diff --git a/.github/workflows/convert_notebooks.py b/.github/workflows/convert_notebooks.py
new file mode 100644
index 0000000..b6ee9dd
--- /dev/null
+++ b/.github/workflows/convert_notebooks.py
@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""
+Notebook to GitHub-Compatible Format Converter
+
+This script fixes Jupyter notebooks for GitHub rendering by:
+1. Converting XML-format notebooks to standard Jupyter JSON format
+2. Cleaning widget metadata that can cause GitHub rendering issues
+"""
+
+import os
+import json
+import re
+import nbformat
+from nbformat.validator import validate
+
+def process_notebooks(directory="."):
+    """Find and process all notebook files in the repository"""
+    notebook_files = []
+    print(f"Searching for notebooks in directory: {directory}")
+    for root, dirs, files in os.walk(directory):
+        # Skip directories that should be excluded
+        if '.git' in dirs:
+            dirs.remove('.git')  # Skip git directory
+        if '.github' in dirs:
+            dirs.remove('.github')  # Skip GitHub directory
+        if '.venv' in dirs:
+            dirs.remove('.venv')  # Skip virtual environments
+        
+        for file in files:
+            if file.endswith('.ipynb'):
+                notebook_path = os.path.join(root, file)
+                print(f"Found notebook: {notebook_path}")
+                notebook_files.append(notebook_path)
+    
+    print(f"Found {len(notebook_files)} notebooks to process")
+    
+    success_count = 0
+    for nb_path in notebook_files:
+        if convert_notebook(nb_path):
+            success_count += 1
+    
+    print(f"Successfully rendered {success_count} out of {len(notebook_files)} notebooks")
+    return success_count
+
+def convert_notebook(filepath):
+    """Convert a notebook to GitHub-compatible format by cleaning widget metadata"""
+    print(f"\nProcessing {filepath}")
+    
+    try:
+        # Read the notebook content
+        with open(filepath, 'r', encoding='utf-8') as f:
+            content = f.read()
+        
+        # Check if this is a XML notebook
+        if '<VSCode.Cell' in content:
+            print(f"  Converting from XML format...")
+            # Extract cells using regex
+            cells = []
+            cell_pattern = re.compile(r'<VSCode\.Cell.*?language="(.*?)".*?>(.*?)</VSCode\.Cell>', re.DOTALL)
+            
+            matches = list(cell_pattern.finditer(content))
+            if not matches:
+                print(f"  WARNING: No cells found in {filepath}")
+                return False
+                
+            print(f"  Found {len(matches)} cells")
+            
+            for match in matches:
+                cell_type, cell_content = match.groups()
+                
+                if cell_type == "markdown":
+                    cells.append(nbformat.v4.new_markdown_cell(
+                        source=cell_content.strip()
+                    ))
+                else:  # python, javascript, etc.
+                    cells.append(nbformat.v4.new_code_cell(
+                        source=cell_content.strip()
+                    ))
+            
+            # Create a new notebook
+            nb = nbformat.v4.new_notebook()
+            nb.cells = cells
+            
+            # Add required metadata
+            nb.metadata = {
+                "kernelspec": {
+                    "display_name": "Python 3",
+                    "language": "python",
+                    "name": "python3"
+                },
+                "language_info": {
+                    "codemirror_mode": {
+                        "name": "ipython",
+                        "version": 3
+                    },
+                    "file_extension": ".py",
+                    "mimetype": "text/x-python",
+                    "name": "python",
+                    "nbconvert_exporter": "python",
+                    "pygments_lexer": "ipython3",
+                    "version": "3.8.10"
+                },
+                # Add empty widget state to prevent GitHub rendering issues
+                "widgets": {
+                    "application/vnd.jupyter.widget-state+json": {
+                        "state": {},
+                        "version_major": 2,
+                        "version_minor": 0
+                    }
+                }
+            }
+            
+            # Validate and write the notebook
+            validate(nb)
+            with open(filepath, 'w', encoding='utf-8') as f:
+                nbformat.write(nb, f)
+            
+            print(f"  Successfully rendered {filepath} for GitHub compatibility")
+            return True
+        
+        else:
+            # It's already in JSON format, clean widget metadata
+            try:
+                notebook = json.loads(content)
+                print(f"  Cleaning widget metadata...")
+                
+                # Remove potentially problematic widget state but keep proper structure
+                if 'metadata' in notebook:
+                    # Replace with clean widget state
+                    notebook['metadata']['widgets'] = {
+                        "application/vnd.jupyter.widget-state+json": {
+                            "state": {},
+                            "version_major": 2,
+                            "version_minor": 0
+                        }
+                    }
+                
+                # Clean widget metadata from cells as well
+                for cell in notebook.get('cells', []):
+                    if 'metadata' in cell and 'widgets' in cell['metadata']:
+                        del cell['metadata']['widgets']
+                
+                # Write the cleaned notebook
+                with open(filepath, 'w', encoding='utf-8') as f:
+                    json.dump(notebook, f, indent=2)
+                
+                print(f"  Successfully cleaned {filepath} for GitHub compatibility")
+                return True
+                
+            except json.JSONDecodeError:
+                print(f"  ERROR: {filepath} is not in valid JSON format or XML format")
+                return False
+    
+    except Exception as e:
+        print(f"  ERROR processing {filepath}: {str(e)}")
+        return False
+
+if __name__ == "__main__":
+    print("Rendering notebooks for GitHub compatibility...")
+    # Get the repository root directory from environment variable if available
+    repo_root = os.environ.get('GITHUB_WORKSPACE', '.')
+    print(f"Repository root: {repo_root}")
+    process_notebooks(repo_root)
diff --git a/.github/workflows/render-notebooks.yml b/.github/workflows/render-notebooks.yml
new file mode 100644
index 0000000..0577b6a
--- /dev/null
+++ b/.github/workflows/render-notebooks.yml
@@ -0,0 +1,61 @@
+name: Render Notebooks for GitHub
+
+on:
+  push:
+    paths:
+      - '**.ipynb'
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:  # Allows manual triggering
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  render-notebooks:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ github.head_ref || github.ref_name }}  # Explicitly checkout the branch that triggered the workflow
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install nbformat nbconvert jupyter
+
+      - name: Run conversion script
+        run: python .github/workflows/convert_notebooks.py
+
+      - name: Configure Git
+        run: |
+          git config --global user.email "github-actions[bot]@users.noreply.github.com"
+          git config --global user.name "github-actions[bot]"
+
+      - name: Commit and push changes
+        run: |
+          CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+          echo "Current branch: $CURRENT_BRANCH"
+          
+          # Stage all notebook files
+          git add "**/*.ipynb"
+          
+          # Check if there are changes to commit
+          if git diff --staged --quiet; then
+            echo "No changes detected in notebooks"
+          else
+            echo "Changes detected in notebooks"
+            git commit -m "Fix notebooks for GitHub compatibility"
+            git push https://x-access-token:${{ secrets.GITHUB_TOKEN }}@github.com/${{ github.repository }}.git HEAD:${CURRENT_BRANCH}
+            echo "Successfully pushed changes"
+          fi
diff --git a/0_Overview.md b/0_Overview.md
index abb8c66..878d624 100644
--- a/0_Overview.md
+++ b/0_Overview.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -104,7 +104,7 @@ Click here for more information about: [Z-Order & V-Order](https://github.com/Mi
  
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/AzurePortal/1_MedallionArch/README.md b/AzurePortal/1_MedallionArch/README.md
index a7b2f92..e64a298 100644
--- a/AzurePortal/1_MedallionArch/README.md
+++ b/AzurePortal/1_MedallionArch/README.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -299,7 +299,7 @@ https://github.com/user-attachments/assets/2a64762a-f120-4448-b0fb-7a49f4d1bedb
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/AzurePortal/1_MedallionArch/docs/README.md b/AzurePortal/1_MedallionArch/docs/README.md
index eef1221..baf619f 100644
--- a/AzurePortal/1_MedallionArch/docs/README.md
+++ b/AzurePortal/1_MedallionArch/docs/README.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -15,7 +15,7 @@ Last updated: 2025-07-16
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/AzurePortal/1_MedallionArch/src/0_notebook_bronze_to_silver.ipynb b/AzurePortal/1_MedallionArch/src/0_notebook_bronze_to_silver.ipynb
index 04efdcf..03ebd49 100644
--- a/AzurePortal/1_MedallionArch/src/0_notebook_bronze_to_silver.ipynb
+++ b/AzurePortal/1_MedallionArch/src/0_notebook_bronze_to_silver.ipynb
@@ -1 +1,369 @@
-{"cells":[{"cell_type":"markdown","source":["# PySpark Code to Move Data from Bronze to Silver"],"metadata":{"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"ab7f0b7c-b0cc-44ec-9948-61d68f4b0b13"},{"cell_type":"markdown","source":["This is an example on how to work with the medallion architecture. From Bronze to Silver"],"metadata":{"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"44f47922-4e3b-45cc-81a6-c5de97634f73"},{"cell_type":"markdown","source":["## Working with 2020orders information"],"metadata":{"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"4e1afae8-b2ef-4e4c-9ac9-485139f19e9c"},{"cell_type":"code","source":["from pyspark.sql.types import *\n","import pyspark.sql.functions \n","from pyspark.sql import *"],"outputs":[],"execution_count":null,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"febb6c3e-6841-42c1-a633-0da056b7f69c"},{"cell_type":"code","source":["# Read the data from the bronze layer:\n","df_raw_2020orders = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/raw_Bronze.Lakehouse/Tables/2020orders\")\n","\n","df_raw_2020orders.head(2)"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":4,"statement_ids":[4],"state":"finished","livy_statement_state":"available","session_id":"ecb846c9-e988-4906-95bc-af67b3aacd94","normalized_state":"finished","queued_time":"2024-10-25T19:11:30.8930212Z","session_start_time":null,"execution_start_time":"2024-10-25T19:14:18.2840528Z","execution_finish_time":"2024-10-25T19:14:24.7554027Z","parent_msg_id":"4d60fa03-18dd-4bbc-adab-cb12ff2ba6cf"},"text/plain":"StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 4, Finished, Available, Finished)"},"metadata":{}},{"output_type":"execute_result","execution_count":11,"data":{"text/plain":"[Row(ID='SO45376', Count=1, Date='1/5/2020', Name='Edgar Mehta', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992),\n Row(ID='SO45381', Count=1, Date='1/6/2020', Name='Jordan Long', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992)]"},"metadata":{}}],"execution_count":2,"metadata":{"jupyter":{"source_hidden":false,"outputs_hidden":false},"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"6357dc47-1bb1-4391-8f38-b5d5a2abf5b2"},{"cell_type":"code","source":["# Clean the data (e.g., filter out rows with null values in the 'age' column):\n","df_cleaned = df_raw_2020orders.filter(df_raw_2020orders[\"Date\"].isNotNull())\n","print(df_cleaned)"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":10,"statement_ids":[10],"state":"finished","livy_statement_state":"available","session_id":"ecb846c9-e988-4906-95bc-af67b3aacd94","normalized_state":"finished","queued_time":"2024-10-25T19:21:35.4162864Z","session_start_time":null,"execution_start_time":"2024-10-25T19:21:35.9099818Z","execution_finish_time":"2024-10-25T19:21:36.2079156Z","parent_msg_id":"d65f6fd9-d9ab-4498-ab5d-0710bab459be"},"text/plain":"StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 10, Finished, Available, Finished)"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["DataFrame[ID: string, Count: int, Date: string, Name: string, Style: string, price: double, tax: double]\n"]}],"execution_count":8,"metadata":{"jupyter":{"source_hidden":false,"outputs_hidden":false},"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"5f5c8125-cbf5-4e00-9d8f-0c437f25b37f"},{"cell_type":"code","source":["# Save the cleaned data to the \"cleansed_Silver\" table in the Silver lakehouse:\n","df_cleaned.write.format(\"delta\").mode(\"overwrite\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/2020orders_silver\")"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":12,"statement_ids":[12],"state":"finished","livy_statement_state":"available","session_id":"ecb846c9-e988-4906-95bc-af67b3aacd94","normalized_state":"finished","queued_time":"2024-10-25T19:23:52.3238132Z","session_start_time":null,"execution_start_time":"2024-10-25T19:23:52.7414203Z","execution_finish_time":"2024-10-25T19:24:09.4412514Z","parent_msg_id":"8c92d669-7856-4961-a9d0-c38d54833ee4"},"text/plain":"StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 12, Finished, Available, Finished)"},"metadata":{}}],"execution_count":10,"metadata":{"jupyter":{"source_hidden":false,"outputs_hidden":false},"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"c83d4e46-2b49-490f-aadb-87a350c85e89"},{"cell_type":"markdown","source":["## Working with products information"],"metadata":{"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"f830afb3-2b02-4076-800a-85ca9fc33fea"},{"cell_type":"code","source":["# Read data from the Bronze layer\n","bronze_df = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/raw_Bronze.Lakehouse/Tables/products\")\n","# Perform transformations (if any)\n","silver_df = bronze_df  # Assuming no transformations for simplicity\n","# Write data to the Silver layer\n","silver_df.write.mode(\"overwrite\").format(\"delta\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/products_silver\")"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":15,"statement_ids":[15],"state":"finished","livy_statement_state":"available","session_id":"ecb846c9-e988-4906-95bc-af67b3aacd94","normalized_state":"finished","queued_time":"2024-10-25T19:27:20.1106109Z","session_start_time":null,"execution_start_time":"2024-10-25T19:27:20.5334249Z","execution_finish_time":"2024-10-25T19:27:25.4936309Z","parent_msg_id":"bf665ff4-43d5-4b02-90a6-6c28640576c3"},"text/plain":"StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 15, Finished, Available, Finished)"},"metadata":{}}],"execution_count":13,"metadata":{"jupyter":{"source_hidden":false,"outputs_hidden":false},"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"7f72ac98-4ece-4a8a-a5c5-5e1fc7273382"}],"metadata":{"kernel_info":{"name":"synapse_pyspark"},"kernelspec":{"name":"synapse_pyspark","language":"Python","display_name":"Synapse PySpark"},"language_info":{"name":"python"},"microsoft":{"language":"python","language_group":"synapse_pyspark","ms_spell_check":{"ms_spell_check_language":"en"}},"widgets":{},"nteract":{"version":"nteract-front-end@1.0.0"},"spark_compute":{"compute_id":"/trident/default","session_options":{"conf":{"spark.synapse.nbs.session.timeout":"1200000"}}},"dependencies":{"lakehouse":{"default_lakehouse":"251cd515-16a3-4555-a3d2-dfd12adb2335","default_lakehouse_name":"raw_Bronze","default_lakehouse_workspace_id":"597e0afc-c8db-4f4d-8464-d13570f5b075"}}},"nbformat":4,"nbformat_minor":5}
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "ab7f0b7c-b0cc-44ec-9948-61d68f4b0b13",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "# PySpark Code to Move Data from Bronze to Silver"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "44f47922-4e3b-45cc-81a6-c5de97634f73",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "This is an example on how to work with the medallion architecture. From Bronze to Silver"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "4e1afae8-b2ef-4e4c-9ac9-485139f19e9c",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Working with 2020orders information"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "febb6c3e-6841-42c1-a633-0da056b7f69c",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        }
+      },
+      "outputs": [],
+      "source": [
+        "from pyspark.sql.types import *\n",
+        "import pyspark.sql.functions \n",
+        "from pyspark.sql import *"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "6357dc47-1bb1-4391-8f38-b5d5a2abf5b2",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-25T19:14:24.7554027Z",
+              "execution_start_time": "2024-10-25T19:14:18.2840528Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "4d60fa03-18dd-4bbc-adab-cb12ff2ba6cf",
+              "queued_time": "2024-10-25T19:11:30.8930212Z",
+              "session_id": "ecb846c9-e988-4906-95bc-af67b3aacd94",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 4,
+              "statement_ids": [
+                4
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 4, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "text/plain": [
+              "[Row(ID='SO45376', Count=1, Date='1/5/2020', Name='Edgar Mehta', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992),\n",
+              " Row(ID='SO45381', Count=1, Date='1/6/2020', Name='Jordan Long', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992)]"
+            ]
+          },
+          "execution_count": 11,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# Read the data from the bronze layer:\n",
+        "df_raw_2020orders = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/raw_Bronze.Lakehouse/Tables/2020orders\")\n",
+        "\n",
+        "df_raw_2020orders.head(2)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "5f5c8125-cbf5-4e00-9d8f-0c437f25b37f",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-25T19:21:36.2079156Z",
+              "execution_start_time": "2024-10-25T19:21:35.9099818Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "d65f6fd9-d9ab-4498-ab5d-0710bab459be",
+              "queued_time": "2024-10-25T19:21:35.4162864Z",
+              "session_id": "ecb846c9-e988-4906-95bc-af67b3aacd94",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 10,
+              "statement_ids": [
+                10
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 10, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "DataFrame[ID: string, Count: int, Date: string, Name: string, Style: string, price: double, tax: double]\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Clean the data (e.g., filter out rows with null values in the 'age' column):\n",
+        "df_cleaned = df_raw_2020orders.filter(df_raw_2020orders[\"Date\"].isNotNull())\n",
+        "print(df_cleaned)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "id": "c83d4e46-2b49-490f-aadb-87a350c85e89",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-25T19:24:09.4412514Z",
+              "execution_start_time": "2024-10-25T19:23:52.7414203Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "8c92d669-7856-4961-a9d0-c38d54833ee4",
+              "queued_time": "2024-10-25T19:23:52.3238132Z",
+              "session_id": "ecb846c9-e988-4906-95bc-af67b3aacd94",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 12,
+              "statement_ids": [
+                12
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 12, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "# Save the cleaned data to the \"cleansed_Silver\" table in the Silver lakehouse:\n",
+        "df_cleaned.write.format(\"delta\").mode(\"overwrite\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/2020orders_silver\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f830afb3-2b02-4076-800a-85ca9fc33fea",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Working with products information"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "id": "7f72ac98-4ece-4a8a-a5c5-5e1fc7273382",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-25T19:27:25.4936309Z",
+              "execution_start_time": "2024-10-25T19:27:20.5334249Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "bf665ff4-43d5-4b02-90a6-6c28640576c3",
+              "queued_time": "2024-10-25T19:27:20.1106109Z",
+              "session_id": "ecb846c9-e988-4906-95bc-af67b3aacd94",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 15,
+              "statement_ids": [
+                15
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, ecb846c9-e988-4906-95bc-af67b3aacd94, 15, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "# Read data from the Bronze layer\n",
+        "bronze_df = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/raw_Bronze.Lakehouse/Tables/products\")\n",
+        "# Perform transformations (if any)\n",
+        "silver_df = bronze_df  # Assuming no transformations for simplicity\n",
+        "# Write data to the Silver layer\n",
+        "silver_df.write.mode(\"overwrite\").format(\"delta\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/products_silver\")"
+      ]
+    }
+  ],
+  "metadata": {
+    "dependencies": {
+      "lakehouse": {
+        "default_lakehouse": "251cd515-16a3-4555-a3d2-dfd12adb2335",
+        "default_lakehouse_name": "raw_Bronze",
+        "default_lakehouse_workspace_id": "597e0afc-c8db-4f4d-8464-d13570f5b075"
+      }
+    },
+    "kernel_info": {
+      "name": "synapse_pyspark"
+    },
+    "kernelspec": {
+      "display_name": "Synapse PySpark",
+      "language": "Python",
+      "name": "synapse_pyspark"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "microsoft": {
+      "language": "python",
+      "language_group": "synapse_pyspark",
+      "ms_spell_check": {
+        "ms_spell_check_language": "en"
+      }
+    },
+    "nteract": {
+      "version": "nteract-front-end@1.0.0"
+    },
+    "spark_compute": {
+      "compute_id": "/trident/default",
+      "session_options": {
+        "conf": {
+          "spark.synapse.nbs.session.timeout": "1200000"
+        }
+      }
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "state": {},
+        "version_major": 2,
+        "version_minor": 0
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
\ No newline at end of file
diff --git a/AzurePortal/1_MedallionArch/src/1_notebook_silver_to_gold.ipynb b/AzurePortal/1_MedallionArch/src/1_notebook_silver_to_gold.ipynb
index 42bf848..d574aae 100644
--- a/AzurePortal/1_MedallionArch/src/1_notebook_silver_to_gold.ipynb
+++ b/AzurePortal/1_MedallionArch/src/1_notebook_silver_to_gold.ipynb
@@ -1 +1,487 @@
