Amazon Bedrock FAQs changed AWS, Feb 4, 2025

1. +Added: Amazon Bedrock customers can choose from some of the most cutting-edge FMs available today. Currently we offer 47 models. This includes language and embeddings models from:
2. +Added: AI21: Jamba 1.5 Large, Jamba 1.5 Mini, Jamba-Instruct, Jurassic-2 Mid, Jurassic-2 Ultra
3. +Added: Anthropic: Claude 3.5 Sonnet, Claude 3.5 Haiku, Claude 3 Opus, Claude 3 Haiku, Claude 3 Sonnet, Claude 2.1, Claude 2.0, Claude Instant
4. +Added: Cohere: Command R+, Command R, Command, Command Light, Embed - English, Embed - Multilingual
5. +Added: Meta: Llama 3.2 90B, Llama 3.2 11B, Llama 3.2 3B, Llama 3.2 1B, Llama 3.1 8B, Llama 3.1 70B, Llama 3.1 405B, Llama 3 8B, Llama 3 70B, Llama 2 13B, Llama 2 70B
6. +Added: Mistral AI: Mistral Large 2 (24.07), Mistral Large (24.02), Mistral Small (24.02), Mixtral 8x7B, Mistral 7B
7. +Added: Stability AI: Stable Image Ultra, Stable Diffusion 3 Large, Stable Image Core, Stable Diffusion XL 1.0
8. +Added: Amazon: Amazon Titan Text Premier, Amazon Titan Text Express, Amazon Titan Text Lite, Amazon Titan Text Embeddings, Amazon Titan Text Embeddings V2, Amazon Titan Multimodal Embeddings, Amazon Titan Image Generator, Amazon Titan Image Generator v2
9. -Removed: Amazon Bedrock customers can choose from some of the most cutting-edge FMs available today. This includes language and embeddings models from:
10. -Removed: AI21 Labs : Jurassic - 2 Ultra, Jurassic - 2 Mid
11. -Removed: Anthropic : Claude 3 Opus, Claude 3 Sonnet, Claude 3 Haiku
12. -Removed: Cohere : Command R, Command R+, Embed
13. -Removed: Meta : Llama 3 8B, Llama 3 70B
14. -Removed: Mistral AI : Mistral 8X7B Instruct, Mistral 7B Instruct, Mistral Large, Mistral Small
15. -Removed: Stability AI : Stable Diffusion XL 1.0
16. -Removed: Amazon Titan : Amazon Titan Text Premier, Amazon Titan Text Express, Amazon Titan Text Lite, Amazon Titan Text Embeddings, Amazon Titan Text Embeddings V2, Amazon Titan Multimodal Embeddings, Amazon Titan Image Generator
17. +Added: What is latency-optimized inference in Amazon Bedrock?
18. +Added: Available in public preview, latency-optimized inference in Amazon Bedrock offers reduced latency without compromising accuracy. As verified by Anthropic, with latency-optimized inference on Amazon Bedrock, Claude 3.5 Haiku runs faster on AWS than anywhere else. Additionally, with latency-optimized inference in Bedrock, Llama 3.1 70B and 405B runs faster on AWS than any other major cloud provider. Using purpose-built AI chips like AWS Trainium2 and advanced software optimizations in Amazon Bedrock, customers can access more options to optimize their inference for a particular use case.
19. +Added: Supported Models : Anthropic's Claude 3.5 Haiku and Meta's Llama 3.1 models 405B and 70B
20. +Added: Availability : The US East (Ohio) Region via cross-region inference
21. +Added: To get started, visit the Amazon Bedrock console . For more information visit the Amazon Bedrock documentation .
22. +Added: How do we get started with latency-optimized inference in Amazon Bedrock?
23. +Added: Accessing the latency-optimized inference in Amazon Bedrock requires no additional setup or model fine-tuning, allowing for immediate enhancement of existing generative AI applications with faster response times. You can toggle on the "Latency optimized" parameter while invoking the Bedrock inference API.
24. +Added: Will AWS and third-party model providers use customer inputs to or outputs from Amazon Bedrock to train Amazon Nova, Amazon Titan or any third-party models?
25. +Added: No, AWS and the third-party model providers will not use any inputs to or outputs from Amazon Bedrock to train Amazon Nova, Amazon Titan, or any third-party models.
26. -Removed: Will AWS and third-party model providers use customer inputs to or outputs from Amazon Bedrock to train Amazon Titan or any third-party models?
27. -Removed: No, AWS and the third-party model providers will not use any inputs to or outputs from Amazon Bedrock to train Amazon Titan or any third-party models.
28. +Added: Why do I see a billing entry for AWS Marketplace for my usage of AWS Bedrock?
29. +Added: Customers will see an AWS Marketplace bill for certain Bedrock serverless models and Bedrock Marketplace models. This is because these models are sold by third party providers as "Third-Party Content", as described in the AWS service terms section 50.12.
30. +Added: Which data sources can I connect to Amazon Bedrock Knowledge Bases?
31. +Added: You can ingest content from various sources, including the web, Amazon Simple Storage Service (Amazon S3), Confluence (preview), Salesforce (preview), and SharePoint (preview). You can also programmatically ingest streaming data or data from unsupported sources. You can also connect to your structured data sources such as Redshift datawarehouse and AWS Glue data catalog.
32. +Added: How does Amazon Bedrock Knowledge Base retrieve data from structured data sources?
