.count('yes')} relevant, {verdicts.count('no')} not")

Project files used on this pageThis lesson builds on a project from earlier lessons. The code below imports these files. Click a file to see its code, or follow the link to the lesson that wrote it. To run the code yourself, keep them in the same folder.

written in Custom judge model
written in TechNest RAG app
written in TechNest RAG app

View the code here

judge.py

import os

from deepeval.models import DeepEvalBaseLLM
from openai import AsyncOpenAI, OpenAI

GROQ_URL = "https://api.groq.com/openai/v1"


class GroqJudge(DeepEvalBaseLLM):
    """A DeepEval judge model that runs on Groq."""

    def __init__(self, model="openai/gpt-oss-120b"):
        self.model_name = model
        key = os.environ["GROQ_API_KEY"]
        # on a 429 (rate limit) the client waits and tries again, up to 8 times
        self.client = OpenAI(api_key=key, base_url=GROQ_URL, max_retries=8)
        self.async_client = AsyncOpenAI(api_key=key, base_url=GROQ_URL, max_retries=8)

    def load_model(self):
        return self.client

    def get_model_name(self):
        return self.model_name

    def request(self, prompt, schema):
        request = {"model": self.model_name, "messages": [{"role": "user", "content": prompt}], "temperature": 0}
        if schema is not None:
            # ask Groq for JSON in the shape of the metric's Pydantic schema
            json_schema = {"name": schema.__name__, "schema": schema.model_json_schema()}
            request["response_format"] = {"type": "json_schema", "json_schema": json_schema}
        return request

    def generate(self, prompt, schema=None):
        reply = self.client.chat.completions.create(**self.request(prompt, schema))
        text = reply.choices[0].message.content
        return schema.model_validate_json(text) if schema else text

    async def a_generate(self, prompt, schema=None):
        reply = await self.async_client.chat.completions.create(**self.request(prompt, schema))
        text = reply.choices[0].message.content
        return schema.model_validate_json(text) if schema else text


judge = GroqJudge(os.environ.get("JUDGE_MODEL", "openai/gpt-oss-120b"))

technest.py

import json
import os
import re

from openai import OpenAI

groq = OpenAI(api_key=os.environ["GROQ_API_KEY"], base_url="https://api.groq.com/openai/v1")
CHAT_MODEL = "qwen/qwen3.8-27b"

SYSTEM_PROMPT = """You are a helpful customer support assistant for TechNest, an online electronics store.
Answer the customer's question using ONLY the information provided in the context below.
If the context does not contain enough information to answer fully, say so honestly.
Keep your answer concise, factual, and friendly. Do not invent any details not present in the context.
Reply in two or three plain sentences, with no lists or tables."""

with open("catalog.json", encoding="utf-8") as f:
    CATALOG = json.load(f)

SKIP = {"a", "an", "and", "are", "can", "do", "does", "for", "how", "i", "in", "is", "it",
        "long", "much", "my", "of", "on", "s", "technest", "the", "to", "what", "with", "you", "your"}


def words(text):
    """The words in a text that carry meaning, in lower case."""
    return {w for w in re.findall(r"[a-z0-9]+", text.lower()) if w not in SKIP}


def retrieve(question, top_k=3):
    asked = words(question)
    ranked = sorted(CATALOG, key=lambda item: len(asked & words(item["title"] + " " + item["content"])), reverse=True)
    return [item["content"] for item in ranked[:top_k]]


def generate(question, contexts):
    context_block = "\n\n".join(f"[{i+1}] {c}" for i, c in enumerate(contexts))
    messages = [
        {"role": "system", "content": SYSTEM_PROMPT},
        {"role": "user", "content": f"Context:\n{context_block}\n\nCustomer question: {question}"},
    ]
    response = groq.chat.completions.create(model=CHAT_MODEL, messages=messages, temperature=0)
    return response.choices[0].message.content.strip()


def answer(question, top_k=3):
    contexts = retrieve(question, top_k)
    return generate(question, contexts), contexts

