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 →

Context recall

Context recall is a RAGAS metric that measures whether the retrieved chunks contain everything the reference answer needs: the share of the reference's claims that some chunk supports.

Last updated: 29 Sep, 2026 · RAGAS 0.4.3

If the chunk with a fact never comes back, no prompt can put that fact in the answer. Context recall measures the search against the golden answer, so it tells you when the fix belongs in retrieval.

Context recall and the missing claim · from the Production RAG Live Marathon · 239:05 to 244:35

Claims from the reference, checked against the chunks

The video lines the metrics up. Faithfulness guards against hallucination; answer relevancy checks the answer addresses the question. Context recall checks the third side: whether the retrieved context is sufficient. It reads two things, the reference, the golden's correct answer, and the retrieved context.

The judge works in two steps. It breaks the reference into claims, the facts a complete answer must contain, then checks whether each claim can be attributed to some retrieved chunk. In the bank example, the reference makes four claims; three are in the chunks and "Rural branch minimum balance is ₹2,500" is in none. Three out of four: 0.75. The gap points at ingestion or at the semantic search.

The ContextRecall API

python

from ragas.metrics.collections import ContextRecall

recall = ContextRecall(llm=judge)
recall.score(user_input=..., retrieved_contexts=[...], reference=...).value  # supported claims / reference claims

The reference with four claims

python

reference = ("Urban branches require a ₹10,000 minimum balance. The non-maintenance fee is ₹350 + taxes "
             "when the balance falls below the limit. Rural branch minimum balance is ₹2,500. "
             "Semi-urban branch minimum balance is ₹5,000.")

Chunks that miss the rural balance

python

chunks = [
    "Minimum balance is ₹10,000 for urban branches.",
    "Non-maintenance fee is ₹350 + taxes if the balance falls below the minimum.",
    "KYC update is required every 8 years.",
    "Semi-urban branch minimum balance is ₹5,000.",
]

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 LLM as a judge
written in TechNest RAG app
written in TechNest RAG app
written in Goldens

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."
  }
]

The video's missing-claim example

ExampleAPI keyFrom the video, run on Groq

from judge import judge
from ragas.metrics.collections import ContextRecall

question = "What is the minimum balance for my savings account?"
reference = ("Urban branches require a ₹10,000 minimum balance. The non-maintenance fee is ₹350 + taxes "
             "when the balance falls below the limit. Rural branch minimum balance is ₹2,500. "
             "Semi-urban branch minimum balance is ₹5,000.")
chunks = [
    "Minimum balance is ₹10,000 for urban branches.",
    "Non-maintenance fee is ₹350 + taxes if the balance falls below the minimum.",
    "KYC update is required every 8 years.",
    "Semi-urban branch minimum balance is ₹5,000.",
]

recall = ContextRecall(llm=judge)
print("rural chunk missing:", recall.score(user_input=question, retrieved_contexts=chunks, reference=reference).value)
with_rural = chunks + ["Rural branch minimum balance is ₹2,500."]
print("rural chunk added:  ", recall.score(user_input=question, retrieved_contexts=with_rural, reference=reference).value)

Output

rural chunk missing: 0.75
rural chunk added:   1.0

The first line is the slide's case. Adding back the missing chunk, and leaving the reference and the question as they were, is the retrieval fix the video describes.

Recall of the TechNest retriever on g004

The AI security course version of this lesson names the usual cause of a low recall: k too small. The chunks are relevant, but the retriever keeps too few of them. g004 asks about shipping and returns, two policies, so try it with three chunks and with one.

ExampleAPI key

import json

from judge import judge
from ragas.metrics.collections import ContextRecall
from technest import retrieve

golden = json.load(open("goldens.json", encoding="utf-8"))[3]
recall = ContextRecall(llm=judge)
for top_k in [3, 1]:
    contexts = retrieve(golden["user_input"], top_k=top_k)
    result = recall.score(user_input=golden["user_input"], retrieved_contexts=contexts, reference=golden["reference"])
    print(f"top_k={top_k}  recall={result.value:.2f}  first chunk: {contexts[0][:50]}...")

Output

top_k=3  recall=1.00  first chunk: TechNest offers free standard shipping on all orde...
top_k=1  recall=0.50  first chunk: TechNest offers free standard shipping on all orde...

Reading the two recall scores

top_k=3 brings back both the return and the shipping policy, so most or all of the reference's claims are supported.
top_k=1 keeps only the first chunk, one of the two policies, and every claim from the other one is unsupported. Recall drops though the retriever ranked well.
The reference did not change, only what was retrieved, so the drop is a retrieval problem.

Context recall vs faithfulness

The video puts the two side by side, because both extract claims and check them. The direction is opposite. Faithfulness takes claims from the answer and checks them against the chunks; the reference plays no part. Context recall takes claims from the reference and checks them against the chunks; the app's answer plays no part. Faithfulness judges the answer, recall judges the retrieved context.

	Faithfulness	Context recall
Claims come from	The app's answer	The golden's reference
Checked against	The retrieved chunks	The retrieved chunks
Judges	The generation	The retrieval
Needs a reference?	No	Yes

When to use context recall

After changing chunk size, top_k or the embedding model, to check nothing needed stopped coming back.
When answers are incomplete and you need to know if the facts were never retrieved.

Watch out. A low recall is not the answer's fault, and the reference is not wrong. The video stresses this: the golden answer is the ideal, so a claim missing from the chunks means the retrieval pipeline must change.

Try it yourself

Run g004 with top_k=5 and check whether recall changes.
Remove the urban-balance chunk from the bank example instead of the rural one and predict the score.

PreviousContext precision

This is what real progress feels like.

Context recall

Claims from the reference, checked against the chunks

The ContextRecall API

The reference with four claims

Chunks that miss the rural balance

The video's missing-claim example

Recall of the TechNest retriever on g004

Reading the two recall scores

Context recall vs faithfulness

When to use context recall

Related