Generative AI - Getting Started with PaLM 2
Learn how to get started with Generative AI and PaLm2 on Vertex AI
The Vertex AI PaLM API is a Google Cloud service that enables the usage and training of generative models.
Let me first remove some of the confusion. Generative AI Studio is a feature of Vertex AI. And it indeed provides access to PaLM 2 via the Vertex AI PaLM API, which is part of Generative AI Studio.
Models
The PaLM API provides 3 foundation models:
- Text for natural language instructions
- Chat for conversations
- Embedding for creating embeddings based on text
Different PaLM 2 model sizes are available. Vertex AI PaLM API supports Gecko for Embeddings and Bison and Unicorn for Text and Chat.
The models are particularly good at creating and understanding our language for a wide set of different tasks.
The Bison model is approx half the price of the GPT-3 Open AI) as of May 2023.
Use the Vertex AI PaLM API
Google provides access to PaLM 2 via the Vertex AI SDK. Install it with pip install google-cloud-aiplatform
make sure you’re running on at last version 1.25.0
.