catalog.json

[
  {
    "id": "prod_001",
    "category": "product",
    "title": "ProBook X1 Laptop",
    "content": "The TechNest ProBook X1 is a 14-inch laptop featuring an Intel Core i7-13th Gen processor, 16GB DDR5 RAM, and a 512GB NVMe SSD. It has a battery life of 12 hours, weighs 1.4kg, and comes with a backlit keyboard. Price: $1,299. Includes a 2-year manufacturer warranty."
  },
  {
    "id": "prod_002",
    "category": "product",
    "title": "PixelPhone 15",
    "content": "The TechNest PixelPhone 15 is a 6.7-inch AMOLED smartphone with a 50MP triple camera system, 8GB RAM, 256GB storage, and a 5,000mAh battery supporting 65W fast charging. Available in Midnight Black and Arctic White. Price: $899. Includes a 1-year warranty."
  },
  {
    "id": "prod_003",
    "category": "product",
    "title": "SoundPods Pro",
    "content": "The TechNest SoundPods Pro are true wireless earbuds with active noise cancellation (ANC), 8 hours of playback per charge plus 24 hours with the case, and IPX4 water resistance. They connect via Bluetooth 5.3 and support multipoint pairing with two devices simultaneously. Price: $149."
  },
  {
    "id": "prod_004",
    "category": "product",
    "title": "UltraTab S2 Tablet",
    "content": "The TechNest UltraTab S2 is a 11-inch tablet powered by a Snapdragon 870 processor with 8GB RAM and 128GB storage expandable via microSD. It features a 120Hz display, a 7,500mAh battery, and supports the TechNest Stylus Pen sold separately. Price: $549. Includes a 1-year warranty."
  },
  {
    "id": "prod_005",
    "category": "product",
    "title": "SmartWatch X",
    "content": "The TechNest SmartWatch X features continuous heart rate monitoring, SpO2 tracking, GPS, and 7-day battery life. It is water-resistant up to 50 metres. Compatible with both Android and iOS. Price: $299. Includes a 1-year warranty and a free extra silicone band."
  },
  {
    "id": "prod_006",
    "category": "product",
    "title": "ProCam 4K Action Camera",
    "content": "The TechNest ProCam 4K shoots 4K video at 60fps and 20MP photos. It is waterproof up to 10 metres without a case, has built-in image stabilisation (EIS), and includes a touch screen. Battery life is 90 minutes of 4K recording. Price: $229. Includes a 1-year warranty."
  },
  {
    "id": "prod_007",
    "category": "product",
    "title": "BassBuds Max Headphones",
    "content": "The TechNest BassBuds Max are over-ear wireless headphones with 40-hour battery life, hybrid active noise cancellation, and a premium 40mm driver for deep bass. They fold flat for travel and include a carrying case. Price: $199. Compatible with all Bluetooth devices."
  },
  {
    "id": "prod_008",
    "category": "product",
    "title": "SoundBar 360",
    "content": "The TechNest SoundBar 360 is a 2.1 soundbar with a 120W output, built-in subwoofer, Dolby Atmos support, and HDMI ARC connectivity. It also supports Bluetooth streaming and has an optical audio input. Dimensions: 90cm wide. Price: $349. Includes a 2-year warranty."
  },
  {
    "id": "policy_001",
    "category": "policy",
    "title": "Return Policy",
    "content": "TechNest accepts returns within 30 days of the original purchase date. Items must be in their original packaging with all accessories included. Customers are responsible for return shipping costs unless the item arrives defective or damaged. Refunds are processed within 5 to 7 business days of receiving the returned item. Digital downloads and opened software are non-refundable."
  },
  {
    "id": "policy_002",
    "category": "policy",
    "title": "Shipping Policy",
    "content": "TechNest offers free standard shipping on all orders over $50 within the continental US. Standard shipping takes 3 to 5 business days. Expedited shipping (1 to 2 business days) is available for $9.99. Same-day delivery is available in select cities for $19.99. Orders placed before 2pm local time are dispatched the same day."
  },
  {
    "id": "policy_003",
    "category": "policy",
    "title": "Warranty Policy",
    "content": "All TechNest products include a minimum 1-year manufacturer warranty covering defects in materials and workmanship. The ProBook X1 and SoundBar 360 include a 2-year warranty. Warranty does not cover physical damage, water damage (unless the product is rated waterproof), or damage from unauthorised modifications. To make a warranty claim, contact support@technest.com with your order number and a description of the issue."
  },
  {
    "id": "policy_004",
    "category": "policy",
    "title": "Payment Policy",
    "content": "TechNest accepts Visa, Mastercard, American Express, PayPal, and Apple Pay. All transactions are encrypted using 256-bit SSL. Buy Now Pay Later is available via Klarna for orders over $100, with 0% interest for 3 monthly instalments. TechNest does not store full card details — payments are processed securely by Stripe."
  },
  {
    "id": "faq_001",
    "category": "faq",
    "title": "Order Tracking",
    "content": "To track your order, visit technest.com/orders and enter your order number and email address. A shipping confirmation email with a tracking link is sent within 24 hours of dispatch. If you have not received your tracking email after 48 hours, check your spam folder or contact support@technest.com."
  },
  {
    "id": "faq_002",
    "category": "faq",
    "title": "International Shipping",
    "content": "TechNest ships to over 40 countries. International shipping rates start at $14.99 and delivery takes 7 to 14 business days. Import duties and taxes are the responsibility of the customer and are not included in the product price. Free shipping promotions apply to US orders only."
  },
  {
    "id": "faq_003",
    "category": "faq",
    "title": "Bulk and Business Orders",
    "content": "TechNest offers volume discounts for businesses purchasing 10 or more units of any single product. Discounts range from 10% for 10 to 49 units up to 25% for 100 or more units. Contact business@technest.com with your requirements for a custom quote. A dedicated account manager is assigned for orders over $10,000."
  }
]

