RAGASragas 0.4.3 · 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
28 small wins to finish your pathNext lesson →

Evals in CI

Evals in CI means running a chosen subset of your goldens as tests on every change, so a score below its threshold fails the build before the change ships.

Last updated: 29 Sep, 2026 · RAGAS 0.4.3

A score someone has to remember to read gets forgotten. In a CI pipeline the score is an assertion. The question the video answers first is which goldens belong there, because running all of them on every push is too slow and too costly.

Where evaluation runs: unit tests and the full exam · from the Production RAG Live Marathon · 213:57 to 219:27

Essential goldens on every deploy, the full set weekly

The video asks the obvious question: running thousands of goldens through a judge is slow and expensive, so should it run on every RAG call? No. It borrows the school calendar. The annual exam covers the whole syllabus and happens once a year; unit tests cover a few chapters and happen often. So you split the golden set.

  • Essential goldens, say the 50 that must always pass, run on every deployment, like unit tests.
  • Feature goldens run when that feature changes; change how answers are formatted and you run the formatting goldens.
  • The full set runs once a week or every two weeks, the annual exam.

In a CI/CD pipeline, a code or config change triggers checks before deployment, and the evaluation subset is one of them. The pipeline stays the same; only the slice of goldens changes.

The pytest test API

python
@pytest.mark.parametrize("golden", GOLDENS, ids=lambda g: g["id"])  # one test per golden
def test_answer_is_grounded(golden):
    ...
    assert result.value >= 0.8, "message shown when it fails"

The essential subset

python
ESSENTIAL = ["g001", "g005"]  # the goldens every deployment must pass
GOLDENS = [g for g in json.load(open("goldens.json", encoding="utf-8")) if g["id"] in ESSENTIAL]

Two of the five goldens: the return policy and the price, the answers that cost money when wrong. Your essential list is a choice, written down in the test file.

One assertion per golden

python
response, contexts = answer(golden["user_input"])
result = faithfulness.score(user_input=golden["user_input"], response=response, retrieved_contexts=contexts)
assert result.value >= 0.8, f"{golden['id']} faithfulness {result.value:.2f}: {response}"

The message carries the score and the answer, so a failing build says what the bot said, not only that it failed. 0.8 is the video's faithfulness pass mark.

The test file

Install pytest, then save this as test_technest.py next to technest.py, catalog.json, judge.py and goldens.json.

pip install "pytest==9.1.1"
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 google import genai
from openai import AsyncOpenAI
from ragas.embeddings import GoogleEmbeddings
from ragas.llms import llm_factory

groq = AsyncOpenAI(
    api_key=os.environ.get("JUDGE_GROQ", os.environ["GROQ_API_KEY"]),
    base_url="https://api.groq.com/openai/v1",
)
judge = llm_factory("openai/gpt-oss-20b", provider="openai", client=groq)


class OneTextPerCall(GoogleEmbeddings):
    """gemini-embedding-2 turns a list into one embedding, so embed each text on its own."""

    def embed_texts(self, texts, **kwargs):
        return [self.embed_text(text) for text in texts]

    async def aembed_texts(self, texts, **kwargs):
        return [await self.aembed_text(text) for text in texts]


embeddings = OneTextPerCall(client=genai.Client(), model="gemini-embedding-2")
technest.py
import json
import os

import numpy as np
from google import genai
from openai import OpenAI

gemini = genai.Client()  # reads GOOGLE_API_KEY
groq = OpenAI(api_key=os.environ["GROQ_API_KEY"], base_url="https://api.groq.com/openai/v1")
EMBED_MODEL = "gemini-embedding-2"
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)


def embed(texts):
    # gemini-embedding-2 turns everything in one call into one embedding, so send one text per call
    vectors = np.array([gemini.models.embed_content(model=EMBED_MODEL, contents=t).embeddings[0].values for t in texts])
    return vectors / np.linalg.norm(vectors, axis=1, keepdims=True)


DOC_VECTORS = embed([f"{item['title']}. {item['content']}" for item in CATALOG])


def retrieve(question, top_k=3):
    scores = DOC_VECTORS @ embed([question])[0]
    best = np.argsort(scores)[::-1][:top_k]
    return [CATALOG[i]["content"] for i in best]


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
[
  {
    "id": "g001",
    "metric_focus": "faithfulness",
    "user_input": "What is TechNest's return policy?",
    "reference": "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."
  },
  {
    "id": "g002",
    "metric_focus": "answer_relevancy",
    "user_input": "What are the RAM and storage specs of the ProBook X1?",
    "reference": "The ProBook X1 has 16GB DDR5 RAM and a 512GB NVMe SSD."
  },
  {
    "id": "g003",
    "metric_focus": "context_precision",
    "user_input": "How long is the battery life on the SoundPods Pro?",
    "reference": "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."
  },
  {
    "id": "g004",
    "metric_focus": "context_recall",
    "user_input": "What are TechNest's shipping options and how long do returns take to process?",
    "reference": "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."
  },
  {
    "id": "g005",
    "metric_focus": "answer_correctness",
    "user_input": "What is the price of the PixelPhone 15?",
    "reference": "The TechNest PixelPhone 15 is priced at $899."
  }
]
python
import json

import pytest
from judge import judge
from ragas.metrics.collections import Faithfulness
from technest import answer

ESSENTIAL = ["g001", "g005"]  # the goldens every deployment must pass
GOLDENS = [g for g in json.load(open("goldens.json", encoding="utf-8")) if g["id"] in ESSENTIAL]
faithfulness = Faithfulness(llm=judge)


@pytest.mark.parametrize("golden", GOLDENS, ids=lambda g: g["id"])
def test_answer_is_grounded(golden):
    response, contexts = answer(golden["user_input"])
    result = faithfulness.score(user_input=golden["user_input"], response=response, retrieved_contexts=contexts)
    assert result.value >= 0.8, f"{golden['id']} faithfulness {result.value:.2f}: {response}"

Running the essential goldens with pytest

ExampleAPI key
pytest -q test_technest.py

What pytest reported

  • One dot per golden: both essential goldens passed the 0.8 faithfulness mark on this run.
  • The time, about a minute here, is almost all judge and app calls. Two goldens keep it short; the full set would take several times as long.
  • A failure would print the assertion message: the golden id, its score, and the bot's answer.

A GitHub Actions job

The same command in a CI job. The keys come from the repository's secrets, never from the file.

yaml
name: evals
on: pull_request
jobs:
  essential-goldens:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"
      - run: pip install "ragas==0.4.3" "langchain-community<0.4" "google-genai==2.25.0" "pytest==9.1.1"
      - run: pytest -q test_technest.py
        env:
          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}

Every change vs a schedule

Essential goldensFeature goldensFull golden set
RunsOn every pull requestWhen that feature changesWeekly or every two weeks
SizeSmallMediumAll of them
Video's analogyUnit testChapter testAnnual exam

When to put evals in CI

  • When a prompt, retriever or model change could break an answer that costs money, without anyone noticing.
  • When more than one person changes the app, so no one has to remember to run the evaluation.
Watch out. Set the threshold from measured scores, not from a wish. Run the essential goldens a few times, look at the lowest score a good answer gets, and set the line a little below it; too high and the build fails on judge wobble, too low and it never catches anything.
Try it yourself
  • Add "g003" to ESSENTIAL and run pytest again.
  • Raise the threshold to 0.99, run it, and read the failure message.
  • Add a second test that checks context_recall for g004 with its own threshold.
PreviousCollections and legacy metrics

Every expert started right here.