-{"cells":[{"cell_type":"markdown","source":["# PySpark Code to Move Data from Silver to Gold"],"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"ab7f0b7c-b0cc-44ec-9948-61d68f4b0b13"},{"cell_type":"markdown","source":["This is an example on how to work with the medallion architecture. From Silver to Gold"],"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"44f47922-4e3b-45cc-81a6-c5de97634f73"},{"cell_type":"markdown","source":["## Working with 2020orders_silver information"],"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"4e1afae8-b2ef-4e4c-9ac9-485139f19e9c"},{"cell_type":"code","source":["from pyspark.sql.types import *\n","import pyspark.sql.functions \n","from pyspark.sql import *\n","from pyspark.sql.functions import sum\n"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":15,"statement_ids":[15],"state":"finished","livy_statement_state":"available","session_id":"8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5","normalized_state":"finished","queued_time":"2024-10-25T20:29:16.4970957Z","session_start_time":null,"execution_start_time":"2024-10-25T20:29:16.9788868Z","execution_finish_time":"2024-10-25T20:29:17.2577679Z","parent_msg_id":"f6330200-43db-4e0b-9e85-773c1fa95042"},"text/plain":"StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 15, Finished, Available, Finished)"},"metadata":{}}],"execution_count":13,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"febb6c3e-6841-42c1-a633-0da056b7f69c"},{"cell_type":"code","source":["# Read the data from the silver layer:\n","df_cleansed_2020orders = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/2020orders_silver\")\n","\n","df_cleansed_2020orders.head(2)"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":16,"statement_ids":[16],"state":"finished","livy_statement_state":"available","session_id":"8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5","normalized_state":"finished","queued_time":"2024-10-25T20:29:17.7525504Z","session_start_time":null,"execution_start_time":"2024-10-25T20:29:18.2199944Z","execution_finish_time":"2024-10-25T20:29:26.3332937Z","parent_msg_id":"901386c6-fa37-4dad-8a8d-34e1276108f8"},"text/plain":"StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 16, Finished, Available, Finished)"},"metadata":{}},{"output_type":"execute_result","execution_count":47,"data":{"text/plain":"[Row(ID='SO45376', Count=1, Date='1/5/2020', Name='Edgar Mehta', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992),\n Row(ID='SO45381', Count=1, Date='1/6/2020', Name='Jordan Long', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992)]"},"metadata":{}}],"execution_count":14,"metadata":{"jupyter":{"outputs_hidden":false,"source_hidden":false},"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"6357dc47-1bb1-4391-8f38-b5d5a2abf5b2"},{"cell_type":"code","source":["df_cleansed_2020orders = df_cleansed_2020orders.withColumn(\"tax\", df_cleansed_2020orders[\"tax\"].cast(\"int\")) # type to int"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":17,"statement_ids":[17],"state":"finished","livy_statement_state":"available","session_id":"8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5","normalized_state":"finished","queued_time":"2024-10-25T20:29:18.1174684Z","session_start_time":null,"execution_start_time":"2024-10-25T20:29:26.7221718Z","execution_finish_time":"2024-10-25T20:29:26.9553583Z","parent_msg_id":"1d52d464-b1ce-40ca-a8b4-ed446b5980fd"},"text/plain":"StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 17, Finished, Available, Finished)"},"metadata":{}}],"execution_count":15,"metadata":{"jupyter":{"source_hidden":false,"outputs_hidden":false},"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"b1478c38-d56e-4a58-a551-405675f4110d"},{"cell_type":"code","source":["df_cleansed_2020orders.printSchema()"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":18,"statement_ids":[18],"state":"finished","livy_statement_state":"available","session_id":"8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5","normalized_state":"finished","queued_time":"2024-10-25T20:29:18.3209761Z","session_start_time":null,"execution_start_time":"2024-10-25T20:29:27.3402865Z","execution_finish_time":"2024-10-25T20:29:27.5846334Z","parent_msg_id":"882470dc-dab6-4bef-bf92-1f25c81c4bad"},"text/plain":"StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 18, Finished, Available, Finished)"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["root\n |-- ID: string (nullable = true)\n |-- Count: integer (nullable = true)\n |-- Date: string (nullable = true)\n |-- Name: string (nullable = true)\n |-- Style: string (nullable = true)\n |-- price: double (nullable = true)\n |-- tax: integer (nullable = true)\n\n"]}],"execution_count":16,"metadata":{"jupyter":{"source_hidden":false,"outputs_hidden":false},"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"f9da346b-2b25-463a-821d-6b8d7bda321e"},{"cell_type":"code","source":["# Group and Aggregate the Data:\n","df_aggregated = df_cleansed_2020orders.groupBy(\"Style\").agg(sum(\"price\").alias(\"total_price_vehicles\"))\n","df_aggregated.show(10, truncate=False)\n","print(df_aggregated)"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":19,"statement_ids":[19],"state":"finished","livy_statement_state":"available","session_id":"8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5","normalized_state":"finished","queued_time":"2024-10-25T20:29:18.5521281Z","session_start_time":null,"execution_start_time":"2024-10-25T20:29:27.9679539Z","execution_finish_time":"2024-10-25T20:29:34.3035094Z","parent_msg_id":"9a5b30d2-5552-495b-b0a7-c5cfed0bebd8"},"text/plain":"StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 19, Finished, Available, Finished)"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["+-----------------------+--------------------+\n|Style                  |total_price_vehicles|\n+-----------------------+--------------------+\n|Mountain-200 Black, 42 |196713.42720000003  |\n|Mountain-100 Silver, 42|71399.78999999998   |\n|Mountain-200 Silver, 42|159499.30919999976  |\n|Mountain-100 Silver, 44|71399.78999999998   |\n|Road-550-W Yellow, 40  |37016.1875          |\n|Mountain-100 Silver, 38|64599.80999999997   |\n|Road-250 Red, 48       |256551.75000000044  |\n|Road-250 Red, 52       |217458.15000000034  |\n|Road-650 Red, 52       |20301.81200000001   |\n|Road-250 Black, 52     |253061.25           |\n+-----------------------+--------------------+\nonly showing top 10 rows\n\nDataFrame[Style: string, total_price_vehicles: double]\n"]}],"execution_count":17,"metadata":{"jupyter":{"outputs_hidden":false,"source_hidden":false},"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"5f5c8125-cbf5-4e00-9d8f-0c437f25b37f"},{"cell_type":"code","source":["# Save the cleaned data to the \"curated_Gold\" table in the Gold lakehouse:\n","df_aggregated.write.format(\"delta\").mode(\"overwrite\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/curated_Gold.Lakehouse/Tables/2020orders_gold\")"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":20,"statement_ids":[20],"state":"finished","livy_statement_state":"available","session_id":"8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5","normalized_state":"finished","queued_time":"2024-10-25T20:29:18.7090964Z","session_start_time":null,"execution_start_time":"2024-10-25T20:29:34.7050563Z","execution_finish_time":"2024-10-25T20:29:39.5141044Z","parent_msg_id":"56e18a6c-9106-4200-a6cc-7386c03b93d3"},"text/plain":"StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 20, Finished, Available, Finished)"},"metadata":{}}],"execution_count":18,"metadata":{"jupyter":{"outputs_hidden":false,"source_hidden":false},"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"c83d4e46-2b49-490f-aadb-87a350c85e89"},{"cell_type":"markdown","source":["## Working with products_silver information"],"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"f830afb3-2b02-4076-800a-85ca9fc33fea"},{"cell_type":"code","source":["# Read data from the Silver layer\n","silver_df = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/products_silver\")\n","# Perform transformations (if any)\n","silver_df = silver_df  # Assuming no transformations for simplicity\n","# Write data to the Gold layer\n","silver_df.write.mode(\"overwrite\").format(\"delta\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/curated_gold.Lakehouse/Tables/products_silver\")"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":21,"statement_ids":[21],"state":"finished","livy_statement_state":"available","session_id":"8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5","normalized_state":"finished","queued_time":"2024-10-25T20:29:45.1788369Z","session_start_time":null,"execution_start_time":"2024-10-25T20:29:45.5790407Z","execution_finish_time":"2024-10-25T20:29:49.090114Z","parent_msg_id":"67830cc7-dbf9-4b47-a9ea-51ce1c29634b"},"text/plain":"StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 21, Finished, Available, Finished)"},"metadata":{}}],"execution_count":19,"metadata":{"jupyter":{"outputs_hidden":false,"source_hidden":false},"microsoft":{"language":"python","language_group":"synapse_pyspark"},"nteract":{"transient":{"deleting":false}}},"id":"7f72ac98-4ece-4a8a-a5c5-5e1fc7273382"}],"metadata":{"kernel_info":{"name":"synapse_pyspark"},"kernelspec":{"name":"synapse_pyspark","language":"Python","display_name":"Synapse PySpark"},"language_info":{"name":"python"},"microsoft":{"language":"python","language_group":"synapse_pyspark","ms_spell_check":{"ms_spell_check_language":"en"}},"nteract":{"version":"nteract-front-end@1.0.0"},"widgets":{},"spark_compute":{"compute_id":"/trident/default","session_options":{"conf":{"spark.synapse.nbs.session.timeout":"1200000"}}},"dependencies":{"lakehouse":{"default_lakehouse":"251cd515-16a3-4555-a3d2-dfd12adb2335","default_lakehouse_name":"raw_Bronze","default_lakehouse_workspace_id":"597e0afc-c8db-4f4d-8464-d13570f5b075"}}},"nbformat":4,"nbformat_minor":5}
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# PySpark Code to Move Data from Silver to Gold"
+      ],
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "ab7f0b7c-b0cc-44ec-9948-61d68f4b0b13"
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "This is an example on how to work with the medallion architecture. From Silver to Gold"
+      ],
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "44f47922-4e3b-45cc-81a6-c5de97634f73"
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Working with 2020orders_silver information"
+      ],
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "4e1afae8-b2ef-4e4c-9ac9-485139f19e9c"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from pyspark.sql.types import *\n",
+        "import pyspark.sql.functions \n",
+        "from pyspark.sql import *\n",
+        "from pyspark.sql.functions import sum\n"
+      ],
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "spark_pool": null,
+              "statement_id": 15,
+              "statement_ids": [
+                15
+              ],
+              "state": "finished",
+              "livy_statement_state": "available",
+              "session_id": "8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5",
+              "normalized_state": "finished",
+              "queued_time": "2024-10-25T20:29:16.4970957Z",
+              "session_start_time": null,
+              "execution_start_time": "2024-10-25T20:29:16.9788868Z",
+              "execution_finish_time": "2024-10-25T20:29:17.2577679Z",
+              "parent_msg_id": "f6330200-43db-4e0b-9e85-773c1fa95042"
+            },
+            "text/plain": "StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 15, Finished, Available, Finished)"
+          },
+          "metadata": {}
+        }
+      ],
+      "execution_count": 13,
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        }
+      },
+      "id": "febb6c3e-6841-42c1-a633-0da056b7f69c"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Read the data from the silver layer:\n",
+        "df_cleansed_2020orders = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/2020orders_silver\")\n",
+        "\n",
+        "df_cleansed_2020orders.head(2)"
+      ],
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "spark_pool": null,
+              "statement_id": 16,
+              "statement_ids": [
+                16
+              ],
+              "state": "finished",
+              "livy_statement_state": "available",
+              "session_id": "8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5",
+              "normalized_state": "finished",
+              "queued_time": "2024-10-25T20:29:17.7525504Z",
+              "session_start_time": null,
+              "execution_start_time": "2024-10-25T20:29:18.2199944Z",
+              "execution_finish_time": "2024-10-25T20:29:26.3332937Z",
+              "parent_msg_id": "901386c6-fa37-4dad-8a8d-34e1276108f8"
+            },
+            "text/plain": "StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 16, Finished, Available, Finished)"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "execute_result",
+          "execution_count": 47,
+          "data": {
+            "text/plain": "[Row(ID='SO45376', Count=1, Date='1/5/2020', Name='Edgar Mehta', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992),\n Row(ID='SO45381', Count=1, Date='1/6/2020', Name='Jordan Long', Style='Mountain-100 Silver, 38', price=3399.99, tax=271.9992)]"
+          },
+          "metadata": {}
+        }
+      ],
+      "execution_count": 14,
