類似度クエリの実行
pgvectorの演算子を使って基本的なベクトル類似度クエリを実行し、データ内の最近傍を見つけます。
「類似度クエリの実行」はCoddyKit上の無料Vector Databases: Pinecone, Weaviate & pgvectorレッスンです。 これはレッスン3/4です。 下記で完全なレッスンを無料で読むことができます。その後、ブラウザ内の組み込みコードエディタと24時間対応のAIチューターでハンズオン演習できます。 これはVector Databases: Pinecone, Weaviate & pgvector学習パスの一部であり、ウェブとCoddyKitアプリ全体で進捗が同期されます。 Vector Databases: Pinecone, Weaviate & pgvectorコースには全4レッスンが含まれています。
このレッスンの一部はまだ翻訳されておらず、英語で表示されています。
Unlocking Similarity Queries
Welcome! In this lesson, we'll dive into one of the most powerful features of vector databases: similarity queries.
You'll learn how to ask your database to find items that are 'similar' to a given item, based on their vector embeddings.
Why Similarity Matters
Similarity queries are at the heart of many AI applications:
- Recommendation Systems: Find products similar to what a user liked.
- Semantic Search: Retrieve documents with similar meaning, not just keyword matches.
- Anomaly Detection: Identify data points that are unusually 'far' from others.
They help us make sense of high-dimensional data.
Measuring Vector Distance
How do we define 'similarity' for vectors? We use distance metrics.
Imagine vectors as points in space. The 'closer' two points are, the more similar their underlying data is. Different metrics measure this distance in different ways.
Euclidean Distance (L2 Norm)
Euclidean distance, also known as L2 distance, is the most intuitive metric. It's the straight-line distance between two points in a Euclidean space.
In pgvector, you use the <-> operator to calculate Euclidean distance. A smaller value means higher similarity.
Cosine Similarity / Distance
Cosine similarity measures the cosine of the angle between two vectors. It tells you if vectors are pointing in roughly the same direction, regardless of their magnitude (length).
pgvector uses the <#> operator for cosine distance. Cosine distance is 1 - cosine_similarity. A smaller cosine distance (closer to 0) means the vectors are more aligned and similar.
Preparing Our Data for Queries
To demonstrate queries, let's set up a simple table with some 3-dimensional vectors. This ensures our code snippets are runnable.
CREATE EXTENSION IF NOT EXISTS vector;
DROP TABLE IF EXISTS items;
CREATE TABLE items (
id serial PRIMARY KEY,
embedding vector(3)
);
INSERT INTO items (embedding) VALUES ('[1,2,3]');
INSERT INTO items (embedding) VALUES ('[1.1,2.1,3.1]');
INSERT INTO items (embedding) VALUES ('[10,20,30]');
INSERT INTO items (embedding) VALUES ('[0.9,1.9,2.9]');
INSERT INTO items (embedding) VALUES ('[1.2,2.2,3.2]');Euclidean Distance Query Example
Now, let's find the 3 items whose embeddings are closest to [1,2,3] using Euclidean distance.
Notice the <-> operator in action!
SELECT
id,
embedding,
embedding <-> '[1,2,3]' AS euclidean_distance
FROM items
ORDER BY euclidean_distance
LIMIT 3;Interpreting Euclidean Results
When you run the query, you'll see a euclidean_distance column. The items with the smallest distance values are the most similar to your query vector [1,2,3].
For example, [1.1,2.1,3.1] should have a very small Euclidean distance, indicating high similarity.
Cosine Distance Query Example
Next, let's perform a similarity search using cosine distance. We'll again query for items similar to [1,2,3].
Observe the <#> operator. Remember, it returns cosine distance, where lower values mean higher similarity.
SELECT
id,
embedding,
embedding <#> '[1,2,3]' AS cosine_distance
FROM items
ORDER BY cosine_distance
LIMIT 3;Interpreting Cosine Results
The cosine_distance column shows how aligned the vectors are. A value close to 0 means the vectors point in almost the same direction (very similar).
A value close to 2 means they point in opposite directions (very dissimilar). Values near 1 mean they are orthogonal.
Choosing the Right Metric
Which metric should you use?
- Euclidean distance is great when the magnitude (length) of the vector is important.
- Cosine similarity/distance is preferred when only the direction of the vector matters, not its length. This is common for text embeddings where vector length might vary but direction captures semantic meaning.
Quick Check: Operators
You've learned about two key pgvector operators for similarity queries. Let's test your knowledge!
Recap: Similarity Queries
Great job! You've learned how to perform similarity queries with pgvector.
- We use distance metrics to quantify similarity.
- Euclidean distance (
<->) measures straight-line distance. - Cosine distance (
<#>) measures the angle between vectors. - Choosing the right metric depends on whether vector magnitude or direction is more relevant for your data.
よくある質問
「類似度クエリの実行」レッスンは無料ですか？
はい。「類似度クエリの実行」の完全なテキストはこのウェブで無料で読めます。インタラクティブに演習し（組み込みコードエディタと24時間対応のAIチューター）、Vector Databases: Pinecone, Weaviate & pgvectorコースの残りをアンロックするには、CoddyKit PROにアップグレードしてください。 Vector Databases: Pinecone, Weaviate & pgvectorコースには全4レッスンが含まれています。
「類似度クエリの実行」で何を学びますか？
pgvectorの演算子を使って基本的なベクトル類似度クエリを実行し、データ内の最近傍を見つけます。 ブラウザで直接実行するハンズオンコードでVector Databases: Pinecone, Weaviate & pgvectorを演習し、24時間対応のAIチューターがレッスンを進める中での質問に答えます。
Vector Databases: Pinecone, Weaviate & pgvectorを始めるのに経験は必要ですか？
事前経験は必要ありません。CoddyKitのVector Databases: Pinecone, Weaviate & pgvectorは初級者から上級者向けに構成されているため、ここから始めるか最初から始めて、自分のペースで進むことができます。 これはレッスン3/4です。
「類似度クエリの実行」レッスンにはどのくらい時間がかかりますか？
ほとんどのCoddyKitレッスンは約5～10分かかります。各レッスンはコンパクトでインタラクティブなので、着実に進歩し、ウェブとアプリ全体で正確に前回の場所から再開できます。
このVector Databases: Pinecone, Weaviate & pgvectorレッスンでコードを書いて実行できますか？
はい。すべてのVector Databases: Pinecone, Weaviate & pgvectorレッスンに組み込みコードエディタが含まれているため、ブラウザでリアルコードを書いて実行し、即座のAIフィードバックを取得できます。ローカル設定は不要です。