AWS Security ChangesHomeSearch

AWS prescriptive-guidance documentation change

Service: prescriptive-guidance · 2026-07-10 · Documentation low

File: prescriptive-guidance/latest/rag-healthcare-use-cases/case-1.md

Summary

Updated image paths and made minor text edits including table formatting (bold headers), section title simplifications, and added asterisks for emphasis.

Security assessment

Changes involve image path updates and non-substantive text formatting. No security vulnerabilities, features, or protocols are mentioned or modified. Healthcare context doesn't inherently imply security changes without explicit evidence.

Diff

diff --git a/prescriptive-guidance/latest/rag-healthcare-use-cases/case-1.md b/prescriptive-guidance/latest/rag-healthcare-use-cases/case-1.md
index 33a41c7d1..a835a8373 100644
--- a//prescriptive-guidance/latest/rag-healthcare-use-cases/case-1.md
+++ b//prescriptive-guidance/latest/rag-healthcare-use-cases/case-1.md
@@ -23 +23 @@ The following image shows the end-to-end-workflow for this solution. It uses Ama
-![Using AWS services and an LLM to generate answers to medical questions.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/enterprise-cognitive-brain.png)
+![Using AWS services and an LLM to generate answers to medical questions.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/44ed1e86-b968-4bc3-b9e5-255603e2f265.png)
@@ -79 +79 @@ The following figure shows the entity extraction and schema validation steps to
-![Workflow for entity extraction and schema validation.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/entity-extraction-schema-validation.png)
+![Workflow for entity extraction and schema validation.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/a1ef23cf-b2e4-4a65-9fb7-a11bffd5b63d.png)
@@ -83 +83 @@ After extraction and validation of the entities, relations, and attributes, you
-![Medical knowledge graph that maps entities to their attributes.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/entity-attribute-mapping.png)
+![Medical knowledge graph that maps entities to their attributes.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/bc42faae-6a01-42aa-b850-ddb3e54f0196.png)
@@ -89 +89 @@ The following tables lists the entities and their attributes that you might extr
-Entity | Attributes  
+**Entity**| **Attributes**  
@@ -109 +109 @@ The following table lists the relationships that entities might have and their c
-Subject entity | Relationship | Object entity | Attributes  
+**Subject entity**| **Relationship**| **Object entity**| **Attributes**  
@@ -128 +128 @@ Subject entity | Relationship | Object entity | Attributes
-## Step 3: Building context retrieval agents to query the medical knowledge graph
+## Step 3: Building context retrieval agents
@@ -164 +164 @@ The following image shows how Amazon Bedrock agents interact with Amazon Neptune
-![Integration of Amazon Bedrock agents with Amazon Neptune.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/bedrock-agents-neptune.png)
+![Integration of Amazon Bedrock agents with Amazon Neptune.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/d39a91c1-c07e-435e-93b9-dd2ec660cc42.png)
@@ -187 +187 @@ The diagram shows the following workflow:
-You can integrate LangChain with Neptune to enable graph-based queries and retrievals. This approach can enhance AI-driven workflows by using the graph database capabilities in Neptune. The custom LangChain retriever acts as an intermediary. The foundational model in Amazon Bedrock can interact with Neptune by using both direct Cypher queries and more complex graph algorithms.
+You can integrate LangChain with Neptune to enable graph-based queries and retrievals. This approach can enhance AI-driven workflows by using the graph database capabilities in Neptune.**** The custom LangChain retriever acts as an intermediary. The foundational model in Amazon Bedrock can interact with Neptune by using both direct Cypher queries and more complex graph algorithms.
@@ -189 +189 @@ You can integrate LangChain with Neptune to enable graph-based queries and retri
-You can use the custom retriever to refine how the LangChain agent interacts with the Neptune graph algorithms. For example, you can use few-shot prompting, which helps you tailor the foundation model's responses based on specific patterns or examples. You can also apply LLM-identified filters to refine the context and improve the precision of responses. This can improve the efficiency and accuracy of the overall retrieval process when interacting with complex graph data.
+You can use the custom retriever to refine how the LangChain agent interacts with the Neptune graph algorithms. For example, you can use few-shot prompting, which helps you tailor the foundation model's responses based on specific patterns or examples. You can also apply**** LLM-identified filters to refine the context and improve the precision of responses. This can improve the efficiency and accuracy of the overall retrieval process when interacting with complex graph data.
@@ -193 +193 @@ The following image shows how a custom LangChain agent orchestrates the interact
-![Integration of a LangChain question-answering agent with Amazon Neptune.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/langchain-agents-neptune.png)
+![Integration of a LangChain question-answering agent with Amazon Neptune.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/b621461a-d9e5-4cc6-9814-d80f845a1f6c.png)
@@ -210 +210 @@ The diagram shows the following workflow:
-## Step 4: Creating a knowledge base of real-time, descriptive data
+## Step 4: Creating a knowledge base
@@ -226 +226 @@ You can deploy a customized RAG solution that uses Amazon Bedrock agents to quer
-![Integration of Amazon Bedrock agents with a medical vector database on Amazon OpenSearch Service.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/bedrock-agents-opensearch.png)
+![Integration of Amazon Bedrock agents with a medical vector database on Amazon OpenSearch Service.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/7730d773-f293-49ad-a585-3ddb1090a3e4.png)
@@ -249 +249 @@ For situations where more complex filtering is involved, you can use a custom La
-![Integration of a LangChain retriever agent with a medical vector database on OpenSearch Service.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/bedrock-langchain-opensearch.png)
+![Integration of a LangChain retriever agent with a medical vector database on OpenSearch Service.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/1ad21cb9-4e76-40d6-80b4-d7d87da06b02.png)
@@ -268 +268 @@ The diagram shows the following workflow:
-## Step 5: Using LLMs to answer medical questions
+## Step 5: Generating responses
@@ -274 +274 @@ When a clinician inputs a query, the _context retrieval layer_ of the applicatio
-![Using AWS services and an LLM to generate answers to medical questions.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/enterprise-cognitive-brain.png)
+![Using AWS services and an LLM to generate answers to medical questions.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/b8419088-f441-4561-adb8-30d20b2e0390.png)