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "6357dc47-1bb1-4391-8f38-b5d5a2abf5b2"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_cleansed_2020orders = df_cleansed_2020orders.withColumn(\"tax\", df_cleansed_2020orders[\"tax\"].cast(\"int\")) # type to int"
+      ],
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "spark_pool": null,
+              "statement_id": 17,
+              "statement_ids": [
+                17
+              ],
+              "state": "finished",
+              "livy_statement_state": "available",
+              "session_id": "8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5",
+              "normalized_state": "finished",
+              "queued_time": "2024-10-25T20:29:18.1174684Z",
+              "session_start_time": null,
+              "execution_start_time": "2024-10-25T20:29:26.7221718Z",
+              "execution_finish_time": "2024-10-25T20:29:26.9553583Z",
+              "parent_msg_id": "1d52d464-b1ce-40ca-a8b4-ed446b5980fd"
+            },
+            "text/plain": "StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 17, Finished, Available, Finished)"
+          },
+          "metadata": {}
+        }
+      ],
+      "execution_count": 15,
+      "metadata": {
+        "jupyter": {
+          "source_hidden": false,
+          "outputs_hidden": false
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        }
+      },
+      "id": "b1478c38-d56e-4a58-a551-405675f4110d"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_cleansed_2020orders.printSchema()"
+      ],
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "spark_pool": null,
+              "statement_id": 18,
+              "statement_ids": [
+                18
+              ],
+              "state": "finished",
+              "livy_statement_state": "available",
+              "session_id": "8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5",
+              "normalized_state": "finished",
+              "queued_time": "2024-10-25T20:29:18.3209761Z",
+              "session_start_time": null,
+              "execution_start_time": "2024-10-25T20:29:27.3402865Z",
+              "execution_finish_time": "2024-10-25T20:29:27.5846334Z",
+              "parent_msg_id": "882470dc-dab6-4bef-bf92-1f25c81c4bad"
+            },
+            "text/plain": "StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 18, Finished, Available, Finished)"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "root\n |-- ID: string (nullable = true)\n |-- Count: integer (nullable = true)\n |-- Date: string (nullable = true)\n |-- Name: string (nullable = true)\n |-- Style: string (nullable = true)\n |-- price: double (nullable = true)\n |-- tax: integer (nullable = true)\n\n"
+          ]
+        }
+      ],
+      "execution_count": 16,
+      "metadata": {
+        "jupyter": {
+          "source_hidden": false,
+          "outputs_hidden": false
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        }
+      },
+      "id": "f9da346b-2b25-463a-821d-6b8d7bda321e"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Group and Aggregate the Data:\n",
+        "df_aggregated = df_cleansed_2020orders.groupBy(\"Style\").agg(sum(\"price\").alias(\"total_price_vehicles\"))\n",
+        "df_aggregated.show(10, truncate=False)\n",
+        "print(df_aggregated)"
+      ],
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "spark_pool": null,
+              "statement_id": 19,
+              "statement_ids": [
+                19
+              ],
+              "state": "finished",
+              "livy_statement_state": "available",
+              "session_id": "8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5",
+              "normalized_state": "finished",
+              "queued_time": "2024-10-25T20:29:18.5521281Z",
+              "session_start_time": null,
+              "execution_start_time": "2024-10-25T20:29:27.9679539Z",
+              "execution_finish_time": "2024-10-25T20:29:34.3035094Z",
+              "parent_msg_id": "9a5b30d2-5552-495b-b0a7-c5cfed0bebd8"
+            },
+            "text/plain": "StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 19, Finished, Available, Finished)"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "+-----------------------+--------------------+\n|Style                  |total_price_vehicles|\n+-----------------------+--------------------+\n|Mountain-200 Black, 42 |196713.42720000003  |\n|Mountain-100 Silver, 42|71399.78999999998   |\n|Mountain-200 Silver, 42|159499.30919999976  |\n|Mountain-100 Silver, 44|71399.78999999998   |\n|Road-550-W Yellow, 40  |37016.1875          |\n|Mountain-100 Silver, 38|64599.80999999997   |\n|Road-250 Red, 48       |256551.75000000044  |\n|Road-250 Red, 52       |217458.15000000034  |\n|Road-650 Red, 52       |20301.81200000001   |\n|Road-250 Black, 52     |253061.25           |\n+-----------------------+--------------------+\nonly showing top 10 rows\n\nDataFrame[Style: string, total_price_vehicles: double]\n"
+          ]
+        }
+      ],
+      "execution_count": 17,
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "5f5c8125-cbf5-4e00-9d8f-0c437f25b37f"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Save the cleaned data to the \"curated_Gold\" table in the Gold lakehouse:\n",
+        "df_aggregated.write.format(\"delta\").mode(\"overwrite\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/curated_Gold.Lakehouse/Tables/2020orders_gold\")"
+      ],
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "spark_pool": null,
+              "statement_id": 20,
+              "statement_ids": [
+                20
+              ],
+              "state": "finished",
+              "livy_statement_state": "available",
+              "session_id": "8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5",
+              "normalized_state": "finished",
+              "queued_time": "2024-10-25T20:29:18.7090964Z",
+              "session_start_time": null,
+              "execution_start_time": "2024-10-25T20:29:34.7050563Z",
+              "execution_finish_time": "2024-10-25T20:29:39.5141044Z",
+              "parent_msg_id": "56e18a6c-9106-4200-a6cc-7386c03b93d3"
+            },
+            "text/plain": "StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 20, Finished, Available, Finished)"
+          },
+          "metadata": {}
+        }
+      ],
+      "execution_count": 18,
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "c83d4e46-2b49-490f-aadb-87a350c85e89"
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Working with products_silver information"
+      ],
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "f830afb3-2b02-4076-800a-85ca9fc33fea"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Read data from the Silver layer\n",
+        "silver_df = spark.read.format(\"delta\").load(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/cleansed_test_Silver.Lakehouse/Tables/products_silver\")\n",
+        "# Perform transformations (if any)\n",
+        "silver_df = silver_df  # Assuming no transformations for simplicity\n",
+        "# Write data to the Gold layer\n",
+        "silver_df.write.mode(\"overwrite\").format(\"delta\").save(\"abfss://fabric_medallion_arch_demo@onelake.dfs.fabric.microsoft.com/curated_gold.Lakehouse/Tables/products_silver\")"
+      ],
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "spark_pool": null,
+              "statement_id": 21,
+              "statement_ids": [
+                21
+              ],
+              "state": "finished",
+              "livy_statement_state": "available",
+              "session_id": "8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5",
+              "normalized_state": "finished",
+              "queued_time": "2024-10-25T20:29:45.1788369Z",
+              "session_start_time": null,
+              "execution_start_time": "2024-10-25T20:29:45.5790407Z",
+              "execution_finish_time": "2024-10-25T20:29:49.090114Z",
+              "parent_msg_id": "67830cc7-dbf9-4b47-a9ea-51ce1c29634b"
+            },
+            "text/plain": "StatementMeta(, 8c75f6dc-9a98-446c-957a-b0fa1e9d3fa5, 21, Finished, Available, Finished)"
+          },
+          "metadata": {}
+        }
+      ],
+      "execution_count": 19,
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "id": "7f72ac98-4ece-4a8a-a5c5-5e1fc7273382"
+    }
+  ],
+  "metadata": {
+    "kernel_info": {
+      "name": "synapse_pyspark"
+    },
+    "kernelspec": {
+      "name": "synapse_pyspark",
+      "language": "Python",
+      "display_name": "Synapse PySpark"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "microsoft": {
+      "language": "python",
+      "language_group": "synapse_pyspark",
+      "ms_spell_check": {
+        "ms_spell_check_language": "en"
+      }
+    },
+    "nteract": {
+      "version": "nteract-front-end@1.0.0"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "state": {},
+        "version_major": 2,
+        "version_minor": 0
+      }
+    },
+    "spark_compute": {
+      "compute_id": "/trident/default",
+      "session_options": {
+        "conf": {
+          "spark.synapse.nbs.session.timeout": "1200000"
+        }
+      }
+    },
+    "dependencies": {
+      "lakehouse": {
+        "default_lakehouse": "251cd515-16a3-4555-a3d2-dfd12adb2335",
+        "default_lakehouse_name": "raw_Bronze",
+        "default_lakehouse_workspace_id": "597e0afc-c8db-4f4d-8464-d13570f5b075"
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
\ No newline at end of file
diff --git a/AzurePortal/2_AI_LLMs/README.md b/AzurePortal/2_AI_LLMs/README.md
index 8967712..909e4b3 100644
--- a/AzurePortal/2_AI_LLMs/README.md
+++ b/AzurePortal/2_AI_LLMs/README.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -397,7 +397,7 @@ Make sure to replace `"your_openai_api_key"`, `"https://your_openai_api_base/"`,
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/AzurePortal/2_AI_LLMs/src/fabric-llms-overview_sample.ipynb b/AzurePortal/2_AI_LLMs/src/fabric-llms-overview_sample.ipynb
index 880187e..a0d1b8e 100644
--- a/AzurePortal/2_AI_LLMs/src/fabric-llms-overview_sample.ipynb
+++ b/AzurePortal/2_AI_LLMs/src/fabric-llms-overview_sample.ipynb
@@ -1,1202 +1,1203 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "519955e9-2dad-456d-93db-a332d38e9433",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "# Fabric: Highlights into AI/LLMs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "d312e8d9-03fe-4b3d-aa6d-c52e3022ae39",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T03:58:26.7170509Z",
-       "execution_start_time": "2024-10-31T03:58:19.270951Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "e267b6ab-5133-4598-8251-d64374cd11e5",
-       "queued_time": "2024-10-31T03:58:18.9132075Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 5,
-       "statement_ids": [
-        5
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 5, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: synapseml\r\n",
-      "Version: 1.0.8\r\n",
-      "Summary: Synapse Machine Learning\r\n",
-      "Home-page: https://github.com/Microsoft/SynapseML\r\n",
-      "Author: Microsoft\r\n",
-      "Author-email: synapseml-support@microsoft.com\r\n",
-      "License: MIT\r\n",
-      "Location: /home/trusted-service-user/cluster-env/clonedenv/lib/python3.11/site-packages\r\n",
-      "Requires: \r\n",
-      "Required-by: \r\n"
-     ]
-    }
-   ],
-   "source": [
-    "!pip show synapseml"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "427610d0-3fae-45e3-8150-92ee7674f44c",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T03:58:28.6254349Z",
-       "execution_start_time": "2024-10-31T03:58:27.1124616Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "0e9f6c0f-062b-4e5d-9061-afcd89c8fd75",
-       "queued_time": "2024-10-31T03:58:19.3223486Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 6,
-       "statement_ids": [
-        6
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 6, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: langchain-openai\r\n",
-      "Version: 0.2.4\r\n",
-      "Summary: An integration package connecting OpenAI and LangChain\r\n",
-      "Home-page: https://github.com/langchain-ai/langchain\r\n",
-      "Author: \r\n",
-      "Author-email: \r\n",
-      "License: MIT\r\n",
-      "Location: /home/trusted-service-user/cluster-env/clonedenv/lib/python3.11/site-packages\r\n",
