Client Portal Get a Quote

Question bank

Pick an answer to see if you're right — with an explanation.

All topicsPythonSQL / MySQLData ScienceNumPyPandasMatplotlibMachine LearningDeep LearningArtificial IntelligenceLarge Language ModelsDjangoAPIsGit & GitHubPower BIExcelStatistics
Large Language ModelsEasy
LLMs generate text by predicting…
aThe next token
bThe next sentence
cThe whole answer at once
dKeywords
Large Language ModelsEasy
What does an LLM's context window limit?
aThe number of API calls per minute
bThe total tokens of input plus output handled in one request
cThe size of the training dataset
dThe number of users
Large Language ModelsEasy
RAG stands for…
aRandom Answer Generation
bRecursive Attention Graph
cRapid AI Gateway
dRetrieval-Augmented Generation
Large Language ModelsEasy
Why do Hindi or Tamil prompts often cost more than English prompts of the same meaning?
aProviders charge a language surcharge
bThey are sent twice
cThey usually split into more tokens
dThey require a larger model
Large Language ModelsEasy
Lower temperature makes output…
aMore random
bLonger
cMore deterministic
dShorter
Large Language ModelsEasy
In tool/function calling, who actually executes the function?
aYour application code
bThe LLM provider's servers
cThe model itself
dThe user's browser
Large Language ModelsMedium
Embeddings are…
aCompressed images
bNumeric vectors representing meaning
cEncrypted text
dModel weights
Large Language ModelsEasy
Which approach is best for answering questions about a price list that changes every week?
aFine-tuning every week
bA longer system prompt with old prices
cHigher temperature
dRAG over the current price list or a tool that queries it
Large Language ModelsEasy
An assistant confidently states a refund policy that does not exist. This is called…
aA hallucination
bA timeout
cOverfitting
dA rate limit
Large Language ModelsMedium
What is the main risk in this code?
args = json.loads(call.function.arguments)
return db.get_order(args['order_id'])
ajson.loads is slow
bThe model may request an order that belongs to another user; authorisation is not checked
cOrder IDs must be integers
dTool calls cannot return dicts
Large Language ModelsMedium
What is the system message for?
messages = [
    {'role': 'system', 'content': 'You are a concise support agent for a bakery.'},
    {'role': 'user', 'content': 'Do you deliver on Sundays?'},
]
aIt is displayed to the end user
bIt stores the model's answer
cIt is billed as free tokens
dIt sets the role and rules the model should follow for the conversation
Large Language ModelsMedium
A chatbot's cost keeps growing as conversations get longer. The most likely reason is…
aTemperature increases over time
bThe model gets slower
cThe full chat history is re-sent as input tokens on every turn
dOutput tokens are free
Large Language ModelsMedium
In a RAG pipeline, why is a long document split into chunks before embedding?
aChunks make the embedding files smaller
bSo retrieval returns small, focused passages that fit in the prompt
cBecause models cannot embed PDFs
dTo randomise the order of the text
Large Language ModelsMedium
Which statement about LLM-as-judge evaluation is most accurate?
aIt is useful but should be calibrated against human ratings
bIt is always more accurate than humans
cIt needs no rubric
dIt removes the need for a test set
Large Language ModelsMedium
Which prompting technique does this use?
Classify the sentiment.
Review: 'Fast delivery, great packaging' -> positive
Review: 'Item arrived broken' -> negative
Review: 'Exactly as described' ->
aZero-shot prompting
bFine-tuning
cFew-shot prompting
dChain-of-thought prompting