## [Zyxel]Amazon Bedrock Workshop
- Date and Time : 2024/10/23 14:00 PM ~ 16:30 PM
- Short URL to this page ---> https://pse.is/6kk8uy <----
- Full URL to this page https://hackmd.io/@Kage/BJl3F1CJ1g
- AWS Attendee : SA: Kage Yang , BD: Max Yang

## Agenda
| Topics | Duration |
| ---------------------------------------- | -------- |
| Amazon Bedrock Introduction | 20 mins |
| Environment setup | 15 mins |
| Prompt Engineering | 10 mins |
| Text Generation | 30 mins |
| Break | 10 mins |
| KnowledgeBase and RAG | 30 mins |
| Agents | 30 mins |

## Lab Instructions ##
- #### Click this link to join the event : https://catalog.us-east-1.prod.workshops.aws/join?access-code=808f-0200d3-72

- #### Workshop Guide : https://catalog.workshops.aws/amazon-bedrock

# References
- Upgraded Claude 3.5 Sonnet from Anthropic (available now), computer use (public beta), and Claude 3.5 Haiku (coming soon) in Amazon Bedrock : https://aws.amazon.com/blogs/aws/upgraded-claude-3-5-sonnet-from-anthropic-available-now-computer-use-public-beta-and-claude-3-5-haiku-coming-soon-in-amazon-bedrock/
- Prompt Engineering with Anthropic's Claude 3 : https://catalog.us-east-1.prod.workshops.aws/workshops/0644c9e9-5b82-45f2-8835-3b5aa30b1848/en-US
- Prompt Engineering improvement :
1. https://aws.amazon.com/blogs/machine-learning/prompt-engineering-techniques-and-best-practices-learn-by-doing-with-anthropics-claude-3-on-amazon-bedrock/
2. https://aws.amazon.com/cn/blogs/china/sixteen-ways-of-prompt-engineering/

- Increase LLM response time :
1. https://aws.amazon.com/blogs/machine-learning/improve-llm-performance-with-human-and-ai-feedback-on-amazon-sagemaker-for-amazon-engineering/
2. https://aws.amazon.com/blogs/machine-learning/improve-llm-responses-in-rag-use-cases-by-interacting-with-the-user/
3. https://community.aws/content/2h2bFxVed2TfqVB3symJaJVZ5fk/streaming-a-response-from-bedrock-knowledge-base
4. https://aws.amazon.com/cn/blogs/china/implementing-claude3s-streaming-response-based-on-lambda/
5. https://community.aws/content/2gYtxK2HNy3bg4z68HJ1FM0OOuK/stream-amazon-bedrock-responses-for-a-more-responsive-ui
6. https://docs.aws.amazon.com/bedrock/latest/userguide/throughput.html

- RAG
1. https://aws.amazon.com/blogs/machine-learning/improve-rag-accuracy-with-fine-tuned-embedding-models-on-amazon-sagemaker/