Document loading and chunking strategies in Agentic AI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why chunk documents before processing?

Imagine you have a very long document to analyze with an AI model. Why is it useful to split this document into smaller chunks before processing?

A Because chunking removes important information from the document.

B Because chunking increases the total size of the document for better accuracy.

C Because smaller chunks reduce memory use and help the model focus on manageable parts.

D Because chunking merges multiple documents into one large file.

💡 Hint

Think about how computers handle large amounts of data and model input limits.

Chunking breaks a large document into smaller pieces so the AI model can process each piece without running out of memory or losing context. This helps keep the analysis accurate and efficient.

❓ Predict Output

intermediate

Output of chunking code snippet

What is the output of this Python code that chunks a text into pieces of 5 words?

Agentic AI

text = 'Machine learning helps computers learn from data and improve over time'
words = text.split()
chunks = [' '.join(words[i:i+5]) for i in range(0, len(words), 5)]
print(chunks)

A ['Machine learning helps computers learn from', 'data and improve over time']

B ['Machine learning helps computers learn', 'from data and improve over', 'time']

C ['Machine learning helps computers', 'learn from data and improve', 'over time']

D ['Machine learning helps', 'computers learn from', 'data and improve', 'over time']

💡 Hint

Look at how the range steps by 5 and how words are joined.

The code splits the text into words, then groups every 5 words into one chunk. The last chunk may have fewer than 5 words.

❓ Model Choice

advanced

Choosing chunk size for embedding models

You want to create vector embeddings from a large document for a search system. Which chunk size strategy is best to balance context and model limits?

A Use moderate chunk sizes (100-300 words) to balance context and model input limits.

B Use very small chunks (1-5 words) to get detailed embeddings.

C Use very large chunks (thousands of words) to keep full context.

D Do not chunk; embed the entire document at once.

💡 Hint

Consider model input size limits and the need for meaningful context.

Moderate chunk sizes keep enough context for meaningful embeddings while respecting model input size limits. Too small loses context; too large exceeds limits.

❓ Metrics

advanced

Evaluating chunking impact on retrieval accuracy

You test two chunking strategies for document search: small chunks (50 words) and large chunks (500 words). Which metric would best show if chunking size affects search accuracy?

A Recall@k measuring how many relevant documents are retrieved in top k results.

B Number of chunks created from the document.

C Training loss of the embedding model.

D Mean Squared Error (MSE) between chunk lengths.

💡 Hint

Think about how to measure search quality and relevance.

Recall@k measures how many relevant documents appear in the top k search results, showing how chunking affects retrieval accuracy.

🔧 Debug

expert

Debugging chunk overlap code error

What error does this code raise when trying to create overlapping chunks of size 4 with step 2?

text = 'AI models learn patterns from data to make predictions'
words = text.split()
chunks = [words[i:i+4] for i in range(0, len(words), 2)]
print(chunks[10])

A TypeError because words is not iterable.

B No error; prints the 11th chunk correctly.

C SyntaxError due to missing colon in list comprehension.

D IndexError because chunks[10] does not exist.

💡 Hint

Check how many chunks are created and if index 10 is valid.

The code creates fewer than 11 chunks, so accessing chunks[10] causes an IndexError.