33. +Added: Amazon Bedrock Knowledge Bases provides a managed Natural Language to SQL to convert natural language into actionable SQL queries and retrieve data, allowing you to build application using data from these sources.
34. +Added: Does Amazon Bedrock Knowledge Bases support multi-turn conversations?
35. +Added: Yes, session context management is built-in, allowing your applications to maintain context across multiple interactions, which is essential for supporting multi-turn conversations.
36. +Added: Does Amazon Bedrock Knowledge Bases provide source attribution for retrieved information?
37. +Added: Yes, all information retrieved includes citations, improving transparency and minimizing the risk of hallucinations in the generated responses.
38. +Added: What multi-modal capabilities does Amazon Bedrock Knowledge Bases offer?
39. +Added: Amazon Bedrock Knowledge Bases supports multi-modal data processing, allowing developers to build generative AI applications that analyze both text and visual data, including images, charts, diagrams, and tables. Model responses can leverage insights from visual elements in addition to text, providing. more accurate and contextually relevant answers. Additionally, source attribution for responses includes visual elements, enhancing transparency and trust in the responses.
40. +Added: What multi-modal data formats does Amazon Bedrock Knowledge Bases support?
41. +Added: Amazon Bedrock Knowledge Bases can process visually rich documents in PDF format, which may contain images, tables, charts, and diagrams. For image-only data, Bedrock Knowledge Bases supports standard image formats like JPEG and PNG, enabling search capabilities where users can retrieve relevant images based on text-based queries.
42. +Added: What are the different parsing options available in Amazon Bedrock Knowledge Bases?
43. +Added: Customers have three parsing options for Bedrock Knowledge Bases. For text-only processing, the built-in default Bedrock parser is available at no additional cost, ideal for cases where multimodal data processing is not required. Amazon Bedrock Data Automation (BDA) or foundation models can be used to parse multimodal data. For more information, refer to the product documentation .
44. +Added: How does Amazon Bedrock Knowledge Bases ensure data security and manage workflow complexities?
45. +Added: Amazon Bedrock Knowledge Base handles various workflow complexities such as content comparison, failure handling, throughput control, and encryption, ensuring that your data is securely processed and managed according to AWS's stringent security standards.
46. -Removed: What types of data formats are accepted by Amazon Bedrock Knowledge Bases?
47. -Removed: Supported data formats include .pdf, .txt, .md, .html, .doc and .docx, .csv, .xls, and .xlsx files. Files must be uploaded to Amazon S3. Point to the location of your data in Amazon S3, and Amazon Bedrock Knowledge Bases takes care of the entire ingestion workflow into your vector database.
48. -Removed: How does Amazon Bedrock Knowledge Bases chunk the documents before converting those chunks to embeddings?
49. -Removed: Amazon Bedrock Knowledge Bases provides three options to chunk text before converting it to embeddings.
50. -Removed: 1. Default option: Amazon Bedrock Knowledge Bases automatically splits your document into chunks each containing 200 tokens, ensuring that a sentence is not broken in the middle. If a document contains less than 200 tokens, then it is not split any further. An overlap of 20% of tokens is maintained between two consecutive chunks.
51. -Removed: 2. Fixed size chunking: In this option, you can specify the maximum number of tokens per chunk and the overlap percentage between chunks for Amazon Bedrock Knowledge Bases, so your document will be automatically split into chunks, ensuring that a sentence is not broken in the middle.
52. -Removed: 3. Create one embedding per document option: Amazon Bedrock creates one embedding per document. This option is suitable if you have preprocessed your documents by splitting them into separate files and do not want Amazon Bedrock to further chunk your documents.
53. -Removed: Which embeddings model is used to convert documents into embeddings (vectors)?
54. -Removed: At present, Amazon Bedrock Knowledge Bases uses the latest version of the Amazon Titan Text Embeddings model available in Amazon Bedrock. Titan Text Embeddings V2 model supports 8K tokens and 100+ languages and creates an embeddings of flexible 256, 512, and 1,024 dimension size.
55. -Removed: Which vector databases are supported by Amazon Bedrock Knowledge Bases?
56. -Removed: Amazon Bedrock Knowledge Bases takes care of the entire ingestion workflow of converting your documents into embeddings (vector) and storing the embeddings in a specialized vector database. Amazon Bedrock Knowledge Bases supports popular databases for vector storage, including vector engine for Amazon OpenSearch Serverless, Pinecone, Redis Enterprise Cloud, Amazon Aurora (coming soon), and MongoDB (coming soon). If you do not have an existing vector database, Amazon Bedrock creates an OpenSearch Serverless vector store for you.
57. -Removed: Is it possible to do a periodic or event-driven sync from Amazon S3 to Amazon Bedrock Knowledge Bases?
58. -Removed: Depending on your use case, you can use Amazon EventBridge to create a periodic or event-driven sync between Amazon S3 and Amazon Bedrock Knowledge Bases.
59. +Added: Contextual grounding checks: help detect and filter hallucinations if the responses are not grounded (e.g., factually inaccurate or new information) in the source information and irrelevant to user's query or instruction.
60. +Added: Automated Reasoning checks: help detect factual inaccuracies in generated content, suggest corrections, and explain why responses are accurate by checking against a structured, mathematical representation of knowledge called an Automated Reasoning Policy.

87 more changed paragraphs are on the page itself.