AWS wellarchitected documentation change
Summary
Added definitions for generative AI terms: Chunking, Data management, Embedding, Indexing, Model customization, Model gateway, Model hub, Model orchestration, and Pre-Training.
Security assessment
Changes are purely definitional additions for generative AI concepts. No security context, vulnerabilities, or security features are mentioned in the added content.
Diff
diff --git a/wellarchitected/latest/generative-ai-lens/definitions.md b/wellarchitected/latest/generative-ai-lens/definitions.md index 370ceebff..239f9aa96 100644 --- a//wellarchitected/latest/generative-ai-lens/definitions.md +++ b//wellarchitected/latest/generative-ai-lens/definitions.md @@ -12,0 +13,6 @@ + * **Chunking:** Breaking up large data files into small, discreet chunks to allow the foundation model to fit that data into a context window. + + * **Data management:** The process of identifying, collecting, storing, aggregating, searching, tracking, governing, and using data. + + * **Embedding:** Transforms chunks of data into vectors that represent semantic meaning. + @@ -24,0 +31,2 @@ + * **Indexing:** Process of inserting embedded chunks into a vector data store. + @@ -30,0 +39,2 @@ + * **Model customization:** The process of modifying a foundation model using various techniques to control its behavior. + @@ -34,0 +45,4 @@ + * **Model gateway:** An interaction layer offering secure access to the model hub through standardized APIs. + + * **Model hub:** A central repository providing access to enterprise foundation models from first-party, third-party, and open-source providers. + @@ -36,0 +51,4 @@ + * **Model orchestration:** Encapsulation of multistep workflows which are characteristic of generative AI workflows. + + * **Pre-Training:** Building a foundation model from scratch. Requires GPU clusters to run continuously for weeks. +