DeepEvaldeepeval 4.2.8 · Python 3.10+
Dashboard
0%
1
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 →

deepeval test run

deepeval test run is DeepEval's command-line test runner: it runs pytest test files, prints a table of every metric's score and reason, and takes flags for parallel runs, caching, repeats and errors.

Last updated: 05 Oct, 2026 · DeepEval 4.2.8

First test run ran it on two fixed answers with metrics that need no model. This lesson points it at the real bot: each golden is asked, each answer judged by the Groq judge for faithfulness and answer relevancy, and the run records which bot model and judge produced the scores.

The test file API

python
@pytest.mark.parametrize("golden", GOLDENS, ids=lambda g: g.name)  # one test per golden
def test_technest(golden):
    ...                                                             # run the bot, build a test case
    assert_test(test_case, [metric, ...])                           # fail below threshold

@deepeval.log_hyperparameters                                       # record what produced this run
def hyperparameters():
    return {"bot model": ..., "judge": ...}

Loading three goldens

The goldens come from goldens.json, loaded as in Datasets and goldens. Three of the five keep the run inside the judge's free token budget.

python
dataset = EvaluationDataset()
dataset.add_goldens_from_json_file("goldens.json", name_key_name="name")
GOLDENS = [g for g in dataset.goldens if g.name in {"g001", "g002", "g005"}]

One judged test per golden

python
@pytest.mark.parametrize("golden", GOLDENS, ids=lambda g: g.name)
def test_technest(golden):
    response, contexts = technest.answer(golden.input)
    test_case = LLMTestCase(input=golden.input, actual_output=response,
                            expected_output=golden.expected_output, retrieval_context=contexts)
    assert_test(test_case, [FaithfulnessMetric(model=judge), AnswerRelevancyMetric(model=judge)])

Logging hyperparameters

@deepeval.log_hyperparameters stores the returned dictionary with the test run. Months later, a saved run still says which bot model, judge and top_k produced its scores; Comparing models uses the same idea with evaluate().

python
@deepeval.log_hyperparameters
def hyperparameters():
    return {"bot model": technest.CHAT_MODEL, "judge": judge.get_model_name(), "top_k": 3}
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.
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"))
pytest.ini
[pytest]
addopts = --tb=no
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."
  }
]
goldens.json
[
  {
    "name": "g001",
    "input": "What is TechNest's return policy?",
    "expected_output": "TechNest accepts returns within 30 days of purchase. Items must be in original packaging with all accessories. Customers pay return shipping unless the item is defective. Refunds are processed in 5 to 7 business days."
  },
  {
    "name": "g002",
    "input": "What are the RAM and storage specs of the ProBook X1?",
    "expected_output": "The ProBook X1 has 16GB DDR5 RAM and a 512GB NVMe SSD."
  },
  {
    "name": "g003",
    "input": "How long is the battery life on the SoundPods Pro?",
    "expected_output": "The SoundPods Pro offer 8 hours of playback per charge and an additional 24 hours from the charging case, giving a total of 32 hours."
  },
  {
    "name": "g004",
    "input": "What are TechNest's shipping options and how long do returns take to process?",
    "expected_output": "TechNest offers free standard shipping on orders over $50 (3 to 5 business days) and expedited shipping for $9.99 (1 to 2 business days). Returns are accepted within 30 days and refunds are processed in 5 to 7 business days after the item is received."
  },
  {
    "name": "g005",
    "input": "What is the price of the PixelPhone 15?",
    "expected_output": "The TechNest PixelPhone 15 is priced at $899."
  }
]

The test_technest.py file

Save the whole file as test_technest.py, next to judge.py, technest.py, catalog.json, goldens.json and the pytest.ini from First test run.

python
import deepeval
import pytest
from deepeval import assert_test
from deepeval.dataset import EvaluationDataset
from deepeval.metrics import AnswerRelevancyMetric, FaithfulnessMetric
from deepeval.test_case import LLMTestCase

import technest
from judge import judge

dataset = EvaluationDataset()
dataset.add_goldens_from_json_file("goldens.json", name_key_name="name")
GOLDENS = [g for g in dataset.goldens if g.name in {"g001", "g002", "g005"}]


@pytest.mark.parametrize("golden", GOLDENS, ids=lambda g: g.name)
def test_technest(golden):
    response, contexts = technest.answer(golden.input)
    test_case = LLMTestCase(input=golden.input, actual_output=response,
                            expected_output=golden.expected_output, retrieval_context=contexts)
    assert_test(test_case, [FaithfulnessMetric(model=judge), AnswerRelevancyMetric(model=judge)])


@deepeval.log_hyperparameters
def hyperparameters():
    return {"bot model": technest.CHAT_MODEL, "judge": judge.get_model_name(), "top_k": 3}

Running the judged suite

ExampleAPI key
deepeval test run test_technest.py

What the suite reported

The table wraps each reason into a narrow column; the lines to read are the FAILED line and the summary.

  • g001 and g002 passed both metrics with 1.0: every claim in the answers is backed by the retrieved chunks, and nothing in them is off the question.
  • g005 passed faithfulness and failed answer relevancy with 0.33. The price is right and backed by the catalog, but the bot added the warranty and the colours, which the question did not ask about. Two metrics on one answer separate "true" from "to the point".
  • The pytest line says 1 failed, 2 passed, and the summary gives a 66.67% pass rate. The test IDs [g001], [g002] and [g005] come from ids=lambda g: g.name.
  • The hyperparameters warning is gone; the run now asks for prompts instead, as in Comparing models.
  • g005 took 95 seconds of the two minutes. On a free key, a long test is most often the judge's client waiting out a 429 before it retries, which does not fail the test.

Flags worth knowing

FlagWhat it doesWhen to use it
-n 2Runs tests in 2 processes (pytest-xdist)Large suites on a judge with a high rate limit
-cReuses cached metric results for unchanged test casesRe-running a suite after fixing one test
-r 3Runs every test case 3 timesSeeing how much a judged score moves between runs
-iRecords a metric error instead of failing the testWhen a judge call can time out and you still want the report
-xStops at the first failureDebugging one broken golden
-d failingShows only failing test cases in the tableCI logs
-id mainNames the runTelling runs apart in saved results

When to run the judged suite

  • Before merging a change to the prompt, the model or retrieve.
  • After upgrading the judge model, to see how much the scores shift on answers that did not change.
Watch out. -n starts several processes, and each one calls the judge at the same time. On Groq's free tier that reaches the tokens-per-minute limit quickly; the judge's retries wait it out, so the run can be slower in parallel than with one process. Rate limits and retries covers the settings that pace the calls.
Try it yourself
  • Run deepeval test run test_technest.py -c after the run above: it finishes in seconds, because the judge scores come from the cache the first run wrote. The bot is still called, and only answers that come back identical reuse a cached score.
  • Add g004 to the set in GOLDENS and run again: four tests instead of three.
  • Pass top_k=5 to technest.answer(golden.input, top_k=5), set "top_k": 5 in hyperparameters so the label matches the run, and check the saved JSON in .deepeval/.latest_test_run.json.
PreviousSafety metrics

Every expert started right here.