-      "Requires: langchain-core, openai, tiktoken\r\n",
-      "Required-by: \r\n"
-     ]
-    }
-   ],
-   "source": [
-    "!pip show langchain-openai"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "baeeb853-2104-4edf-abf4-4d4be50cb977",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T03:58:30.5465258Z",
-       "execution_start_time": "2024-10-31T03:58:29.0000586Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "716d9975-263b-4d92-b25c-b342106f5f43",
-       "queued_time": "2024-10-31T03:58:19.511824Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 7,
-       "statement_ids": [
-        7
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 7, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Name: langchain\r\n",
-      "Version: 0.3.6\r\n",
-      "Summary: Building applications with LLMs through composability\r\n",
-      "Home-page: https://github.com/langchain-ai/langchain\r\n",
-      "Author: \r\n",
-      "Author-email: \r\n",
-      "License: MIT\r\n",
-      "Location: /home/trusted-service-user/cluster-env/clonedenv/lib/python3.11/site-packages\r\n",
-      "Requires: aiohttp, langchain-core, langchain-text-splitters, langsmith, numpy, pydantic, PyYAML, requests, SQLAlchemy, tenacity\r\n",
-      "Required-by: langchain-community\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "!pip show langchain"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c58cc406-c4f5-4607-a740-0802e8e4b550",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Ensure you have the API key and endpoint URL for your deployed model. Set these as environment variables"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "3c8ada7c-2632-4c69-86d2-f5260ee8f1b7",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:20:14.3495341Z",
-       "execution_start_time": "2024-10-31T04:20:14.1128215Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "2573bf75-fe6d-40dc-b9f6-e06ebb9f7f73",
-       "queued_time": "2024-10-31T04:20:13.6194485Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 22,
-       "statement_ids": [
-        22
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 22, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_VERSION\"] = \"2023-08-01-preview\"\n",
-    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://your-resource.openai.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2024-08-01-preview\"\n",
-    "os.environ[\"AZURE_OPENAI_API_KEY\"] = \"your-value\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3fac48a9-45fb-4e86-9792-8ee340b0ac60",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Create an instance of the Azure OpenAI class using the environment variables set above"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "5db10350-8000-4cbd-9bdf-d7da62d7fe61",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:20:14.9382032Z",
-       "execution_start_time": "2024-10-31T04:20:14.7083469Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "7dfaca5a-f738-4010-bba1-f764ea70f450",
-       "queued_time": "2024-10-31T04:20:14.027325Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 23,
-       "statement_ids": [
-        23
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 23, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from langchain_openai import AzureChatOpenAI\n",
-    "\n",
-    "# Set the API base URL\n",
-    "api_base = os.environ[\"AZURE_OPENAI_ENDPOINT\"]\n",
-    "\n",
-    "# Create an instance of the Azure OpenAI Class\n",
-    "llm = AzureChatOpenAI(\n",
-    "    openai_api_key=os.environ[\"AZURE_OPENAI_API_KEY\"],\n",
-    "    temperature=0.7,\n",
-    "    verbose=True,\n",
-    "    top_p=0.9\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b17d7450-34b5-4ece-8e20-a77ddcdd93c4",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Use the Azure OpenAI service to generate text or perform other language model tasks"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "cfc5fd62-085a-4eff-9192-696d9f249a8e",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:20:16.0500538Z",
-       "execution_start_time": "2024-10-31T04:20:15.2936074Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "e14e4d0b-1fd0-4dac-a07d-6479d6536ce3",
-       "queued_time": "2024-10-31T04:20:14.4969185Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 24,
-       "statement_ids": [
-        24
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 24, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='Salut, comment ça va ?' additional_kwargs={'refusal': None} response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 33, 'total_tokens': 39, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'gpt-4o-mini', 'system_fingerprint': 'fp_d54531d9eb', 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'protected_material_code': {'filtered': False, 'detected': False}, 'protected_material_text': {'filtered': False, 'detected': False}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}} id='run-8cb7f29a-44c1-4f65-a648-15afb2d793dc-0' usage_metadata={'input_tokens': 33, 'output_tokens': 6, 'total_tokens': 39, 'input_token_details': {}, 'output_token_details': {}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Define a prompt\n",
-    "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"Hi, how are you?\"),\n",
-    "]\n",
-    "\n",
-    "# Generate a response from the Azure OpenAI service using the invoke method\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "\n",
-    "# Print the response\n",
-    "print(ai_msg)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "79729106-c7f1-4879-bc2b-871b50c2ac9a",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Define a prompt template for generating definitions"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "ca633361-c27b-4294-b8a7-9fc4a316afa4",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:20:16.587491Z",
-       "execution_start_time": "2024-10-31T04:20:16.3655978Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "cc3215f4-71a5-4231-af47-9bd9a8f5698a",
-       "queued_time": "2024-10-31T04:20:14.7799392Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 25,
-       "statement_ids": [
-        25
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 25, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
-    "copy_prompt = PromptTemplate(\n",
-    "    input_variables=[\"technology\"],\n",
-    "    template=\"Define the following word: {technology}\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "899839d9-adca-4042-b662-73edcad7e432",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Create an LLMChain with the defined prompt template"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "bd4f65ca-049b-481d-bbbd-a017c6c0119b",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:20:17.1233668Z",
-       "execution_start_time": "2024-10-31T04:20:16.9052959Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "27790d83-509f-4716-bb69-9c288ad069ba",
-       "queued_time": "2024-10-31T04:20:15.1325692Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 26,
-       "statement_ids": [
-        26
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 26, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from langchain.chains import LLMChain\n",
-    "\n",
-    "chain = LLMChain(llm=llm, prompt=copy_prompt)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "936b3ddf-cc65-436c-ba4e-ae0abe21fc2c",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Set up the LangChain transformer to execute the processing chain\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "63a00038-37b4-49ee-9c53-128c8acf9d01",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:20:18.181457Z",
-       "execution_start_time": "2024-10-31T04:20:17.4351576Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "3fb30420-f0c9-477b-ad1a-001dc0d8d37a",
-       "queued_time": "2024-10-31T04:20:15.6799013Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 27,
-       "statement_ids": [
-        27
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 27, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from synapse.ml.cognitive.langchain import LangchainTransformer\n",
-    "\n",
-    "openai_api_key= os.environ[\"AZURE_OPENAI_API_KEY\"]\n",
-    "\n",
-    "transformer = (\n",
-    "    LangchainTransformer()\n",
-    "    .setInputCol(\"technology\")\n",
-    "    .setOutputCol(\"definition\")\n",
-    "    .setChain(chain)\n",
-    "    .setSubscriptionKey(openai_api_key)\n",
-    "    .setUrl(api_base)\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c74293f0-925e-4987-a6a1-b3b9b8e14b9d",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Construct a DataFrame with technology names."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "8e03963e-2fcf-4934-b96f-ac27b4e0353c",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:24:08.3891172Z",
-       "execution_start_time": "2024-10-31T04:24:02.0675933Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "856f5b73-26e8-4d20-a901-356cd92b9c2a",
-       "queued_time": "2024-10-31T04:24:01.6603792Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 29,
-       "statement_ids": [
-        29
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 29, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "+-----+----------+----------------------+\n",
-      "|label|technology|transformed_technology|\n",
-      "+-----+----------+----------------------+\n",
-      "|    0|    docker|                DOCKER|\n",
-      "|    1|     spark|                 SPARK|\n",
-      "|    2|    python|                PYTHON|\n",
-      "+-----+----------+----------------------+\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from pyspark.sql import SparkSession\n",
-    "from pyspark.sql.functions import udf\n",
-    "from pyspark.sql.types import StringType\n",
-    "\n",
-    "# Initialize Spark session\n",
-    "spark = SparkSession.builder.appName(\"example\").getOrCreate()\n",
-    "\n",
-    "# Construct a DataFrame with technology names\n",
-    "df = spark.createDataFrame(\n",
-    "    [\n",
-    "        (0, \"docker\"), (1, \"spark\"), (2, \"python\")\n",
-    "    ],\n",
-    "    [\"label\", \"technology\"]\n",
-    ")\n",
-    "\n",
-    "# Define a simple UDF to transform the technology column\n",
-    "def transform_technology(tech):\n",
-    "    return tech.upper()\n",
-    "\n",
-    "# Register the UDF\n",
-    "transform_udf = udf(transform_technology, StringType())\n",
-    "\n",
-    "# Apply the UDF to the DataFrame\n",
-    "transformed_df = df.withColumn(\"transformed_technology\", transform_udf(df[\"technology\"]))\n",
-    "\n",
-    "# Show the transformed DataFrame\n",
-    "transformed_df.show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "47ab1ba6-deaf-488d-9e95-8202669d948c",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Extract content from PDFs linked in arXiv papers and generate prompts for extracting specific information.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "8b52c87e-5971-4d28-bc4b-4160d29a1c24",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:27:08.3224773Z",
-       "execution_start_time": "2024-10-31T04:27:08.0430507Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "4eeab690-4159-41dc-be69-3cceed484314",
-       "queued_time": "2024-10-31T04:27:07.6309068Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 30,
-       "statement_ids": [
-        30
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 30, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from langchain.document_loaders import OnlinePDFLoader\n",
-    "\n",
-    "def paper_content_extraction(inputs: dict) -> dict:\n",
-    "    arxiv_link = inputs[\"arxiv_link\"]\n",
-    "    loader = OnlinePDFLoader(arxiv_link)\n",
-    "    pages = loader.load_and_split()\n",
-    "    return {\"paper_content\": pages[0].page_content + pages[1].page_content}\n",
-    "\n",
-    "def prompt_generation(inputs: dict) -> dict:\n",
-    "    output = inputs[\"Output\"]\n",
-    "    prompt = (\n",
-    "        \"find the paper title, author, summary in the paper description below, output them. \"\n",
-    "        \"After that, Use websearch to find out 3 recent papers of the first author in the author section below \"\n",
