Amazon Bedrock - Intro Flashcards

Introduction to amazon Bedrock (11 cards)

1
Q

What is Amazon Bedrock?

A

A fully managed service on AWS for building generative AI applications

It allows users to configure and interact with various models.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What does ‘fully managed service’ mean in the context of Amazon Bedrock?

A

Users do not need to manage the service; AWS handles it for them

Users focus only on using the service without worrying about underlying infrastructure.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

How does Amazon Bedrock ensure data security?

A

All data used for training models remains within the user’s AWS account and never leaves it

Users retain control over their data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is the pricing model for Amazon Bedrock?

A

Pay-per-use pricing model

Detailed pricing information is provided later.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is a unified API in Amazon Bedrock?

A

A standardized way to access Amazon Bedrock and its models

It simplifies interactions with various foundation models.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Name some companies that provide foundation models on Amazon Bedrock.

A
  • AI21 Labs
  • Cohere
  • Stability.ai
  • Amazon
  • Anthropic
  • Meta
  • Mitral AI

More companies and models may be added over time.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What happens when a model is used in Amazon Bedrock?

A

Amazon Bedrock makes a copy of the foundation model available only to the user

This allows for personalization without sharing data with model providers.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What does fine-tuning a foundation model mean?

A

Using personal data to adapt the model to specific user needs

This customization helps improve the model’s relevance to the user’s use case.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is RAG in the context of Amazon Bedrock?

A

Refers to retrieval-augmented generation, which fetches data from external sources for more accurate responses

This feature enhances the quality of answers provided by the model.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is the interactive playground in Amazon Bedrock?

A

A feature that allows users to select models and interact with them by asking questions

It provides a hands-on experience with the models.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

True or False: Data used to train models in Amazon Bedrock is shared with third-party providers.

A

False

Data remains within the user’s account and is not sent back to model providers.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly