Move over ChatGPT and OpenAI !!
AWS has new Generative AI service that’s going to give you a run for your money.
Amazon Bedrock is a fully managed service that makes leading foundation models from AI companies available through an API.
Just a couple of definitions to get us started:
Generative AI:
- Generative artificial intelligence (also generative AI or GenAI) is artificial intelligence capable of generating text, images, or other media, using generative models.Generative AI models learn the patterns and structure of their input training data and then generate new data that has similar characteristics.
Foundation Model:
- A foundation model is a large machine learning model, trained on a vast quantity of data at scale such that it can be adapted to a wide range of downstream tasks.
- An FM uses learned patterns and relationships to predict the next item in a sequence.
Foundation Models
Even though they are pre-trained, FMs can continue to learn from data inputs or prompts during inference. This means that you can develop comprehensive outputs through carefully curated prompts.
Tasks that FMs can perform include language processing, visual comprehension, code generation, and human-centered engagement.
Inference is the process of running live data through a trained AI model to make a prediction or solve a task.
Benefits of Amazon Bedrock:
- Choice of leading foundation models
- Easy model customization with your data
- Fully managed agents that dynamically invoke APIs to execute tasks
With Amazon Bedrock, you can explore the following capabilities:
- Text playground – A hands-on text generation application in the AWS Management Console.
- Image playground – A hands-on image generation application in the console.
- Chat playground – A hands-on conversation generation application in the console.
- Examples library – A user interface where you can review models with their descriptions, and load them, with a preselected example, directly into a playground to review and test them.
- Amazon Bedrock API – Explore with the AWS CLI, or use the API to access the base models. Can be easily integrated into software apps using the Python Boto3 library.
Supported models in Amazon Bedrock
Amazon Bedrock supports models from the following providers:
- AI21 Labs
- Amazon
- Anthropic
- Cohere
- Meta
- Stability.ai
You can use the console playgrounds to experiment with a model.
Depending on the model, you can use models with on-demand throughput or provisioned throughput.
In your applications, you can use the Amazon Bedrock API to make inference calls to a model.
Playgrounds
Amazon Bedrock offers easy access to a choice of high-performing foundation models from leading AI companies, including AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon.
Before you can use any of the foundation models, you must request access to that model. If you try to use the model (with the API or within the console) before you have requested access to it, you will receive an error message.
The Amazon Bedrock console playgrounds are where you can experiment with models before deciding to use them in an application.
In the console, access the playgrounds by choosing Playgrounds in the left navigation pane. You can also navigate directly to the playground when you choose a model from a model details page or the examples page.
There are playgrounds for:
- Text
- Chat
- Images
Within each playground you can enter prompts and experiment with inference parameters. Prompts are usually one or more sentences of text that set up a scenario, question, or task for a model.
Inference parameters influence the response generated by a model, such as the randomness of generated text. When you load a model into a playground, the playground configures the model with its default inference settings.
When you submit a response, the model responds with its generated output.
To learn more about Amazon Bedrock, click the link below to head over to my course on Udemy!
Amazon Bedrock: Generative AI with Python