-    "        \"(first author is the first name separated by comma) and list the paper titles in bullet points: \"\n",
-    "        \"<Paper Description Start>\\n\" + output + \"<Paper Description End>.\"\n",
-    "    )\n",
-    "    return {\"prompt\": prompt}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "89d79c38-ba0c-4062-911c-7ede02536298",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Set up a chain to extract structured information from an arXiv link\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "e85241a0-11c2-49c1-9b2e-63187cb24d9a",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:28:11.2331925Z",
-       "execution_start_time": "2024-10-31T04:28:11.0134852Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "232b4aa0-1b84-47f8-bb5d-347a575d9640",
-       "queued_time": "2024-10-31T04:28:10.663514Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 31,
-       "statement_ids": [
-        31
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 31, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from langchain.chains import TransformChain, SimpleSequentialChain\n",
-    "\n",
-    "paper_content_extraction_chain = TransformChain(\n",
-    "    input_variables=[\"arxiv_link\"],\n",
-    "    output_variables=[\"paper_content\"],\n",
-    "    transform=paper_content_extraction,\n",
-    "    verbose=False,\n",
-    ")\n",
-    "\n",
-    "paper_summarizer_template = \"\"\"\n",
-    "You are a paper summarizer, given the paper content, it is your job to summarize the paper into a short summary, \n",
-    "and extract authors and paper title from the paper content.\n",
-    "\"\"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "64937339-791c-4aad-953b-ca990bfd324a",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Use Microsoft Fabric's native integration with the MLflow framework to log the trained machine learning models, the used hyperparameters, and evaluation metrics."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "id": "5bac7684-a123-4733-baa3-a748ff0fd070",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.livy.statement-meta+json": {
-       "execution_finish_time": "2024-10-31T04:36:54.8917645Z",
-       "execution_start_time": "2024-10-31T04:36:44.7561664Z",
-       "livy_statement_state": "available",
-       "normalized_state": "finished",
-       "parent_msg_id": "d2abef17-25d7-41c4-a62f-051d9b5fe8d7",
-       "queued_time": "2024-10-31T04:36:44.2999954Z",
-       "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-       "session_start_time": null,
-       "spark_pool": null,
-       "state": "finished",
-       "statement_id": 33,
-       "statement_ids": [
-        33
-       ]
-      },
-      "text/plain": [
-       "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 33, Finished, Available, Finished)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Registered model 'RandomForestRegressionModel' already exists. Creating a new version of this model...\n",
-      "2024/10/31 04:36:52 INFO mlflow.store.model_registry.abstract_store: Waiting up to 300 seconds for model version to finish creation. Model name: RandomForestRegressionModel, version 2\n",
-      "Created version '2' of model 'RandomForestRegressionModel'.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Model Name: RandomForestRegressionModel\n",
-      "Model Version: 2\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.mlflow.run-widget+json": {
-       "data": {
-        "metrics": {},
-        "params": {
-         "n_estimators": "3",
-         "random_state": "42"
-        },
-        "tags": {
-         "mlflow.rootRunId": "20c75f63-d266-40b1-83f7-d9c76fd1f4f4",
-         "mlflow.runName": "icy_hamster_xr34qfzf",
-         "mlflow.user": "4b3a56ea-6f42-450e-b7c3-fb2932c7ac32",
-         "synapseml.experiment.artifactId": "17b41ab7-b0e0-4adc-9fc9-403dd72b6e5b",
-         "synapseml.experimentName": "Notebook-1",
-         "synapseml.livy.id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
-         "synapseml.notebook.artifactId": "789d5fef-b2a1-409b-996f-0cdb4e748a90",
-         "synapseml.user.id": "ea5a1fdc-a08c-493a-bce9-8422f28ecd05",
-         "synapseml.user.name": "System Administrator"
-        }
-       },
-       "info": {
-        "artifact_uri": "sds://onelakewestus3.pbidedicated.windows.net/6361aeaa-b63a-44ea-b28f-26db10b31a6c/17b41ab7-b0e0-4adc-9fc9-403dd72b6e5b/20c75f63-d266-40b1-83f7-d9c76fd1f4f4/artifacts",
-        "end_time": 1730349412,
-        "experiment_id": "d52403ad-a9c2-41ba-b582-9b8e9a57917e",
-        "lifecycle_stage": "active",
-        "run_id": "20c75f63-d266-40b1-83f7-d9c76fd1f4f4",
-        "run_name": "",
-        "run_uuid": "20c75f63-d266-40b1-83f7-d9c76fd1f4f4",
-        "start_time": 1730349405,
-        "status": "FINISHED",
-        "user_id": "7ebfac85-3ebb-440f-a743-e52052051f6a"
-       },
-       "inputs": {
-        "dataset_inputs": []
-       }
-      }
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import mlflow\n",
-    "from mlflow.models import infer_signature\n",
-    "from sklearn.datasets import make_regression\n",
-    "from sklearn.ensemble import RandomForestRegressor\n",
-    "\n",
-    "# Generate synthetic regression data\n",
-    "X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)\n",
-    "\n",
-    "# Model parameters\n",
-    "params = {\"n_estimators\": 3, \"random_state\": 42}\n",
-    "\n",
-    "# Model tags for MLflow\n",
-    "model_tags = {\n",
-    "    \"project_name\": \"grocery-forecasting\",\n",
-    "    \"store_dept\": \"produce\",\n",
-    "    \"team\": \"stores-ml\",\n",
-    "    \"project_quarter\": \"Q3-2023\"\n",
-    "}\n",
-    "\n",
-    "# Log MLflow entities\n",
-    "with mlflow.start_run() as run:\n",
-    "    # Train the model\n",
-    "    model = RandomForestRegressor(**params).fit(X, y)\n",
-    "\n",
-    "    # Infer the model signature\n",
-    "    signature = infer_signature(X, model.predict(X))\n",
-    "\n",
-    "    # Log parameters and the model\n",
-    "    mlflow.log_params(params)\n",
-    "    mlflow.sklearn.log_model(model, artifact_path=\"sklearn-model\", signature=signature)\n",
-    "\n",
-    "    # Register the model with tags\n",
-    "    model_uri = f\"runs:/{run.info.run_id}/sklearn-model\"\n",
-    "    model_version = mlflow.register_model(model_uri, \"RandomForestRegressionModel\", tags=model_tags)\n",
-    "\n",
-    "    # Output model registration details\n",
-    "    print(f\"Model Name: {model_version.name}\")\n",
-    "    print(f\"Model Version: {model_version.version}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "315ebdcd-e78c-4bc5-93d6-f202d02bddc5",
-   "metadata": {
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "source": [
-    "## Use MLflow to search among multiple models saved within the workspace"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "60e6f7d3-d1ec-4ccc-9745-6c7938d2f4bc",
-   "metadata": {
-    "jupyter": {
-     "outputs_hidden": false,
-     "source_hidden": false
-    },
-    "microsoft": {
-     "language": "python",
-     "language_group": "synapse_pyspark"
-    },
-    "nteract": {
-     "transient": {
-      "deleting": false
-     }
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from pprint import pprint\n",
-    "from mlflow.tracking import MlflowClient\n",
-    "\n",
-    "client = MlflowClient()\n",
-    "for rm in client.search_registered_models():\n",
-    "    pprint(dict(rm), indent=4)"
-   ]
-  }
- ],
- "metadata": {
-  "application/vnd.jupyter.widget-state+json": {
-   "version": "1.0"
-  },
-  "dependencies": {
-   "environment": {
-    "environmentId": "766562be-9e21-456c-b270-cac7e4bf8d18",
-    "workspaceId": "6361aeaa-b63a-44ea-b28f-26db10b31a6c"
-   }
-  },
-  "kernel_info": {
-   "name": "synapse_pyspark"
-  },
-  "kernelspec": {
-   "display_name": "Synapse PySpark",
-   "language": "Python",
-   "name": "synapse_pyspark"
-  },
-  "language_info": {
-   "name": "python"
-  },
-  "microsoft": {
-   "language": "python",
-   "language_group": "synapse_pyspark",
-   "ms_spell_check": {
-    "ms_spell_check_language": "en"
-   }
-  },
-  "nteract": {
-   "version": "nteract-front-end@1.0.0"
-  },
-  "spark_compute": {
-   "compute_id": "/trident/default",
-   "session_options": {
-    "conf": {
-     "spark.synapse.nbs.session.timeout": "1200000"
-    }
-   }
-  },
-  "widgets": {
-   "application/vnd.jupyter.widget-state+json": {
-    "state": {},
-    "version": "1.0"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "519955e9-2dad-456d-93db-a332d38e9433",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "# Fabric: Highlights into AI/LLMs"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "d312e8d9-03fe-4b3d-aa6d-c52e3022ae39",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T03:58:26.7170509Z",
+              "execution_start_time": "2024-10-31T03:58:19.270951Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "e267b6ab-5133-4598-8251-d64374cd11e5",
+              "queued_time": "2024-10-31T03:58:18.9132075Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 5,
+              "statement_ids": [
+                5
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 5, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Name: synapseml\r\n",
+            "Version: 1.0.8\r\n",
+            "Summary: Synapse Machine Learning\r\n",
+            "Home-page: https://github.com/Microsoft/SynapseML\r\n",
+            "Author: Microsoft\r\n",
+            "Author-email: synapseml-support@microsoft.com\r\n",
+            "License: MIT\r\n",
+            "Location: /home/trusted-service-user/cluster-env/clonedenv/lib/python3.11/site-packages\r\n",
+            "Requires: \r\n",
+            "Required-by: \r\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip show synapseml"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "id": "427610d0-3fae-45e3-8150-92ee7674f44c",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T03:58:28.6254349Z",
+              "execution_start_time": "2024-10-31T03:58:27.1124616Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "0e9f6c0f-062b-4e5d-9061-afcd89c8fd75",
+              "queued_time": "2024-10-31T03:58:19.3223486Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 6,
+              "statement_ids": [
+                6
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 6, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Name: langchain-openai\r\n",
+            "Version: 0.2.4\r\n",
+            "Summary: An integration package connecting OpenAI and LangChain\r\n",
+            "Home-page: https://github.com/langchain-ai/langchain\r\n",
+            "Author: \r\n",
+            "Author-email: \r\n",
+            "License: MIT\r\n",
+            "Location: /home/trusted-service-user/cluster-env/clonedenv/lib/python3.11/site-packages\r\n",
+            "Requires: langchain-core, openai, tiktoken\r\n",
+            "Required-by: \r\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip show langchain-openai"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "baeeb853-2104-4edf-abf4-4d4be50cb977",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T03:58:30.5465258Z",
+              "execution_start_time": "2024-10-31T03:58:29.0000586Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "716d9975-263b-4d92-b25c-b342106f5f43",
+              "queued_time": "2024-10-31T03:58:19.511824Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 7,
+              "statement_ids": [
+                7
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 7, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Name: langchain\r\n",
+            "Version: 0.3.6\r\n",
+            "Summary: Building applications with LLMs through composability\r\n",
+            "Home-page: https://github.com/langchain-ai/langchain\r\n",
+            "Author: \r\n",
+            "Author-email: \r\n",
+            "License: MIT\r\n",
+            "Location: /home/trusted-service-user/cluster-env/clonedenv/lib/python3.11/site-packages\r\n",
+            "Requires: aiohttp, langchain-core, langchain-text-splitters, langsmith, numpy, pydantic, PyYAML, requests, SQLAlchemy, tenacity\r\n",
