Similarity search and retrieval in Prompt Engineering / GenAI - Full Explanation

Introduction

Imagine trying to find a photo or document that looks or feels like another one you have, but you don't know its exact name or location. Similarity search and retrieval helps solve this problem by finding items that are alike based on their content, not just exact matches.

Explanation

Feature Representation

To compare items like images, text, or sounds, each item is first turned into a set of numbers called features. These features capture important details about the item, such as colors in a photo or meanings in a sentence. This step makes it easier to compare different items using math.

Turning items into numerical features allows computers to compare their similarities effectively.

Similarity Measurement

Once items are represented by features, a similarity score is calculated between them. This score shows how close or alike two items are. Common ways to measure similarity include calculating distances or angles between feature sets, where smaller distances mean more similarity.

Similarity scores quantify how alike two items are based on their features.

Indexing for Fast Search

When there are many items to search through, checking each one can be slow. Indexing organizes the features in a special way so the system can quickly find the most similar items without looking at everything. This makes searching fast even in huge collections.

Indexing speeds up similarity search by organizing data for quick access.

Retrieval Process

During retrieval, the system takes a new item, converts it to features, and uses the index to find items with the highest similarity scores. These results are then shown to the user as the closest matches. This process helps find related content even if exact matches don't exist.

Retrieval finds and returns items most similar to the query based on similarity scores.

Real World Analogy

Imagine you have a favorite song and want to find other songs that sound similar. Instead of knowing their names, you listen for similar beats, instruments, or moods. A music app does this by analyzing songs' features and quickly suggesting ones that feel alike.

Feature Representation → Listening to the beats, instruments, and mood of a song to understand its characteristics

Similarity Measurement → Comparing how close two songs sound based on their beats and mood

Indexing for Fast Search → Organizing songs in a playlist by their style so you can quickly find similar ones

Retrieval Process → Getting a list of songs that sound most like your favorite song

Diagram

Diagram

┌─────────────────────┐
│   Input Item (Query) │
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│ Feature Representation│
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│ Similarity Measurement│
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│   Indexed Database   │
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│   Retrieval Results  │
└─────────────────────┘

This diagram shows the flow from input item to feature extraction, similarity measurement, searching the indexed database, and retrieving results.

Key Facts

Feature Representation → A numerical summary of an item's important characteristics used for comparison.

Similarity Score → A number that shows how alike two items are based on their features.

Indexing → A method to organize data for faster searching in large collections.

Retrieval → The process of finding and returning items most similar to a query.

Common Confusions

Similarity search finds exact matches only.

Similarity search finds exact matches only. Similarity search finds items that are close or alike, not just exact copies, allowing flexible and broader results.

Features are the original data itself.

Features are the original data itself. Features are simplified numerical representations extracted from the original data to enable easy comparison.

Summary

Similarity search helps find items that are alike based on their content, not exact names or matches.

Items are converted into numerical features to compare their similarity using scores.

Indexing organizes data to make searching fast, and retrieval returns the closest matches to the query.

Practice

1.

What is the main goal of similarity search in machine learning?

easy

A. To count the number of items in a dataset

B. To sort items alphabetically

C. To find items that are close or alike in a collection

D. To remove duplicate items from a list

Solution

1. Step 1: Understand the purpose of similarity search

   Similarity search is used to find items that are similar or close to each other in a dataset.

2. Step 2: Compare options with the definition

   Only To find items that are close or alike in a collection describes finding similar or close items, which matches the goal of similarity search.

3. Final Answer:

   To find items that are close or alike in a collection -> Option C

4. Quick Check:

   Similarity search = find similar items [OK]

Hint: Similarity search finds close or alike items [OK]

Common Mistakes:

• Confusing similarity search with sorting
• Thinking similarity search counts items
• Assuming it removes duplicates

2.

Which of the following is the correct way to compute cosine similarity between two vectors A and B in Python using numpy?

import numpy as np
A = np.array([1, 2, 3])
B = np.array([4, 5, 6])
# What code computes cosine similarity?

easy

A. np.dot(A, B) * (np.linalg.norm(A) + np.linalg.norm(B))

B. np.dot(A, B) / (np.linalg.norm(A) - np.linalg.norm(B))

C. np.sum(A * B) / (np.linalg.norm(A) - np.linalg.norm(B))

D. np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B))

Solution

1. Step 1: Recall cosine similarity formula

   Cosine similarity = dot product of A and B divided by product of their norms.

2. Step 2: Match formula to code options

   np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B)) matches the formula exactly: np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B)).

3. Final Answer:

   np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B)) -> Option D

4. Quick Check:

   Cosine similarity = dot / (norm A * norm B) [OK]

Hint: Cosine similarity = dot product divided by norms product [OK]

Common Mistakes:

• Adding norms instead of multiplying
• Subtracting norms in denominator
• Multiplying dot product by sum of norms

3.

