Skip to main content

Palm Embeddings

Palm embedding is a technique that converts text into numerical vectors, capturing meaning and context. Similar text snippets have close embeddings, allowing for tasks like semantic search and text classification.

Getting started with PALM Embedding​

  1. To get the PALM API key, navigate to PALM API setup page

  2. Click on Get an API Key and sign in using google account.

    img Palm Embeddings Configuration

  3. Create an API key for the existing project or new project.

    img Palm Embeddings Configuration

    img Palm Embeddings Configuration

Setting up the PALM Embedding model in Unstract​

Now that we have an API key from PALM, we can use it to set up an Embedding profile on the Unstract platform. For this:

  • Sign in to the Unstract Platform

  • From the side navigation menu, choose Settings 🞂 Embedding

  • Click on the New Embedding Profile button.

  • From the list of Embeddings, choose PALM. You should see a dialog box where you enter details.

    img Palm Embeddings Configuration

  • For Name,enter a name for this connector.

  • In the Model Name enter the PALM model which supports embedding prefixed with 'models/'.For eg "models/embedding-gecko-001". To get the PALM model names, refer PALM Models Section

  • In the API Key field, paste the API key we created on the PALM website.

  • Leave the Embed Batch Size field to the default value.

  • Click on Test Connection and ensure it succeeds. You can finally click on Submit and that should create a new Embedding Profile for use in your Unstract projects.