+            "Required-by: langchain-community\r\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip show langchain"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "c58cc406-c4f5-4607-a740-0802e8e4b550",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Ensure you have the API key and endpoint URL for your deployed model. Set these as environment variables"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 19,
+      "id": "3c8ada7c-2632-4c69-86d2-f5260ee8f1b7",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:20:14.3495341Z",
+              "execution_start_time": "2024-10-31T04:20:14.1128215Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "2573bf75-fe6d-40dc-b9f6-e06ebb9f7f73",
+              "queued_time": "2024-10-31T04:20:13.6194485Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 22,
+              "statement_ids": [
+                22
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 22, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "import os\n",
+        "\n",
+        "os.environ[\"OPENAI_API_VERSION\"] = \"2023-08-01-preview\"\n",
+        "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"https://your-resource.openai.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2024-08-01-preview\"\n",
+        "os.environ[\"AZURE_OPENAI_API_KEY\"] = \"your-value\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "3fac48a9-45fb-4e86-9792-8ee340b0ac60",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Create an instance of the Azure OpenAI class using the environment variables set above"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 20,
+      "id": "5db10350-8000-4cbd-9bdf-d7da62d7fe61",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:20:14.9382032Z",
+              "execution_start_time": "2024-10-31T04:20:14.7083469Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "7dfaca5a-f738-4010-bba1-f764ea70f450",
+              "queued_time": "2024-10-31T04:20:14.027325Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 23,
+              "statement_ids": [
+                23
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 23, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from langchain_openai import AzureChatOpenAI\n",
+        "\n",
+        "# Set the API base URL\n",
+        "api_base = os.environ[\"AZURE_OPENAI_ENDPOINT\"]\n",
+        "\n",
+        "# Create an instance of the Azure OpenAI Class\n",
+        "llm = AzureChatOpenAI(\n",
+        "    openai_api_key=os.environ[\"AZURE_OPENAI_API_KEY\"],\n",
+        "    temperature=0.7,\n",
+        "    verbose=True,\n",
+        "    top_p=0.9\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "b17d7450-34b5-4ece-8e20-a77ddcdd93c4",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Use the Azure OpenAI service to generate text or perform other language model tasks"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 21,
+      "id": "cfc5fd62-085a-4eff-9192-696d9f249a8e",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:20:16.0500538Z",
+              "execution_start_time": "2024-10-31T04:20:15.2936074Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "e14e4d0b-1fd0-4dac-a07d-6479d6536ce3",
+              "queued_time": "2024-10-31T04:20:14.4969185Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 24,
+              "statement_ids": [
+                24
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 24, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "content='Salut, comment \u00e7a va ?' additional_kwargs={'refusal': None} response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 33, 'total_tokens': 39, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_name': 'gpt-4o-mini', 'system_fingerprint': 'fp_d54531d9eb', 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'protected_material_code': {'filtered': False, 'detected': False}, 'protected_material_text': {'filtered': False, 'detected': False}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}} id='run-8cb7f29a-44c1-4f65-a648-15afb2d793dc-0' usage_metadata={'input_tokens': 33, 'output_tokens': 6, 'total_tokens': 39, 'input_token_details': {}, 'output_token_details': {}}\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Define a prompt\n",
+        "messages = [\n",
+        "    (\n",
+        "        \"system\",\n",
+        "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+        "    ),\n",
+        "    (\"human\", \"Hi, how are you?\"),\n",
+        "]\n",
+        "\n",
+        "# Generate a response from the Azure OpenAI service using the invoke method\n",
+        "ai_msg = llm.invoke(messages)\n",
+        "\n",
+        "# Print the response\n",
+        "print(ai_msg)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "79729106-c7f1-4879-bc2b-871b50c2ac9a",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Define a prompt template for generating definitions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 22,
+      "id": "ca633361-c27b-4294-b8a7-9fc4a316afa4",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:20:16.587491Z",
+              "execution_start_time": "2024-10-31T04:20:16.3655978Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "cc3215f4-71a5-4231-af47-9bd9a8f5698a",
+              "queued_time": "2024-10-31T04:20:14.7799392Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 25,
+              "statement_ids": [
+                25
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 25, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from langchain.prompts import PromptTemplate\n",
+        "\n",
+        "copy_prompt = PromptTemplate(\n",
+        "    input_variables=[\"technology\"],\n",
+        "    template=\"Define the following word: {technology}\",\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "899839d9-adca-4042-b662-73edcad7e432",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Create an LLMChain with the defined prompt template"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 23,
+      "id": "bd4f65ca-049b-481d-bbbd-a017c6c0119b",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:20:17.1233668Z",
+              "execution_start_time": "2024-10-31T04:20:16.9052959Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "27790d83-509f-4716-bb69-9c288ad069ba",
+              "queued_time": "2024-10-31T04:20:15.1325692Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 26,
+              "statement_ids": [
+                26
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 26, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from langchain.chains import LLMChain\n",
+        "\n",
+        "chain = LLMChain(llm=llm, prompt=copy_prompt)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "936b3ddf-cc65-436c-ba4e-ae0abe21fc2c",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Set up the LangChain transformer to execute the processing chain\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 24,
+      "id": "63a00038-37b4-49ee-9c53-128c8acf9d01",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:20:18.181457Z",
+              "execution_start_time": "2024-10-31T04:20:17.4351576Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "3fb30420-f0c9-477b-ad1a-001dc0d8d37a",
+              "queued_time": "2024-10-31T04:20:15.6799013Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 27,
+              "statement_ids": [
+                27
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 27, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from synapse.ml.cognitive.langchain import LangchainTransformer\n",
+        "\n",
+        "openai_api_key= os.environ[\"AZURE_OPENAI_API_KEY\"]\n",
+        "\n",
+        "transformer = (\n",
+        "    LangchainTransformer()\n",
+        "    .setInputCol(\"technology\")\n",
+        "    .setOutputCol(\"definition\")\n",
+        "    .setChain(chain)\n",
+        "    .setSubscriptionKey(openai_api_key)\n",
+        "    .setUrl(api_base)\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "c74293f0-925e-4987-a6a1-b3b9b8e14b9d",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Construct a DataFrame with technology names."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 26,
+      "id": "8e03963e-2fcf-4934-b96f-ac27b4e0353c",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:24:08.3891172Z",
+              "execution_start_time": "2024-10-31T04:24:02.0675933Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "856f5b73-26e8-4d20-a901-356cd92b9c2a",
+              "queued_time": "2024-10-31T04:24:01.6603792Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 29,
+              "statement_ids": [
+                29
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 29, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "+-----+----------+----------------------+\n",
+            "|label|technology|transformed_technology|\n",
+            "+-----+----------+----------------------+\n",
+            "|    0|    docker|                DOCKER|\n",
+            "|    1|     spark|                 SPARK|\n",
+            "|    2|    python|                PYTHON|\n",
+            "+-----+----------+----------------------+\n",
+            "\n"
+          ]
+        }
+      ],
+      "source": [
+        "from pyspark.sql import SparkSession\n",
+        "from pyspark.sql.functions import udf\n",
+        "from pyspark.sql.types import StringType\n",
+        "\n",
+        "# Initialize Spark session\n",
+        "spark = SparkSession.builder.appName(\"example\").getOrCreate()\n",
+        "\n",
+        "# Construct a DataFrame with technology names\n",
+        "df = spark.createDataFrame(\n",
+        "    [\n",
+        "        (0, \"docker\"), (1, \"spark\"), (2, \"python\")\n",
+        "    ],\n",
+        "    [\"label\", \"technology\"]\n",
+        ")\n",
+        "\n",
+        "# Define a simple UDF to transform the technology column\n",
+        "def transform_technology(tech):\n",
+        "    return tech.upper()\n",
+        "\n",
+        "# Register the UDF\n",
+        "transform_udf = udf(transform_technology, StringType())\n",
+        "\n",
+        "# Apply the UDF to the DataFrame\n",
+        "transformed_df = df.withColumn(\"transformed_technology\", transform_udf(df[\"technology\"]))\n",
+        "\n",
+        "# Show the transformed DataFrame\n",
+        "transformed_df.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "47ab1ba6-deaf-488d-9e95-8202669d948c",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Extract content from PDFs linked in arXiv papers and generate prompts for extracting specific information.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 27,
+      "id": "8b52c87e-5971-4d28-bc4b-4160d29a1c24",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:27:08.3224773Z",
+              "execution_start_time": "2024-10-31T04:27:08.0430507Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "4eeab690-4159-41dc-be69-3cceed484314",
+              "queued_time": "2024-10-31T04:27:07.6309068Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 30,
+              "statement_ids": [
+                30
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 30, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from langchain.document_loaders import OnlinePDFLoader\n",
+        "\n",
+        "def paper_content_extraction(inputs: dict) -> dict:\n",
+        "    arxiv_link = inputs[\"arxiv_link\"]\n",
+        "    loader = OnlinePDFLoader(arxiv_link)\n",
+        "    pages = loader.load_and_split()\n",
+        "    return {\"paper_content\": pages[0].page_content + pages[1].page_content}\n",
+        "\n",
+        "def prompt_generation(inputs: dict) -> dict:\n",
+        "    output = inputs[\"Output\"]\n",
+        "    prompt = (\n",
+        "        \"find the paper title, author, summary in the paper description below, output them. \"\n",
+        "        \"After that, Use websearch to find out 3 recent papers of the first author in the author section below \"\n",
+        "        \"(first author is the first name separated by comma) and list the paper titles in bullet points: \"\n",
+        "        \"<Paper Description Start>\\n\" + output + \"<Paper Description End>.\"\n",
+        "    )\n",
+        "    return {\"prompt\": prompt}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "89d79c38-ba0c-4062-911c-7ede02536298",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Set up a chain to extract structured information from an arXiv link\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 28,
