Amazon Bedrock

• AI platform for enterprises to build, use, and customize AI models.
• Offers a catalog of foundation models, implements retrieval-augmented generation (RAG) and vector embeddings, hosts knowledge bases, implements fine-tuning of foundation models, and allows continued pre-training of selected foundation models, along with a broad set of capabilities you need to build generative AI applications with security, privacy, and responsible AI. 
• Use the API or GUI in the console to test various prompts and configurations with different foundation models.
• Improves response generation by incorporating external data sources into knowledge bases, which can be queried to augment the responses from foundation models.
• Develops customer support applications, customizes models, and boosts application efficiency. (credit)

‍

• A wide variety of AI models to use (33) and three different playgrounds to play around in!
• Complements the almost 30 other Amazon machine learning services available, including Amazon Q, the AWS generative AI assistant

‍

• You need to request access to models before you can use them
• Requires an extra prompt “Let’s think step by step.” Without that line, the model often goes off the rails and generates a wrong answer.

‍