Skip to content

Latest commit

 

History

History
 
 

12_bedrock

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
archive
archive
 
 
data
data
 
 
emails
emails
 
 
images
images
 
 
letters
letters
 
 
rag_data
rag_data
 
 
utils
utils
 
 
.gitignore
.gitignore
 
 
.gitkeep
.gitkeep
 
 
01_bedrock_overview.ipynb
01_bedrock_overview.ipynb
 
 
02_small_text_summarization_titan.ipynb
02_small_text_summarization_titan.ipynb
 
 
03_long_text_summarization_titan.ipynb
03_long_text_summarization_titan.ipynb
 
 
04_chatbot_titan.ipynb
04_chatbot_titan.ipynb
 
 
05_assistant_titan.ipynb
05_assistant_titan.ipynb
 
 
06_extract_entities_claude.ipynb
06_extract_entities_claude.ipynb
 
 
07_generate_images_stable_diffusion.ipynb
07_generate_images_stable_diffusion.ipynb
 
 
08_generate_embeddings_titan.ipynb
08_generate_embeddings_titan.ipynb
 
 
09_semantic_search_titan_embeddings_claude.ipynb
09_semantic_search_titan_embeddings_claude.ipynb
 
 
10_semantic_search_w_metadata_filtering_faiss_claude.ipynb
10_semantic_search_w_metadata_filtering_faiss_claude.ipynb
 
 
11_semantic_search_w_metadata_filtering_faiss_titan.ipynb
11_semantic_search_w_metadata_filtering_faiss_titan.ipynb
 
 
12_summaries_llamaindex_bedrock_claude.ipynb
12_summaries_llamaindex_bedrock_claude.ipynb
 
 
13_summaries_llamaindex_bedrock_titan.ipynb
13_summaries_llamaindex_bedrock_titan.ipynb
 
 
14_llamaindex_reranker_bedrock_claude.ipynb
14_llamaindex_reranker_bedrock_claude.ipynb
 
 
15_llamaindex_reranker_bedrock_titan.ipynb
15_llamaindex_reranker_bedrock_titan.ipynb
 
 
16_opensearch_serverless_titan_embeddings_claude.ipynb
16_opensearch_serverless_titan_embeddings_claude.ipynb
 
 
17_pinecone_titan_embeddings_claude.ipynb
17_pinecone_titan_embeddings_claude.ipynb
 
 
18_generate_code_claude.ipynb
18_generate_code_claude.ipynb
 
 
19_generate_sql_query_claude.ipynb
19_generate_sql_query_claude.ipynb
 
 
20_interpret_code_langchain_claude.ipynb
20_interpret_code_langchain_claude.ipynb
 
 
21_translate_code_langchain_claude.ipynb
21_translate_code_langchain_claude.ipynb
 
 
22_chatbot_llama2.ipynb
22_chatbot_llama2.ipynb
 
 
23_assistant_llama2.ipynb
23_assistant_llama2.ipynb
 
 
24_finetune_titan_classification.ipynb
24_finetune_titan_classification.ipynb
 
 
25_finetune_titan_summarization.ipynb
25_finetune_titan_summarization.ipynb
 
 
26_finetune_titan_question_answer.ipynb
26_finetune_titan_question_answer.ipynb
 
 
27_finetune_llama2_summarization.ipynb
27_finetune_llama2_summarization.ipynb
 
 
28_finetune_llama2_question_answer.ipynb
28_finetune_llama2_question_answer.ipynb
 
 
29_finetune_cohere_summarization.ipynb
29_finetune_cohere_summarization.ipynb
 
 
30_finetune_cohere_question_answer.ipynb
30_finetune_cohere_question_answer.ipynb
 
 
31_continued_pretrainining_titan_shareholder_pdf.ipynb
31_continued_pretrainining_titan_shareholder_pdf.ipynb
 
 
32_continued_pretrainining_titan_oreilly_pdf.ipynb
32_continued_pretrainining_titan_oreilly_pdf.ipynb
 
