Retrieval strategies (similarity, MMR, hybrid) in Agentic AI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to compute cosine similarity between query and documents.

Agentic AI

similarity_scores = cosine_similarity(query_vector, [1])

Drag options to blanks, or click blank then click option'

Aempty_vectors

Bquery_vector

Crandom_vectors

Ddocument_vectors

Attempts:

3 left

💡 Hint

Common Mistakes

Using the query vector instead of document vectors for comparison.

The cosine similarity compares the query vector to each document vector to find how similar they are.

2fill in blank

medium

Complete the code to select top k documents based on similarity scores.

Agentic AI

top_k_indices = similarity_scores.argsort()[::-1][:[1]]

Drag options to blanks, or click blank then click option'

A0

Bn

Ck

Dlen

Attempts:

3 left

💡 Hint

Common Mistakes

Using 0 or len instead of k for slicing.

We select the top k documents by sorting similarity scores in descending order and taking the first k indices.

3fill in blank

hard

Fix the error in the Maximal Marginal Relevance (MMR) score calculation.

Agentic AI

mmr_score = lambda doc, selected: lambda_param * similarity(doc, query) - (1 - lambda_param) * max(similarity(doc, s) for s in [1])

Drag options to blanks, or click blank then click option'

Aselected

Bquery

Call_docs

Ddocuments

Attempts:

3 left

💡 Hint

Common Mistakes

Using the query or all documents instead of selected documents for redundancy check.

In MMR, we subtract the maximum similarity of the candidate document to already selected documents to reduce redundancy.

4fill in blank

hard

Fill both blanks to implement a hybrid retrieval score combining similarity and MMR.

Agentic AI

hybrid_score = lambda doc, selected: alpha * similarity(doc, query) + (1 - alpha) * [1](doc, selected)
selected_doc = max(candidates, key=lambda doc: [2](doc, selected))

Drag options to blanks, or click blank then click option'

Ammr_score

Bsimilarity

Chybrid_score

Dredundancy_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using similarity instead of mmr_score for the first blank.

Using similarity instead of hybrid_score for selection.

The hybrid score combines similarity and MMR. We use mmr_score function and select the document with the highest hybrid_score.

5fill in blank

hard

Fill all three blanks to create a dictionary of document scores filtered by a threshold.

Agentic AI

filtered_scores = {doc: [1] for doc, score in scores.items() if score [2] [3]

Drag options to blanks, or click blank then click option'

Ascore

B>

Cthreshold

Ddoc

Attempts:

3 left

💡 Hint

Common Mistakes

Using doc instead of score as dictionary value.

Using '<' instead of '>' for filtering.

This dictionary comprehension keeps documents with scores greater than a threshold and maps each document to its score.

Practice

1. Which retrieval strategy focuses on ranking results purely based on how close they are to the query?

easy

A. Random retrieval

B. Maximal Marginal Relevance (MMR)

C. Similarity-based retrieval

D. Hybrid retrieval

Solution

1. Step 1: Understand similarity-based retrieval

   Similarity-based retrieval ranks results by how close or similar they are to the query, focusing only on relevance.

2. Step 2: Compare with other strategies

   MMR balances relevance and diversity, hybrid combines methods, and random is unrelated.

3. Final Answer:

   Similarity-based retrieval -> Option C

4. Quick Check:

   Similarity = closeness only [OK]

Hint: Similarity means closest match only [OK]

Common Mistakes:

• Confusing MMR with similarity
• Thinking hybrid is only similarity
• Choosing random as a valid strategy

2. Which of the following is the correct way to describe Maximal Marginal Relevance (MMR)?

easy

A. Combines all retrieval methods without weighting

B. Ranks results by random selection

C. Only uses keyword matching

D. Balances relevance and diversity in retrieval

Solution

1. Step 1: Define MMR

   MMR is designed to balance relevance to the query and diversity among the results to avoid redundancy.

2. Step 2: Eliminate incorrect options

   Random selection is unrelated, keyword matching is too narrow, and combining without weighting is not MMR.

3. Final Answer:

   Balances relevance and diversity in retrieval -> Option D

4. Quick Check:

   MMR = relevance + diversity [OK]

Hint: MMR mixes relevance with diversity [OK]

Common Mistakes:

• Thinking MMR is random
• Assuming MMR uses only keywords
• Believing MMR combines methods blindly

3. Given the following pseudo-code for a hybrid retrieval method combining similarity and MMR scores:

results = []
for doc in documents:
    sim_score = similarity(query, doc)
    mmr_score = mmr(query, doc, results)
    combined_score = 0.6 * sim_score + 0.4 * mmr_score
    results.append((doc, combined_score))
results.sort(key=lambda x: x[1], reverse=True)
print([doc for doc, score in results[:3]])

What does this code output?

medium

A. Top 3 documents ranked by combined similarity and MMR scores

B. Top 3 documents ranked by similarity score only

C. Top 3 documents ranked by MMR score only

D. Random 3 documents from the list

Solution

1. Step 1: Analyze score calculation

   The code calculates a combined score using 60% similarity and 40% MMR for each document.

2. Step 2: Understand sorting and output

   Documents are sorted by this combined score in descending order, then top 3 are printed.

3. Final Answer:

   Top 3 documents ranked by combined similarity and MMR scores -> Option A

4. Quick Check:

   Hybrid = combined scores [OK]

Hint: Check weighted sum and sorting for final ranking [OK]

Common Mistakes:

• Ignoring MMR score in combined score
• Assuming sorting by similarity only
• Thinking output is random

4. Consider this buggy code snippet for MMR retrieval:

def mmr(query, docs, selected):
    scores = []
    for doc in docs:
        relevance = similarity(query, doc)
        diversity = min([similarity(doc, s) for s in selected])
        score = relevance - 0.5 * diversity
        scores.append((doc, score))
    return max(scores, key=lambda x: x[1])[0]

What is the main error causing a crash when selected is empty?

medium

A. Using min() on an empty list causes an error

B. Incorrect use of max() function

C. Missing return statement

D. Similarity function is undefined

Solution

1. Step 1: Identify cause of crash

   When selected is empty, the list inside min() is empty, causing a ValueError.

2. Step 2: Understand min() behavior

   min() cannot operate on empty lists, so the code crashes at that line.

3. Final Answer:

   Using min() on an empty list causes an error -> Option A

4. Quick Check:

   min(empty list) = error [OK]

Hint: Check min() on empty lists for errors [OK]

Common Mistakes:

• Blaming max() instead of min()
• Ignoring empty list edge case
• Assuming similarity is undefined

5. You want to improve a search system by combining similarity and MMR retrieval. Which approach best balances relevance and diversity in the final results?

hard

A. Use MMR with a diversity weight of zero

B. Combine similarity and MMR scores with adjustable weights

C. Use only similarity scores to rank results

D. Randomly shuffle results after similarity ranking

Solution

1. Step 1: Understand the goal

   Balancing relevance and diversity requires combining both similarity and MMR scores meaningfully.

2. Step 2: Evaluate options

   Using only similarity or zero diversity weight ignores diversity; random shuffling loses relevance order.

3. Step 3: Best approach

   Combining similarity and MMR with adjustable weights allows tuning the balance effectively.

4. Final Answer:

   Combine similarity and MMR scores with adjustable weights -> Option B

5. Quick Check:

   Hybrid weighted combination = best balance [OK]

Hint: Adjust weights to balance relevance and diversity [OK]

Common Mistakes:

• Ignoring diversity by using similarity only
• Setting diversity weight to zero in MMR
• Randomizing results without scoring