DEVSAIO

Embeddings explained: what they are and how to use them

Embeddings turn text into numbers that capture meaning. Learn how they power search, recommendations and RAG, with code.

DEVSAIO team · 2 min read
Share on X

An embedding is a list of numbers (a vector) that represents the meaning of a piece of text. Texts with similar meaning get vectors that point in similar directions, even if they share no words.

“How do I reset my password?” and “I forgot my login” have very similar embeddings. That's what makes embeddings so useful.

Getting an embedding

python
r = client.embeddings.create(model="bge-m3", input=["How do I reset my password?", "I forgot my login"])
a, b = r.data[0].embedding, r.data[1].embedding

Comparing meaning: cosine similarity

python
import math

def cosine(a, b):
    dot = sum(x * y for x, y in zip(a, b))
    return dot / (math.sqrt(sum(x * x for x in a)) * math.sqrt(sum(y * y for y in b)))

print(cosine(a, b))  # close to 1 = very similar

What you can build

  • Semantic search: find help articles by meaning, not keywords.
  • RAG (retrieval-augmented generation): find the relevant documents, then give them to a chat model so it answers from your data. See RAG with embeddings in Python.
  • Deduplication: spot near-duplicate tickets or products.
  • Clustering: group feedback into themes automatically.
  • Recommendations: “articles similar to this one”.

Practical tips

  • Embed once, store forever. Save vectors in a database (pgvector, SQLite with a vector extension, or a vector database) instead of recomputing.
  • Chunk long documents into passages of a few hundred words before embedding.
  • Use the same model for your documents and your queries; vectors from different models aren't comparable.
  • Embeddings are cheap compared with chat; even large document sets usually cost little to index.
Try it with one API key

Claude, GPT, Gemini, DeepSeek, image and video models through one OpenAI- and Anthropic-compatible endpoint. Prepaid, pay only for what you use.

Keep reading