Retrieval strategies (similarity, MMR, hybrid) in Agentic AI - Model Pipeline Trace

Model Pipeline - Retrieval strategies (similarity, MMR, hybrid)

This pipeline shows how different retrieval strategies find the best information from a large set. It uses similarity, Maximal Marginal Relevance (MMR), and a hybrid of both to pick relevant and diverse results.

Data Flow - 7 Stages

1Input Query

1 query string→Receive user question or search phrase→1 query string

"What are the benefits of exercise?"

↓

2Document Collection

1000 documents (text)→Load all documents to search from→1000 documents (text)

Articles about health, fitness, nutrition, etc.

↓

3Embedding Generation

1 query string, 1000 documents→Convert query and documents into vector embeddings→1 query vector (512 dims), 1000 document vectors (512 dims)

Query vector: [0.12, -0.03, ..., 0.45], Document vector: [0.05, 0.10, ..., -0.02]

↓

4Similarity Calculation

1 query vector, 1000 document vectors→Calculate cosine similarity scores between query and each document→1000 similarity scores (float -1 to 1)

Scores like 0.85, 0.60, 0.45 for documents

↓

5MMR Re-ranking

Top 100 documents with similarity scores→Re-rank documents balancing relevance and diversity using MMR→Top 10 documents re-ranked

Selected documents that are relevant but not too similar to each other

↓

6Hybrid Strategy

Similarity scores and MMR scores→Combine similarity and MMR scores to select final documents→Final 5 documents

Documents that are both highly relevant and diverse

↓

7Output Results

Final 5 documents→Return selected documents as search results→5 documents (text)

Articles explaining exercise benefits with different focuses

Training Trace - Epoch by Epoch

Loss
0.7 | *
0.6 |  *
0.5 |   *
0.4 |    *
0.3 |     *
0.2 |      *
    +----------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.55	Initial training with random weights, loss high, accuracy low
2	0.48	0.68	Model starts learning to rank documents better
3	0.35	0.78	Loss decreases steadily, accuracy improves
4	0.28	0.83	Model converging, better relevance and diversity balance
5	0.24	0.87	Final epoch shows good performance on validation data

Prediction Trace - 5 Layers

Layer 1: Embedding Generation

Layer 2: Similarity Calculation

Layer 3: MMR Re-ranking

Layer 4: Hybrid Strategy

Layer 5: Output Results

Model Quiz - 3 Questions

What does the similarity calculation stage do?

A Converts text into numbers

B Removes duplicate documents

C Measures how close the query and documents are in meaning

D Combines relevance and diversity scores

Key Insight

This visualization shows how combining similarity and MMR retrieval strategies helps find documents that are both relevant and diverse, improving the quality of search results.

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