Scoring the return-policy chunks at top_k=3 and top_k=1

ExampleAPI key

from deepeval.metrics import ContextualRelevancyMetric
from deepeval.test_case import LLMTestCase
from judge import judge
from technest import retrieve

question = "What is TechNest's return policy?"
metric = ContextualRelevancyMetric(model=judge)
for top_k in [3, 1]:
    contexts = retrieve(question, top_k=top_k)
    metric.measure(LLMTestCase(input=question, retrieval_context=contexts))
    print(f"top_k={top_k}  relevancy={metric.score:.2f}")
    for number, node in enumerate(metric.verdicts_list, 1):
        verdicts = [v.verdict for v in node.verdicts]
        print(f"   chunk {number}: {verdicts.count('yes')} relevant, {verdicts.count('no')} not  {contexts[number - 1][:35]}...")
print(metric.reason)

Output

top_k=3  relevancy=0.36
   chunk 1: 5 relevant, 0 not  TechNest accepts returns within 30 ...
   chunk 2: 0 relevant, 5 not  TechNest offers free standard shipp...
   chunk 3: 0 relevant, 4 not  All TechNest products include a min...
top_k=1  relevancy=1.00
   chunk 1: 5 relevant, 0 not  TechNest accepts returns within 30 ...
The score is 1.00 because the context directly answers the query, stating that "TechNest accepts returns within 30 days of the original purchase date," "Items must be in their original packaging with all accessories included," and "Refunds are processed within 5 to 7 business days of receiving the returned item," fully covering the return policy.

How the extra chunks lowered relevancy

top_k=3 scores 0.36. The judge found 5 statements in the return policy, all relevant, then 5 in the shipping policy and 4 in the warranty policy, none relevant. Five out of fourteen is 0.36.
top_k=1 scores 1.00. Only the return policy comes back, and all 5 of its statements are about returns.
The useful chunk is the same in both runs. The score moved only because of what came with it, which is what this metric measures: the signal-to-noise of the context the generator reads.