How to Create and Manage a Microsoft Teams Copilot Agent

Creating and managing a Teams Copilot Agent can significantly enhance your team's productivity and streamline various tasks. In this blog post, we'll walk you through the steps to set up and configure your agent, along with some useful tips to optimize its performance.

Pre-requisites

Before you start, ensure you have access to Copilot in Teams. You may need to be part of the ACL Group that manages access to the agent. Additionally, users in this group must have access to the SharePoint folder where the source data is located.

Step-by-Step Guide

1. Navigate to Copilot in Teams

In Teams, go to the Copilot section under "Chats."

2. Create an Agent

Click on "Create an Agent" and then select "Configure."

3. Select a Template

You can choose a template that will auto-populate instructions and other fields. These instructions essentially define the persona your agent will assume.

Tip: Pick a template of the kind of agent you want, then place the instructions template in ChatGPT or Copilot or OCI Gen AI and ask it to create a persona based on a given context of your choosing.

4. Point the Agent at Source Data

In the "Knowledge" section, point the agent at the source data. Place the files that will serve as the content for the agent in SharePoint or Teams. You can add up to 20 sources in SharePoint.

Tip: Avoid versioning files; store the latest version of the document. Organize the content and folders the agent is pointing to for higher accuracy.

5. Configure Agent Capabilities

If you want to build an agent that generates images or writes code exclusively, check the respective boxes. For a general-purpose conversational agent, leave these boxes unchecked.

6. Set Starter Prompts

These are prompts users will see when they start a conversation with the agent. You can hardcode common prompts to get users started.

7. Create the Agent

Once all the information is filled out, hit "Create" (top right).

8. Set Access Controls

Enter the ACLs to expose the agent to specific users. Copy the link to the agent and share it with the people who will access it (they also need to have Copilot).

Tip: Individual users may not work depending on your company policies; only ACL groups.

Editing an Agent

To edit an agent, go back to "Create an Agent," click on "View all agents," and navigate to the one you want to edit. You can change the instructions or access settings as needed.

If you are using Microsoft Teams, you can create very useful Agents on top of your existing data and make research, discovery and troubleshooting more engaging, it is a great way to assist new employees or help enhance productivity in general!

Oracle Application Express (APEX) - Generative AI Capabilities

Oracle Application Express (APEX) continues to revolutionize the way developers create web applications with its new Generative AI assistant. This cutting-edge feature integrates artificial intelligence into APEX’s low-code environment, allowing developers to accelerate the development process like never before. With the APEX Generative AI assistant, users can now generate SQL queries, PL/SQL and JavaScript code, and even create applications simply by describing their requirements in plain language. This means less time spent writing code and more time focused on refining application logic and design.

By bridging the gap between natural language and complex code generation, the AI assistant significantly reduces the learning curve for new developers while enhancing the efficiency of experienced ones. As Oracle APEX continues to evolve, the inclusion of AI-powered features sets a new standard for rapid application development, providing a powerful toolset that enhances productivity and creativity across all skill levels.

This introduction of generative AI in APEX showcases Oracle’s commitment to integrating advanced technologies that make development more accessible, efficient, and intuitive. Whether you're a seasoned developer or just beginning your journey with APEX, the Generative AI assistant opens up new possibilities for creating robust, data-rich applications faster than ever before.

Let us take a look at how to setup the Generative AI feature and what are some of the uses cases!

Note: click the images below to expand them for ease of use and readability! 

Setup

In order to take advantage of these features, we need to allow APEX to interact with an LLM via the API layer, and to do that we want to navigate to the "Workspace Utilities" area then select the "Generative AI" option.

Once we are there, you can create a trust between your APEX instance and an LLM, in the screenshot below we see the trust setup with Open AI, using an API key that I have access to, and I also show the options available to you besides Open AI, which are Cohere and Oracle's OCI Generative AI Service (which I recommend specially if you already use Oracle Cloud Infrastructure, to take advantage of all the security you already have in place in your Virtual Cloud Network!).

APEX Assistant - SQL Workshop

Now for the exciting part! Within the SQL Workshop, you will see an option to click on the "APEX Assistant" which will open a panel on the right side, allowing you to access the query builder feature!

In the above we see the assistant joining two tables for us, in this example! We simply asked whether two tables in the current schema could be joined, and it provided the SQL statement to do just that! This can be very useful when seeking assistance in writing complex SQL for a data lineage you may not be very familiar with, and it is also something you cannot easily accomplish in another tool, like Chat GPT, because the APEX Assistant has access to the metadata in your database directly, making things easier!

Besides the query builder feature, we have the general assistance mode, where we can ask it to develop code for us, modify and optimize code, etc. In this example we ask it to write a PLSQL stored procedure:

Notice how the "insert" feature will drop the code provided into your development canvas automatically!

In this next example, we switched the language to JavaScript, and asked a question a bit more complex:

Create Applications using Gen AI

Besides the AI Assistant in the SQL Workshop, there's another very useful feature, this time in the App Builder!

