Retrieval strategies (similarity, MMR, hybrid) in Agentic AI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a similarity-based retrieval strategy?

A similarity-based retrieval strategy finds items that are most alike to a query by measuring how close or similar their features are. It often uses metrics like cosine similarity or Euclidean distance to rank results.

intermediate

Explain Maximal Marginal Relevance (MMR) in retrieval.

MMR balances relevance and diversity by selecting items that are both similar to the query and different from each other. This helps avoid redundant results and provides a varied set of answers.

intermediate

What does a hybrid retrieval strategy combine?

A hybrid retrieval strategy combines similarity-based methods with other techniques like MMR or rule-based filters to improve both relevance and diversity of results.

beginner

Why is diversity important in retrieval results?

Diversity ensures that retrieved results cover different aspects or perspectives, reducing repetition and increasing the chance of finding useful information.

beginner

Name two common similarity metrics used in retrieval strategies.

Cosine similarity and Euclidean distance are two common metrics used to measure how close or similar items are in retrieval tasks.

Which retrieval strategy explicitly balances relevance and diversity?

A Pure similarity-based retrieval

B Maximal Marginal Relevance (MMR)

C Random selection

D Rule-based filtering

MMR selects items that are relevant to the query but also different from each other to ensure diversity.

What does a similarity-based retrieval strategy primarily use to rank results?

A Predefined categories

B Random chance

C User feedback only

D Similarity metrics like cosine similarity

Similarity-based retrieval ranks items by how close they are to the query using similarity metrics.

A hybrid retrieval strategy might combine similarity with which other approach?

A Only random selection

B Ignoring diversity

C Maximal Marginal Relevance (MMR)

D No filtering

Hybrid strategies combine similarity with methods like MMR to improve result quality.

Why avoid only similarity-based retrieval without diversity?

A Results may be repetitive and less useful

B It is faster

C It always gives the best results

D It ignores relevance

Without diversity, results can be very similar and redundant, reducing usefulness.

Which metric measures the angle between two vectors in retrieval?

A Cosine similarity

B Euclidean distance

C Manhattan distance

D Jaccard index

Cosine similarity measures the angle between vectors, indicating how similar they are.

Describe how Maximal Marginal Relevance (MMR) improves retrieval results compared to pure similarity-based methods.

Think about why showing only very similar items might not be helpful.

Explain what a hybrid retrieval strategy is and why it might be better than using only one retrieval method.

Consider mixing strengths of different approaches.

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