嵌入：核心概念
探索嵌入的含义、它们如何在向量空间中表示数据，以及它们在相似度计算中的作用。
嵌入：核心概念 是 CoddyKit 上的免费 Vector Databases: Pinecone, Weaviate & pgvector 课时。 这是第 2 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 Vector Databases: Pinecone, Weaviate & pgvector 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Vector Databases: Pinecone, Weaviate & pgvector 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
Meet Embeddings!
Embeddings are digital fingerprints for your data — they turn words, images, or whole documents into vectors that capture meaning and context.
Why Do We Need Them?
Computers understand numbers, not raw language or images. Embeddings bridge that gap, giving the machine a numerical description it can actually process.
Your Data's New Home: Vector Space
An embedding lives in a vector space — a coordinate system with many dimensions. Each piece of data is a point, and similar items sit closer together.
Understanding Vectors
A vector is just an ordered list of numbers like [0.1, 0.5, -0.2, 0.8]. Each number captures a learned feature — not usually human-readable on its own.
How Data Becomes a Vector
An embedding model does the conversion: it processes your input and outputs a vector encoding its meaning. Similar meanings produce numerically similar vectors.
Dimensions: More Than Just 3D!
Embeddings often have hundreds or thousands of dimensions — think 768 or 1536. More dimensions capture finer nuance in the data's meaning.
Finding Similarities with Vectors
Here's the power: data with similar meaning produces vectors that sit close in the space, while unrelated data lands far apart. That proximity drives search.
How Do We Measure "Closeness"?
We measure closeness with distance metrics. Cosine similarity compares the angle between vectors; Euclidean distance measures the straight line between them.
Vectors: A Numerical Representation
Real embeddings come from complex models, but we can sketch vectors in code — notice how similar concepts get numerically similar values.
def main():
# Simplified example: Not actual embeddings generated by a model
# Imagine these numbers capture semantic features or attributes.
# Vector for a 'cat' (e.g., furry, small, pet, meows)
vector_cat = [0.7, 0.3, 0.1, 0.9]
# Vector for a 'dog' (e.g., furry, medium, pet, barks)
vector_dog = [0.6, 0.4, 0.2, 0.8]
# Vector for a 'car' (e.g., machine, transport, engine, fast)
vector_car = [0.1, 0.9, 0.8, 0.2]
print(f"Vector for 'Cat': {vector_cat}")
print(f"Vector for 'Dog': {vector_dog}")
print(f"Vector for 'Car': {vector_car}")
# In a real vector space, the 'cat' and 'dog' vectors
# would be much closer to each other than to the 'car' vector.
if __name__ == "__main__":
main()Check Your Understanding
Let's quickly test what you've learned about embeddings.
Recap: Your Data's Digital Fingerprint
Recap: embeddings are numeric vectors of complex data that let computers process meaning. They live in a vector space where proximity means similarity, measured by metrics like cosine.
常见问题解答
「嵌入：核心概念」课时是免费的吗？
是的 — 「嵌入：核心概念」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Vector Databases: Pinecone, Weaviate & pgvector 课程的其余内容，请升级到 CoddyKit PRO。 Vector Databases: Pinecone, Weaviate & pgvector 课程共包含 4 节课。
「嵌入：核心概念」这节课中我会学到什么？
探索嵌入的含义、它们如何在向量空间中表示数据，以及它们在相似度计算中的作用。 你通过在浏览器中直接运行的动手代码来练习 Vector Databases: Pinecone, Weaviate & pgvector，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 Vector Databases: Pinecone, Weaviate & pgvector 需要有经验吗？
无需任何先前经验。CoddyKit 上的 Vector Databases: Pinecone, Weaviate & pgvector 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 2 节课，共 4 节。
「嵌入：核心概念」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 Vector Databases: Pinecone, Weaviate & pgvector 课中编写并运行代码吗？
能。每节 Vector Databases: Pinecone, Weaviate & pgvector 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。