How to create embeddings for semantic search

Turn text into vectors for search and RAG with OpenAI or Google embedding models.

Call the embeddings endpoint

Send text to the embeddings endpoint and store the returned vector in your vector database. Use the same model for indexing and searching.

Example

from openai import OpenAI

client = OpenAI(api_key="YOUR_TOKENREX_KEY", base_url="https://tokenrex.ai/api/public")
e = client.embeddings.create(model="text-embedding-3-small", input="TokenRex unified API")
print(len(e.data[0].embedding))

Get API key Cost calculator Docs

Questions

Do I need a separate key for each provider?: No. One TokenRex API key works for every enabled model; change only the model ID.

Related