Merge branch 'main' into RobertoRaspatella-patch-1

Author: AlexanderHodicke

.gitignore

@@ -44,3 +44,6 @@ terraform.rc
 # Exclude cached Python binary files
 *.pyc
 __pycache__
+
+desktop.ini
+

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "githubPullRequests.ignoredPullRequestBranches": [
+        "main"
+    ]
+}

ai/README.md

@@ -1,23 +1,26 @@
-# AI Services
+# OCI Generative AI and AI Services
 
-Oracle Cloud Infrastructure (OCI) AI Services, Generative AI Services and Generative AI Agents are a collection of services with prebuilt machine learning and Generative AI models that make it easy for developers to apply AI to applications and business processes. The models can be custom-trained (or fine-tuned) for more accurate business results. Teams within an organization can reuse the models, datasets, and data labels across services. OCI AI makes it possible for developers to easily add AI to applications without slowing down application development.
+Oracle Cloud Infrastructure (OCI) [Generative AI Service](https://docs.oracle.com/en-us/iaas/Content/generative-ai/overview.htm), [Generative AI Agents](https://docs.oracle.com/en-us/iaas/Content/generative-ai-agents/overview.htm) and [AI Services](https://www.oracle.com/uk/artificial-intelligence/ai-services/) are a collection of services with prebuilt machine learning and Generative AI models that make it easy for developers to apply AI to applications and business processes. The models can be custom-trained (or fine-tuned) for more accurate business results. Teams within an organization can reuse the models, datasets, and data labels across services. OCI AI makes it possible for developers to easily add AI to applications without slowing down application development.
 
-Reviewed: 03.06.2025
+Reviewed: 21.08.2025
 
 
 # Useful Links
 
 ## Examples and hands-on workshops
 - [AI Solutions Hub](https://www.oracle.com/artificial-intelligence/solutions/)
 - [Oracle LiveLabs](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/home)
+- [This repository](https://github.com/oracle-devrel/technology-engineering/tree/main/ai) and [Oracle-samples repository](https://github.com/oracle-samples/oci-data-science-ai-samples)
+- [Oracle Developer Coaching channel on Youtube](https://www.youtube.com/@oracledevs)
 
 ## Discover Oracle AI
-- [Oracle AI Services on Oracle.com](https://www.oracle.com/artificial-intelligence/ai-services/)
+- [Oracle AI on Oracle.com](https://www.oracle.com/artificial-intelligence/)
 - [Oracle Generative AI on Oracle.com](https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/)
-- [Oracle AI Strategy and Platform webinar](https://go.oracle.com/LP=138234?elqCampaignId=489428&src1=:so:ch:or:dg::::&SC=:so:ch:or:dg::::&pcode=WWMK230822P00010)
+- [Oracle AI First Principles - Youtube series](https://www.youtube.com/watch?v=ZCX-gT1q0ZQ)
 - [Oracle’s Generative AI strategy](https://blogs.oracle.com/ai-and-datascience/post/generative-ai-strategy)
-- [AI use cases - 10 examples](https://www.oracle.com/a/ocom/docs/gated/ai-use-cases-ebook.pdf)
-- [Availability of AI Services across OCI datacenters](https://www.oracle.com/uk/cloud/public-cloud-regions/service-availability/#commercial)
+- [Oracle AI & Data Science Blog](https://blogs.oracle.com/ai-and-datascience/)
+- [AI use cases - 11 examples](https://www.oracle.com/a/ocom/docs/gated/ai-use-cases-ebook.pdf)
+- [Availability of AI Services across OCI datacenters](https://www.oracle.com/cloud/distributed-cloud/#service-availability)
 
 ## Learning paths and certifications
 - [OCI AI Foundations Certification](https://mylearn.oracle.com/ou/learning-path/become-an-oci-ai-foundations-associate-2024/140164)

ai/gen-ai-agents/Document Understanding MCP AI Agent/files/package-lock.json

@@ -18,7 +18,7 @@
     "framer-motion": "^12.9.4",
     "lucide-react": "^0.511.0",
     "markdown-to-jsx": "^7.7.6",
-    "next": "15.4.2",
+    "next": "15.5.2",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-markdown": "^10.1.0"

ai/gen-ai-agents/Document Understanding MCP AI Agent/files/package.json

@@ -94,7 +94,7 @@ traitlets==5.14.3
 typing-inspect==0.9.0
 typing_extensions==4.12.2
 tzdata==2024.2
-urllib3==2.3.0
+urllib3==2.5.0
 wcwidth==0.2.13
 yarl==1.18.0
 zstandard==0.23.0

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

@@ -2,7 +2,7 @@
 
 An AI-powered assistant that routes user input across tools like Gmail, Google Calendar, Weather API, Calculator, and Oracle’s Generative AI services for smart, dynamic task automation.
 
-Reviewed: 23.04.2025
+Reviewed: 23.08.2025
 
 # When to use this asset?
 

ai/gen-ai-agents/assistant-secretary-agent/readme.md

@@ -4,7 +4,7 @@ CSV Analyzer Agent is an AI-Agent assistant designed to automate document unders
 It intelligently routes user questions through a multi-step process that includes PDF information extraction, CSV data analysis, code generation, execution, and natural language explanation.  
 It supports dynamic workflows like PDF parsing, CSV querying, and context-aware reporting through a Streamlit UI.
 
-Reviewed: April 18, 2025
+Reviewed: August 18, 2025
 
 # When to use this asset?
 

ai/gen-ai-agents/csvpdf_analyzer/readme.md

@@ -40,6 +40,9 @@ class State(TypedDict):
     standalone_question: str = ""
 
     # similarity_search
+    # 30/06: modified, now they're a dict with
+    # page_content and metadata
+    # populated with docs_serializable (utils.py)
     retriever_docs: Optional[list] = []
     # reranker
     reranker_docs: Optional[list] = []

ai/gen-ai-agents/custom_rag_agent/agent_state.py

@@ -1,7 +1,7 @@
 """
 File name: answer_generator.py
 Author: Luigi Saetta
-Date last modified: 2025-03-31
+Date last modified: 2025-04-02
 Python Version: 3.11
 
 Description:
@@ -67,10 +67,8 @@ def build_context_for_llm(self, docs: list):
 
         docs: list[Documents]
         """
-        _context = ""
-
-        for doc in docs:
-            _context += doc.page_content + "\n\n"
+        # more Pythonic
+        _context = "\n\n".join(doc["page_content"] for doc in docs)
 
         return _context
 
@@ -79,7 +77,7 @@ def invoke(self, input: State, config=None, **kwargs):
         """
         Generate the final answer
         """
-        # get the config
+        # get the model_id from config
         model_id = config["configurable"]["model_id"]
 
         if config["configurable"]["main_language"] in self.dict_languages:
@@ -102,6 +100,7 @@ def invoke(self, input: State, config=None, **kwargs):
         try:
             llm = get_llm(model_id=model_id)
 
+            # docs are returned from the reranker
             _context = self.build_context_for_llm(input["reranker_docs"])
 
             system_prompt = PromptTemplate(