Given the following vectors, what is the cosine similarity between vec1 and vec2?

import numpy as np
vec1 = np.array([1, 0, 0])
vec2 = np.array([0, 1, 0])
cos_sim = np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2))
print("{:.2f}".format(cos_sim))

medium

A. 0.00

B. 0.50

C. -1.00

D. 1.00

Solution

1. Step 1: Calculate dot product of vec1 and vec2

   Dot product = 1*0 + 0*1 + 0*0 = 0.

2. Step 2: Calculate norms and cosine similarity

   Norm of vec1 = 1, norm of vec2 = 1, so cosine similarity = 0 / (1*1) = 0.

3. Final Answer:

   0.00 -> Option A

4. Quick Check:

   Orthogonal vectors have cosine similarity 0 [OK]

Hint: Orthogonal vectors have cosine similarity zero [OK]

Common Mistakes:

• Confusing dot product with cosine similarity
• Forgetting to divide by norms
• Rounding errors causing wrong answer

4.

Consider this code snippet for similarity search. What is the error?

import numpy as np
vectors = [np.array([1, 2]), np.array([3, 4])]
query = np.array([1, 0])
scores = []
for v in vectors:
    score = np.dot(query, v) / np.linalg.norm(query) * np.linalg.norm(v)
    scores.append(score)
print(scores)

medium

A. Missing parentheses causing wrong order of operations

B. Using np.dot instead of np.cross

C. Vectors have different lengths

D. Query vector is not normalized

Solution

1. Step 1: Analyze the cosine similarity formula in code

   The formula should divide dot product by product of norms: dot(query, v) / (norm(query) * norm(v)).

2. Step 2: Identify missing parentheses

   Code does np.dot(query, v) / np.linalg.norm(query) * np.linalg.norm(v), which computes division then multiplication separately, causing wrong result.

3. Final Answer:

   Missing parentheses causing wrong order of operations -> Option A

4. Quick Check:

   Use parentheses to group denominator multiplication [OK]

Hint: Use parentheses to group denominator in cosine similarity [OK]

Common Mistakes:

• Forgetting parentheses around denominator
• Using cross product instead of dot product
• Ignoring vector length mismatch

5.

You have a collection of text documents converted into vectors. You want to find the top 2 most similar documents to a new query vector using cosine similarity. Which approach is best?

1. Compute cosine similarity between query and each document vector.
2. Sort documents by similarity score descending.
3. Return top 2 documents.

Which code snippet correctly implements this?

import numpy as np

docs = [np.array([1, 0]), np.array([0, 1]), np.array([1, 1])]
query = np.array([1, 0])

# Choose the correct code:

hard

A. scores = [np.dot(query, d) * np.linalg.norm(query) * np.linalg.norm(d) for d in docs]
top2 = sorted(scores)[:2]
print(top2)

B. scores = [np.dot(query, d) / (np.linalg.norm(query) * np.linalg.norm(d)) for d in docs]
top2 = sorted(range(len(scores)), key=lambda i: scores[i], reverse=True)[:2]
print(top2)

C. scores = [np.dot(query, d) / (np.linalg.norm(query) - np.linalg.norm(d)) for d in docs]
top2 = sorted(range(len(scores)), key=lambda i: scores[i])[:2]
print(top2)

D. scores = [np.cross(query, d) / (np.linalg.norm(query) * np.linalg.norm(d)) for d in docs]
top2 = sorted(range(len(scores)), key=lambda i: scores[i], reverse=True)[:2]
print(top2)

Solution

1. Step 1: Compute cosine similarity correctly

   scores = [np.dot(query, d) / (np.linalg.norm(query) * np.linalg.norm(d)) for d in docs] top2 = sorted(range(len(scores)), key=lambda i: scores[i], reverse=True)[:2] print(top2) computes cosine similarity as dot product divided by product of norms, which is correct.

2. Step 2: Sort indices by similarity descending and select top 2

   scores = [np.dot(query, d) / (np.linalg.norm(query) * np.linalg.norm(d)) for d in docs] top2 = sorted(range(len(scores)), key=lambda i: scores[i], reverse=True)[:2] print(top2) sorts indices by scores descending and selects top 2, matching the requirement.

3. Final Answer:

   scores = [np.dot(query, d) / (np.linalg.norm(query) * np.linalg.norm(d)) for d in docs] top2 = sorted(range(len(scores)), key=lambda i: scores[i], reverse=True)[:2] print(top2) -> Option B

4. Quick Check:

   Cosine similarity + sort descending + top 2 = scores = [np.dot(query, d) / (np.linalg.norm(query) * np.linalg.norm(d)) for d in docs] top2 = sorted(range(len(scores)), key=lambda i: scores[i], reverse=True)[:2] print(top2) [OK]

Hint: Compute cosine similarity, sort descending, pick top results [OK]

Common Mistakes:

• Multiplying norms instead of dividing
• Using cross product instead of dot product
• Sorting ascending instead of descending