+      "id": "e85241a0-11c2-49c1-9b2e-63187cb24d9a",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:28:11.2331925Z",
+              "execution_start_time": "2024-10-31T04:28:11.0134852Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "232b4aa0-1b84-47f8-bb5d-347a575d9640",
+              "queued_time": "2024-10-31T04:28:10.663514Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 31,
+              "statement_ids": [
+                31
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 31, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from langchain.chains import TransformChain, SimpleSequentialChain\n",
+        "\n",
+        "paper_content_extraction_chain = TransformChain(\n",
+        "    input_variables=[\"arxiv_link\"],\n",
+        "    output_variables=[\"paper_content\"],\n",
+        "    transform=paper_content_extraction,\n",
+        "    verbose=False,\n",
+        ")\n",
+        "\n",
+        "paper_summarizer_template = \"\"\"\n",
+        "You are a paper summarizer, given the paper content, it is your job to summarize the paper into a short summary, \n",
+        "and extract authors and paper title from the paper content.\n",
+        "\"\"\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "64937339-791c-4aad-953b-ca990bfd324a",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Use Microsoft Fabric's native integration with the MLflow framework to log the trained machine learning models, the used hyperparameters, and evaluation metrics."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 30,
+      "id": "5bac7684-a123-4733-baa3-a748ff0fd070",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.livy.statement-meta+json": {
+              "execution_finish_time": "2024-10-31T04:36:54.8917645Z",
+              "execution_start_time": "2024-10-31T04:36:44.7561664Z",
+              "livy_statement_state": "available",
+              "normalized_state": "finished",
+              "parent_msg_id": "d2abef17-25d7-41c4-a62f-051d9b5fe8d7",
+              "queued_time": "2024-10-31T04:36:44.2999954Z",
+              "session_id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+              "session_start_time": null,
+              "spark_pool": null,
+              "state": "finished",
+              "statement_id": 33,
+              "statement_ids": [
+                33
+              ]
+            },
+            "text/plain": [
+              "StatementMeta(, 7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325, 33, Finished, Available, Finished)"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Registered model 'RandomForestRegressionModel' already exists. Creating a new version of this model...\n",
+            "2024/10/31 04:36:52 INFO mlflow.store.model_registry.abstract_store: Waiting up to 300 seconds for model version to finish creation. Model name: RandomForestRegressionModel, version 2\n",
+            "Created version '2' of model 'RandomForestRegressionModel'.\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Model Name: RandomForestRegressionModel\n",
+            "Model Version: 2\n"
+          ]
+        },
+        {
+          "data": {
+            "application/vnd.mlflow.run-widget+json": {
+              "data": {
+                "metrics": {},
+                "params": {
+                  "n_estimators": "3",
+                  "random_state": "42"
+                },
+                "tags": {
+                  "mlflow.rootRunId": "20c75f63-d266-40b1-83f7-d9c76fd1f4f4",
+                  "mlflow.runName": "icy_hamster_xr34qfzf",
+                  "mlflow.user": "4b3a56ea-6f42-450e-b7c3-fb2932c7ac32",
+                  "synapseml.experiment.artifactId": "17b41ab7-b0e0-4adc-9fc9-403dd72b6e5b",
+                  "synapseml.experimentName": "Notebook-1",
+                  "synapseml.livy.id": "7383b5d4-1dea-4b9b-85d6-fe5ef5b7d325",
+                  "synapseml.notebook.artifactId": "789d5fef-b2a1-409b-996f-0cdb4e748a90",
+                  "synapseml.user.id": "ea5a1fdc-a08c-493a-bce9-8422f28ecd05",
+                  "synapseml.user.name": "System Administrator"
+                }
+              },
+              "info": {
+                "artifact_uri": "sds://onelakewestus3.pbidedicated.windows.net/6361aeaa-b63a-44ea-b28f-26db10b31a6c/17b41ab7-b0e0-4adc-9fc9-403dd72b6e5b/20c75f63-d266-40b1-83f7-d9c76fd1f4f4/artifacts",
+                "end_time": 1730349412,
+                "experiment_id": "d52403ad-a9c2-41ba-b582-9b8e9a57917e",
+                "lifecycle_stage": "active",
+                "run_id": "20c75f63-d266-40b1-83f7-d9c76fd1f4f4",
+                "run_name": "",
+                "run_uuid": "20c75f63-d266-40b1-83f7-d9c76fd1f4f4",
+                "start_time": 1730349405,
+                "status": "FINISHED",
+                "user_id": "7ebfac85-3ebb-440f-a743-e52052051f6a"
+              },
+              "inputs": {
+                "dataset_inputs": []
+              }
+            }
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "import mlflow\n",
+        "from mlflow.models import infer_signature\n",
+        "from sklearn.datasets import make_regression\n",
+        "from sklearn.ensemble import RandomForestRegressor\n",
+        "\n",
+        "# Generate synthetic regression data\n",
+        "X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)\n",
+        "\n",
+        "# Model parameters\n",
+        "params = {\"n_estimators\": 3, \"random_state\": 42}\n",
+        "\n",
+        "# Model tags for MLflow\n",
+        "model_tags = {\n",
+        "    \"project_name\": \"grocery-forecasting\",\n",
+        "    \"store_dept\": \"produce\",\n",
+        "    \"team\": \"stores-ml\",\n",
+        "    \"project_quarter\": \"Q3-2023\"\n",
+        "}\n",
+        "\n",
+        "# Log MLflow entities\n",
+        "with mlflow.start_run() as run:\n",
+        "    # Train the model\n",
+        "    model = RandomForestRegressor(**params).fit(X, y)\n",
+        "\n",
+        "    # Infer the model signature\n",
+        "    signature = infer_signature(X, model.predict(X))\n",
+        "\n",
+        "    # Log parameters and the model\n",
+        "    mlflow.log_params(params)\n",
+        "    mlflow.sklearn.log_model(model, artifact_path=\"sklearn-model\", signature=signature)\n",
+        "\n",
+        "    # Register the model with tags\n",
+        "    model_uri = f\"runs:/{run.info.run_id}/sklearn-model\"\n",
+        "    model_version = mlflow.register_model(model_uri, \"RandomForestRegressionModel\", tags=model_tags)\n",
+        "\n",
+        "    # Output model registration details\n",
+        "    print(f\"Model Name: {model_version.name}\")\n",
+        "    print(f\"Model Version: {model_version.version}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "315ebdcd-e78c-4bc5-93d6-f202d02bddc5",
+      "metadata": {
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "## Use MLflow to search among multiple models saved within the workspace"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "60e6f7d3-d1ec-4ccc-9745-6c7938d2f4bc",
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "microsoft": {
+          "language": "python",
+          "language_group": "synapse_pyspark"
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [],
+      "source": [
+        "from pprint import pprint\n",
+        "from mlflow.tracking import MlflowClient\n",
+        "\n",
+        "client = MlflowClient()\n",
+        "for rm in client.search_registered_models():\n",
+        "    pprint(dict(rm), indent=4)"
+      ]
+    }
+  ],
+  "metadata": {
+    "application/vnd.jupyter.widget-state+json": {
+      "version": "1.0"
+    },
+    "dependencies": {
+      "environment": {
+        "environmentId": "766562be-9e21-456c-b270-cac7e4bf8d18",
+        "workspaceId": "6361aeaa-b63a-44ea-b28f-26db10b31a6c"
+      }
+    },
+    "kernel_info": {
+      "name": "synapse_pyspark"
+    },
+    "kernelspec": {
+      "display_name": "Synapse PySpark",
+      "language": "Python",
+      "name": "synapse_pyspark"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "microsoft": {
+      "language": "python",
+      "language_group": "synapse_pyspark",
+      "ms_spell_check": {
+        "ms_spell_check_language": "en"
+      }
+    },
+    "nteract": {
+      "version": "nteract-front-end@1.0.0"
+    },
+    "spark_compute": {
+      "compute_id": "/trident/default",
+      "session_options": {
+        "conf": {
+          "spark.synapse.nbs.session.timeout": "1200000"
+        }
+      }
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "state": {},
+        "version_major": 2,
+        "version_minor": 0
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
\ No newline at end of file
diff --git a/AzurePortal/3_AISkills.md b/AzurePortal/3_AISkills.md
index a2ac1f2..aaecd13 100644
--- a/AzurePortal/3_AISkills.md
+++ b/AzurePortal/3_AISkills.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ----------
 
@@ -99,7 +99,7 @@ Key Features:
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/AzurePortal/4_CICD/0_deployment-pipelines/README.md b/AzurePortal/4_CICD/0_deployment-pipelines/README.md
index 180585a..058bccc 100644
--- a/AzurePortal/4_CICD/0_deployment-pipelines/README.md
+++ b/AzurePortal/4_CICD/0_deployment-pipelines/README.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -196,7 +196,7 @@ Steps to Set Up Incremental Refresh:
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/AzurePortal/4_CICD/0_deployment-pipelines/samples/README.md b/AzurePortal/4_CICD/0_deployment-pipelines/samples/README.md
index 7abe2d4..435e6e0 100644
--- a/AzurePortal/4_CICD/0_deployment-pipelines/samples/README.md
+++ b/AzurePortal/4_CICD/0_deployment-pipelines/samples/README.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -14,7 +14,7 @@ Last updated: 2025-07-16
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/AzurePortal/4_CICD/1_github-integration.md b/AzurePortal/4_CICD/1_github-integration.md
index 9c754d5..f6f3151 100644
--- a/AzurePortal/4_CICD/1_github-integration.md
+++ b/AzurePortal/4_CICD/1_github-integration.md
@@ -6,7 +6,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ----------
 
@@ -64,7 +64,7 @@ https://github.com/user-attachments/assets/64f099a1-b749-47a6-b723-fa1cb5c575a3
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/README.md b/README.md
index cf4c702..f72cdce 100644
--- a/README.md
+++ b/README.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -24,7 +24,6 @@ Last updated: 2025-07-16
 
 </details>
 
-
 For this workshop, you can set up your infrastructure using either of the following approaches:
 
 1. [Infrastructure via Azure Portal](./AzurePortal/): This approach involves creating the infrastructure and performing `all necessary steps through the Azure Portal` and its resources interface. 
@@ -72,7 +71,7 @@ This is an introductory workshop on Microsoft Fabric. Please follow as described
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/Terraform/README.md b/Terraform/README.md
index a31bab3..3dff5c2 100644
--- a/Terraform/README.md
+++ b/Terraform/README.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -143,7 +143,7 @@ https://github.com/user-attachments/assets/1ab31707-6f4c-4ec7-9e92-5d5cc96ac5bb
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->
diff --git a/Terraform/troubleshooting.md b/Terraform/troubleshooting.md
index 687daea..2d4994c 100644
--- a/Terraform/troubleshooting.md
+++ b/Terraform/troubleshooting.md
@@ -5,7 +5,7 @@ Costa Rica
 [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
 [brown9804](https://github.com/brown9804)
 
-Last updated: 2025-07-16
+Last updated: 2025-09-11
 
 ------------------------------------------
 
@@ -176,7 +176,7 @@ Error: Failed to get existing workspaces: Error retrieving keys for Storage Acco
 
 <!-- START BADGE -->
 <div align="center">
-  <img src="https://img.shields.io/badge/Total%20views-522-limegreen" alt="Total views">
-  <p>Refresh Date: 2025-07-16</p>
+  <img src="https://img.shields.io/badge/Total%20views-1474-limegreen" alt="Total views">
+  <p>Refresh Date: 2025-09-11</p>
 </div>
 <!-- END BADGE -->