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 →

SingleTurnSample

SingleTurnSample is the RAGAS class that holds one test case: the question, the chunks the app retrieved, the app's answer, and the expected answer from the golden.

Last updated: 29 Sep, 2026 · RAGAS 0.4.3

A golden has a question and an expected answer. To score the app, you run the app on the question and keep what it returned. The four together are one sample, and every RAGAS metric reads its inputs from those four fields.

The test case: input, expected, actual and context · from the Production RAG Live Marathon · 185:14 to 189:13

From a golden to a test case

The video breaks the pipeline down on a whiteboard. The golden sends its input, the question, into the RAG app. The retriever fetches the context from the vector store; the LLM writes the actual output from that context. A test case then collects four things: the input, the expected output from the golden, the actual output and the retrieved context from the real run. In the video's exam analogy, the expected output comes from the teacher, and the actual output and context are what the student, the RAG app, wrote.

The golden's question goes into the RAG app; its retriever returns chunks and its generator returns an answer; the question, chunks, answer and the golden's reference together form one SingleTurnSample.

The SingleTurnSample fields

python

from ragas import SingleTurnSample

sample = SingleTurnSample(
    user_input="...",          # the input: the golden's question
    retrieved_contexts=[...],  # the context: chunks the app retrieved
    response="...",            # the actual output: the app's answer
    reference="...",           # the expected output: the golden's answer
)

RAGAS names the four parts differently from the video: user_input, retrieved_contexts, response and reference. The next lessons use these names.

Running the app on one golden

python

golden = goldens[0]
response, contexts = answer(golden["user_input"])

Filling the sample

python

sample = SingleTurnSample(
    user_input=golden["user_input"],
    retrieved_contexts=contexts,
    response=response,
    reference=golden["reference"],
)

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 TechNest RAG app
written in TechNest RAG app
written in Goldens

View the code here

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."
  }
]

Turning the five goldens into samples

This is the video's phase one: run the app on every golden and keep what comes back. The loop builds one sample per golden.

ExampleAPI key

import json

from ragas import SingleTurnSample
from technest import answer

goldens = json.load(open("goldens.json", encoding="utf-8"))
samples = []
for golden in goldens:
    response, contexts = answer(golden["user_input"])
    samples.append(SingleTurnSample(user_input=golden["user_input"], retrieved_contexts=contexts,
                                    response=response, reference=golden["reference"]))

first = samples[0]
print("user_input:        ", first.user_input)
print("retrieved_contexts:", len(first.retrieved_contexts), "chunks")
print("response:          ", first.response)
print("reference:         ", first.reference)
print()
print(len(samples), "samples built")

Output

user_input:         What is TechNest's return policy?
retrieved_contexts: 3 chunks
response:           TechNest accepts returns within 30 days of the original purchase date, provided the items are in their original packaging with all accessories included. Customers are responsible for return shipping costs unless the item arrives defective or damaged, and refunds are processed within 5 to 7 business days of receiving the returned item.
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.

5 samples built

What one sample holds

user_input and reference came from the golden, unchanged.
retrieved_contexts and response came from the app's real run, so they change when the app changes.
Five samples means the app ran five times: five searches and five answers. That is the data every metric reads.

Fields a metric does not need

Only the fields a metric reads have to be filled. A sample with a question and an answer is valid; the empty fields stay None.

Example

from ragas import SingleTurnSample

thin = SingleTurnSample(user_input="What is the price of the PixelPhone 15?", response="It costs $899.")
print(thin.retrieved_contexts, thin.reference)

Output

None None

Golden fields vs app fields

Field	Video's name	Comes from	Changes when the app changes?
`user_input`	input	The golden	No
`reference`	expected output	The golden	No
`retrieved_contexts`	retrieved context	The app's retriever	Yes
`response`	actual output	The app's LLM	Yes

Where you use samples

Scoring one answer by hand while you debug a metric.
Building a list of samples for evaluate(), the older API in evaluate() and EvaluationDataset.

Conversations use another class

There is also a MultiTurnSample for whole conversations with a chatbot. This course stays with single turns; the last lesson names the multi-turn metrics.

Watch out. Keep the chunks in the order the retriever returned them. Context precision scores that order, and a list sorted or deduplicated later scores a ranking the app never produced.

Try it yourself

Print samples[3].retrieved_contexts and check whether both the shipping and the return policy came back for g004.
Build the samples with answer(golden["user_input"], top_k=1) and compare the first sample's chunks.
Print first on its own to see every field a sample can hold.

PreviousGoldens

Every expert started right here.

SingleTurnSample

From a golden to a test case

The SingleTurnSample fields

Running the app on one golden

Filling the sample

Turning the five goldens into samples

What one sample holds

Fields a metric does not need

Golden fields vs app fields

Where you use samples

Related