Turn Contextual Relevancy

Q: When should I use TurnContextualRelevancyMetric instead of the single-turn version?

When retrieval happens turn-by-turn in a ConversationalTestCase and you want each turn's signal-to-noise measured in context. The single-turn ContextualRelevancyMetric inspects one retrieval against one query.

Q: Is this a retriever metric or a generator metric?

A retriever metric. It only measures how much of each turn's is relevant to the user's input and never reads the answer — a low score points to a noisy retriever, not a bad generator.

LLM-as-a-judge

Multi-turn

RAG

Chatbot

Multimodal

The turn contextual relevancy metric is a conversational metric that evaluates whether the retrieval context contains relevant information to address the user's input throughout a conversation.

Required Arguments

To use the TurnContextualRelevancyMetric, you'll have to provide the following arguments when creating a ConversationalTestCase:

turns

You must provide the role, content, and retrieval_context for evaluation to happen. Read the How Is It Calculated section below to learn more.

Usage

First, set the eval mode:

deepeval set-eval-mode llm         # LLM-as-a-judge (default)
deepeval set-eval-mode hybrid      # LLM extracts, Jev decides
deepeval set-eval-mode system_one  # Jev-as-a-judge, no LLM

The TurnContextualRelevancyMetric() can be used for end-to-end multi-turn evaluation:

from deepeval.test_case import Turn, ConversationalTestCase
from deepeval.metrics import TurnContextualRelevancyMetric
from deepeval import evaluate

content = "We offer a 30-day full refund at no extra cost."
retrieval_context = [
    "All customers are eligible for a 30 day full refund at no extra cost."
]

convo_test_case = ConversationalTestCase(
    turns=[
        Turn(role="user", content="What if these shoes don't fit?"),
        Turn(role="assistant", content=content, retrieval_context=retrieval_context)
    ],
    expected_outcome="The chatbot must explain the store policies like refunds, discounts, ..etc.",
)

metric = TurnContextualRelevancyMetric(threshold=0.5)

# To run metric as a standalone
# metric.measure(convo_test_case)
# print(metric.score, metric.reason)

evaluate(test_cases=[convo_test_case], metrics=[metric])

There are TEN optional parameters when creating a TurnContextualRelevancyMetric:

[Optional] threshold: a number representing the minimum passing threshold. Can also be set to None to run the metric in score-only mode. Defaulted to 0.5.
[Optional] model: a string specifying which of OpenAI's GPT models to use, OR any custom LLM model of type DeepEvalBaseLLM. Defaulted to gpt-5.4.
[Optional] include_reason: a boolean which when set to True, will include a reason for its evaluation score. Defaulted to True.
[Optional] strict_mode: a boolean which when set to True, enforces a binary metric score: 1 for perfection, 0 otherwise. It also overrides the current threshold and sets it to 1. Defaulted to False.
[Optional] async_mode: a boolean which when set to True, enables concurrent execution within the measure() method. Defaulted to True.
[Optional] verbose_mode: a boolean which when set to True, prints the intermediate steps used to calculate said metric to the console, as outlined in the How Is It Calculated section. Defaulted to False.
[Optional] window_size: an integer which defines the size of the sliding window of turns used during evaluation. Defaulted to 10.
[Optional] flaky: a boolean which when set to True, marks the metric as flaky. Defaulted to False.
[Optional] system_one_model: the Jev model to use, as a string or a DeepEvalBaseSystemOneModel. Only used under hybrid or system_one eval_mode. Defaulted to jev-latest.
[Optional] eval_mode: llm, hybrid or system_one, choosing whether an LLM, Jev, or both judge. Defaulted to the configured eval mode (llm unless set).

As a standalone

You can also run the TurnContextualRelevancyMetric on a single test case as a standalone, one-off execution.

...

metric.measure(convo_test_case)
print(metric.score, metric.reason)

How Is It Calculated?

You can change how the TurnContextualRelevancyMetric is calculated by setting the eval mode.

LLM-as-a-judge

The TurnContextualRelevancyMetric score is calculated according to the following equation:

\text{Turn Contextual Relevancy} = \frac{\sum \text{Turn Contextual Relevancy Scores}}{\text{Total Number of Assistant Turns}}

The TurnContextualRelevancyMetric first constructs a sliding windows of turns. For each window, it:

Extracts statements from each retrieval context node
Evaluates each statement to determine if it is relevant to the user's input
Calculates the interaction score as the ratio of relevant statements to total statements

\text{Contextual Relevancy} = \frac{\text{Number of Relevant Statements}}{\text{Total Number of Statements}}

The final score is the average of all relevancy scores across the conversation. This measures whether your retrieval system is returning contextually relevant information for each turn.

Hybrid

Under the hybrid eval mode, each node in an assistant turn's retrieval_context is split into sentences in code, and Jev, a System One model, answers one yes/no question per statement: is it relevant to the user's message? P(yes) >= 0.5 counts as relevant. The equation and the LLM-written reasons are unchanged. If a Jev call fails, the LLM makes that decision instead.

Jev-as-a-judge

Under the system_one eval mode, Jev judges the whole metric in one request. It is sent the whole conversation (with each assistant turn's retrieval_context) and asked three questions:

Question	Type	Weight
Every statement in the `retrieval_context` of each assistant turn in `turns` is relevant to addressing the user turns before it.	Noul	2
Every node in the `retrieval_context` of each assistant turn in `turns` contains at least one statement relevant to addressing the user turns before it.	Noul	1
Across `turns`, how much of the `retrieval_context` of the assistant turns is relevant to addressing the user turns before it? (None of it → All of it)	Score	1

Each answer becomes a value in $[0, 1]$ and the score is their weighted mean. No LLM is called: the reason lists each answer with its probability, and metric.confidence reports how decisive Jev was.

FAQs

When should I use TurnContextualRelevancyMetric instead of the single-turn version?

When retrieval happens turn-by-turn in a ConversationalTestCase and you want each turn's retrieval_context signal-to-noise measured in context. The single-turn ContextualRelevancyMetric inspects one retrieval against one query.

Is this a retriever metric or a generator metric?

A retriever metric. It only measures how much of each turn's retrieval_context is relevant to the user's input and never reads the answer — a low score points to a noisy retriever, not a bad generator.

How is relevancy different from Turn Contextual Recall and Precision?

Relevancy measures signal vs noise, recall measures completeness, and precision measures ranking.

My chatbot answered correctly but this score is low — is that a bug?

No. It grades the retrieved context, not the reply, so irrelevant nodes lower the score even when the answer is good. Tighten retrieval (fewer, more targeted chunks) to raise it.

On this page