Skip to main content

Google / VertexAI Gemini Pro

Vertex AI Gemini Pro is a powerful large language model (LLM) by Google, accessible through their Vertex AI platform. It excels in various tasks like text generation, translation, and code analysis, making it a versatile tool for developers and businesses.

Getting started with Google / VertexAI Gemini Pro LLMs

  1. Vertex AI is provided by Google Cloud Platform.Navigate to Google Cloud Platform and signup using google account.

  2. Create an Organization and first project. Click on the APIs and services from quick access.

    img Gemini Pro LLM

  3. Click on ENABLE APIS AND SERVICES

    img Gemini Pro LLM

  4. Search for Vertex AI API and click on the search result.

    img Gemini Pro LLM

  5. Now Enable the 'Vertex AI API'.

    img Gemini Pro LLM

  6. select Credentials 🞂 Create Credentials 🞂 Service Account.

    img Gemini Pro LLM

  7. Create the Service Account as shown below.

    img Gemini Pro LLM

    img Gemini Pro LLM

    img Gemini Pro LLM

  8. Click on the created Service Account link.

    img Gemini Pro LLM

  9. Create the Key in json format as shown below.

    img Gemini Pro LLM

Setting up the Google / VertexAI Gemini Pro connector in Unstract

Now that we have all the required details, we can use it to set up an LLM profile on the Unstract platform. For this:

  • Sign in to the Unstract Platform

  • From the side navigation menu, choose Settings 🞂 LLMs

  • Click on the New LLM Profile button.

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

    img Anyscale Configuration

  • For Name, enter a name for this connector.

  • In Credentialsfield, paste in the whole downloaded service account key we copied from the text editor earlier.

  • For Models field,enter gemini-1.5-pro.For more models refer to Gemini Models.

  • For Max output tokens,enter 8192. For more models and its token limit refer to Gemini Models.

  • For Project, enter the Google project name in which the Vertex AI is enabled (or) Check the project_id in credentials json.

  • Leave Max Retries value to its default.

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