Gemini · Create embeddings — Turns text into vectors, for search and matching — on your company's own Google Gemini key. Store the vectors beside your records, then compare them to find the closest match: the product a customer means, or the help article that answers a question.

Who can do this

Workspace Admins and Editors, on every plan.

Before you start

A Google Gemini connection in Connections — see Connect Google Gemini.

Steps

  1. Select + where the vectors should be made. In the step picker, open AI, then Gemini, and select Create embeddings.
  2. In Connection, choose the connection with your key.
  3. Optional: in Model, choose one from the list read from Google. Left empty, the step uses Gemini's current embedding model.
  4. In Text, a text with values in {{ }} — {{ $json.description }} — or a list of texts from an earlier step, up to 512. Each text gets its own vector, in order.
  5. Select Run this step.

Output

One item, whatever the number of texts: count, dimensions (the length of each vector), embeddings (one list of numbers per text, in order), first (the first vector) and usage — model and seconds. Output shows usage as the usage strip.

Good to know

  • Keep one model for one set of vectors. Vectors from different models cannot be compared.
  • A long list is sent to Gemini in parts of 100 texts, and still comes back as one item.
  • Each item is a separate call. Pin the output while you build — see Pin a step's output.

If something goes wrong

What the run says Why What to do
Google Gemini refused: … Check the connection's details on Connections. The key is wrong or revoked. Replace the key on Connections.
Google Gemini refused: … Gemini refused the request — a text too long for the model, a model that does not make embeddings, or a rate limit. It is not tried again. Read Gemini's reason; choose a model from the list.
Text is empty when the step ran — an earlier step may not have given the value it names. Text came out empty. Check the value in Data from earlier steps.
Text holds … texts; one step takes up to 512. Split the list first. The list is too long. Split it, or send fewer — see Repeat steps for each item with Loop Over Items.
Could not reach Google Gemini: … / Google Gemini did not answer within 5 minutes. Gemini did not answer. Try again; set If this step fails to try again.