 
33_multimodal_titan_image_generator.ipynb
33_multimodal_titan_image_generator.ipynb
 
 
34_multimodal_titan_embedding.ipynb
34_multimodal_titan_embedding.ipynb
 
 
README.md
README.md
 
 
converted-to-mountains.png
converted-to-mountains.png
 
 
converted.png
converted.png
 
 
generated_image-.png
generated_image-.png
 
 
generated_image.png
generated_image.png
 
 
insurance_claim_schema.json
insurance_claim_schema.json
 
 
lambda-handler.py
lambda-handler.py
 
 
sales.csv
sales.csv
 
 
upscaled-to-8k.png
upscaled-to-8k.png
 
 

README.md

Chapter 12: Amazon Bedrock: Managed Service for Generative AI

Questions and Answers

Q: What are the key features of Amazon Bedrock for Generative AI?

A: Amazon Bedrock for Generative AI offers features such as retrieval-augmented generation, semantic-search, and agent-based use cases. It supports foundation models from Amazon and various third-party companies, which can be accessed through the AWS Console, CLI, or SDK. It allows for private customization of these foundation models using custom datasets.

Q: What are the benefits of using large language models such as Amazon Titan, Anthropic Claude, Cohere Command, Meta Llama2, and AI21 Jurassic within Amazon Bedrock?

A: Large language models within Amazon Bedrock offer benefits such as advanced text generation and processing capabilities, which can be leveraged for tasks like generating SQL code, summarizing text, and creating embeddings. They are accessible for various generative AI applications and can be utilized through Bedrock's managed services and APIs.

Q: What is the role of multimodal foundation models such as Stable Diffusion in Amazon Bedrock?

A: Stable Diffusion foundation models in Amazon Bedrock are used to generate unique, realistic, high-quality images, art, logos, and designs from text-based prompts. They play a critical role in multimodal content generation within the Bedrock ecosystem.

Q: How do Bedrock Inference APIs enhance Generative AI applications?

A: Bedrock Inference APIs enhance Generative AI applications by enabling content generation using text-to-text models, text-to-image models, and embedding models. These APIs facilitate the integration of generative AI capabilities into various applications.

Q: What are the key considerations in fine-tuning models within Amazon Bedrock?

A: Key considerations in fine-tuning models within Amazon Bedrock include ensuring data privacy, using secure access methods, and customizing models for specific use cases. Fine-tuning involves configuring model inputs and outputs to remain private and secure within the user's environment.

Q: What are the data privacy and network security mechanisms in Amazon Bedrock?

A: Amazon Bedrock's data privacy and network security measures include data isolation per AWS customer, encryption in transit and at rest, and secure connectivity via AWS VPC Endpoints. It adheres to GDPR and other data sovereignty regulations.

Q: How does Amazon Bedrock ensure effective governance and monitoring of Generative AI models?

A: Amazon Bedrock ensures effective governance and monitoring of Generative AI models by tracking API activity and metrics using AWS CloudTrail and Amazon CloudWatch. This enables monitoring of model usage and performance within the user's AWS account.

Chapters

  • Chapter 1 - Generative AI Use Cases, Fundamentals, Project Lifecycle
  • Chapter 2 - Prompt Engineering and In-Context Learning
  • Chapter 3 - Large-Language Foundation Models
  • Chapter 4 - Quantization and Distributed Computing
  • Chapter 5 - Fine-Tuning and Evaluation
  • Chapter 6 - Parameter-efficient Fine Tuning (PEFT)
  • Chapter 7 - Fine-tuning using Reinforcement Learning with RLHF
  • Chapter 8 - Optimize and Deploy Generative AI Applications
  • Chapter 9 - Retrieval Augmented Generation (RAG) and Agents
  • Chapter 10 - Multimodal Foundation Models
  • Chapter 11 - Controlled Generation and Fine-Tuning with Stable Diffusion
  • Chapter 12 - Amazon Bedrock Managed Service for Generative AI

Related Resources