Merge branch 'main' into dependabot/maven/app-dev/devops-and-containers/functions/java-basic-authorizer-apigw-fn-example/files/fn-authorizer-auth-basic/junit-junit-4.13.1

Author: AlexanderHodicke

ai-data-strategy/enablement-assets/README.md

@@ -0,0 +1,2 @@
+# Enablement Asssets 
+AI and Data Strategy enablement presentations 

ai/ai-ecosystem/README.md

@@ -1,9 +1,9 @@
 # Generative AI Ecosystem
 
-Reviewed: 02.07.2025
+Reviewed: 16.10.2025
 
 # Team Publications
 
 ## GitHub
 
-- [NVIDIA Omniverse Digital Twin](https://github.com/oracle-devrel/technology-engineering/tree/main/ai/ai-ecosystem/nvidia-omniverse-digital-twin)
+- [NVIDIA Omniverse Digital Twin](./nvidia-omniverse-digital-twin) demonstrates how to deploy an Omniverse digital twin on OCI

ai/ai-ecosystem/nvidia-omniverse-digital-twin/README.md

@@ -8,7 +8,7 @@ nodes on Oracle Cloud Infrastructure (OCI) to visualize the airflow over the
 car as well as AI inference to quickly assess how changes to the car will
 affect the airflow.
 
-Reviewed: 02.07.2025
+Reviewed: 16.10.2025
 
 # When to use this asset?
 
@@ -108,4 +108,4 @@ Copyright (c) 2025 Oracle and/or its affiliates.
 
 Licensed under the Universal Permissive License (UPL), Version 1.0.
 
-See [LICENSE](https://github.com/oracle-devrel/technology-engineering/blob/main/LICENSE) for more details.
+See [LICENSE](./LICENSE) for more details.

ai/ai-vision/README.md

@@ -25,7 +25,7 @@ Reviewed: 21.09.2025
 
 ## GitHub
 
-- [OCI object detection and image segmentation using SAM2](.ai-vision-and-sam/)
+- [OCI object detection and image segmentation using SAM2](./ai-vision-and-sam/)
 - [OCI image classification using data labeling and vision service](https://github.com/carlgira/oci-image-classification)
 - [OCI object detection using data labeling and vision service](https://github.com/carlgira/oci-object-detection) 
 - [AI vision web client](https://github.com/oracle-devrel/oci-tf-vision-web-client)

ai/gen-ai-agents/assistant-secretary-agent/files/local_requirements.txt

@@ -36,7 +36,7 @@ langchain==0.3.14
 langchain-community==0.3.14
 langchain-core==0.3.29
 langchain-experimental==0.3.4
-langchain-text-splitters==0.3.5
+langchain-text-splitters==0.3.9
 langgraph==0.2.62
 langgraph-checkpoint==2.0.8
 langgraph-sdk==0.1.51

ai/gen-ai-agents/custom-rag-agent/start_ui_mcp.sh

@@ -0,0 +1,2 @@
+streamlit run ui_mcp_agent.py
+

ai/gen-ai-agents/mcp-oci-integration/README.md

@@ -8,6 +8,10 @@ This repository contains code and examples to help in the following tasks:
 * **Integrate** MCP Servers with OCI **APM** for **Observability**
 * **how-to** create a **docker** image for your MCP server
 
+**Author**: L. Saetta
+
+**Reviewed**: 15.10.2025
+
 ![MCP console](./images/mcp_cli.png)
 
 ## What is MCP?
@@ -51,7 +55,7 @@ The code is available [here](./mcp_semantic_search_with_iam.py).
 
 Access to Oracle 23AI Vector Search is through the **new** [langchain-oci integration library](https://github.com/oracle/langchain-oracle)
 
-## Adding security
+## Adding Security
 If you want to put your **MCP** server in production, you need to add security, at several levels.
 
 Just to mention few important points:
@@ -84,4 +88,22 @@ An example is [here](./mcp_selectai.py)
 
 For **Select AI** configuration, see [here](./configure_select_ai.md)
 
+## OCI Consumption Analysis
+Another use case demonstrated in this set of demos is leveraging an AI Assistant powered by MCP servers to analyze the **OCI tenant consumption** in a natural and interactive way.
+
+Using the [MCP Consumption Server](./mcp_consumption.py), you can explore various dimensions of consumption and ask questions such as:
+* List the top 10 services by total amount for a given period (start_date, end_date).
+* List the top 10 compartments by total consumption.
+* For a specific service (or list of services), show the consumption breakdown across the top 5 compartments.
+
+The key advantage of this approach is that you don’t need to export or replicate data into a Data Warehouse (DWH) — all information is retrieved directly from the OCI Usage API in real time.
+
+How to Use:
+* Configure your OCI credentials.
+* Start the MCP Consumption Server
+* Launch the AI Assistant
+* Point the Assistant to the MCP URL (or to your MCP Aggregator).
+
+### Security (Optional)
+You can enhance security by placing the MCP server behind an OCI API Gateway and enabling JWT-based authentication using OCI IAM.
 

ai/gen-ai-agents/mcp-oci-integration/requirements.txt

@@ -6,7 +6,7 @@ annotated-types==0.7.0
 anyio==4.10.0
 astroid==3.3.11
 attrs==25.3.0
-Authlib==1.6.3
+Authlib==1.6.5
 black==25.1.0
 blinker==1.9.0
 cachetools==6.2.0

ai/gen-ai-agents/mcp-oci-integration/start_aggregator.sh

@@ -0,0 +1,2 @@
+python mcp_aggregator.py
+

ai/gen-ai-agents/mcp-oci-integration/start_mcp_consumption.sh

@@ -0,0 +1,2 @@
+python mcp_consumption.py --port 9500
+