Here another option is introduced, to use a conversational agent to generate apps, in addition to existing options like creating an app from a file!

This is a powerful feature to get you started with your application, and I am excited to see how it evolves in the feature allowing for more customization and increased usability, but it is definitely a step in the right direction!

Conclusion

As we saw, there's plenty of new features to be excited about in the way of Generative AI within APEX, and I am very excited to see how these features evolve over time, but they are certainly already powerful, particularly the Assistant in the SQL Workshop, and if you use APEX already, there is no reason not to jump on these very cool features!

UML Diagrams For Productivity and Clarity

Following up on the last two entries regarding using Python to interact with Oracle MySQL and Oracle Linux, I want to introduce a tool called PlantUML, which is a fantastic tool for creating visual aids to help your development journey, and we will create a simple UML diagram for the Python UI that we discussed in the last entry, for monitoring various services. We will also take a look at a couple of Class Diagrams for a couple of Kafka Consumer and Producer services.

Before getting to the diagram and the UML code, let's talk about how to run PlantUML locally on your machine using VS Code.

VS Code

Install VS code, it’s free.

https://code.visualstudio.com/download

Plant UML Extension

In VS code, go to the extensions marketplace, and install the PlantUML Extension.

You also need to have Java JRE on your machine, install that as well from: https://www.java.com/en/download/manual.jsp

Diagram Previews

To use it, create a new text file in VS Code, and then select PlantUml as the language. Then paste the UML code, and hit “alt + d”, to open the preview screen. You can then copy images.

Now, let's look at some examples, including one following up on our Python Monitoring UI referenced in the last blog entry.

UI Diagram

@startuml

!define RECTANGLE_SIZE_SIZE_RECTANGLE 12

skinparam componentStyle rectangle

skinparam rectangle {

  BackgroundColor<<main>> LightGray

  BackgroundColor<<option>> White

  BorderColor<<main>> Black

  BorderColor<<option>> Gray

}

rectangle "Python UI - Homepage" <<main>> {

    rectangle "Kafka Status" <<option>> 

    rectangle "Zookeeper Status" <<option>> 

    rectangle "MySQL Status" <<option>> 

    rectangle "Map View" <<option>> 

}

@enduml

Class Diagram - Consumer

Diagram depicting a consumer service in a Kafka architecture for a vehicle telemetry system.

@startuml

class KafkaConsumer {

    +consumeMessage()

    +parseJSON(String message)

    +processData(SchoolBusData busData)

}

class SchoolBusData {

    +happenedAtTime: String

    +assetId: String

    +latitude: float

    +longitude: float

    +headingDegrees: int

    +accuracyMeters: float

    +gpsSpeedMetersPerSecond: float

    +ecuSpeedMetersPerSecond: float

}

class DatabaseConnector {

    +insertSchoolBusData(SchoolBusData busData)

}

KafkaConsumer --> SchoolBusData : Parses

KafkaConsumer --> DatabaseConnector : Inserts into

DatabaseConnector --> MySQLDatabase : Stores

 

class MySQLDatabase {

    +save()

}

@enduml

Class Diagram - Producer

@startuml

class KafkaProducer {

    +produceMessage()

    +serializeToJSON(SchoolBusData busData)

    +sendToKafka(String jsonMessage)

}

class SchoolBusData {

    +happenedAtTime: String

    +assetId: String

    +latitude: float

    +longitude: float

    +headingDegrees: int

    +accuracyMeters: float

    +gpsSpeedMetersPerSecond: float

    +ecuSpeedMetersPerSecond: float

    +generateSampleData(): SchoolBusData

}

KafkaProducer --> SchoolBusData : Generates

KafkaProducer --> KafkaTopic : Sends message

class KafkaTopic {

    +receiveMessage(String jsonMessage)

}

@enduml

These are a couple of types of diagrams that you can create using PlantUML in VS Code, in another entry we will be covering a couple of different diagrams, including a sequence diagram, regarding a proposed architecture for getting data out of Oracle Fusion Cloud.

Oracle Linux and MySQL, Kafka and Python Flask Monitoring API

In this entry we will dig deeper into the previous post that dealt with invoking an Oracle MySQL stored procedure using Python. The focus of this entry is creating a Python API to monitor Kafka and MySQL running on an Oracle Linux VM. This API can be invoked from a User Interface that will allow the user to check the statuses of these different components.

To create a Python API that will execute the commands on your Oracle Linux or RHEL system to check the status of MySQL, Zookeeper, and Kafka, you can use the subprocess module in Python to run shell commands. 

Below is an example of how you can implement this.

Step-by-Step Implementation:

• Create Python Functions to Check Status: Each function will execute the corresponding system command using subprocess.run and return the output.
• Set Up Flask API: We'll use Flask to create a simple API that the UI can call to retrieve the status.

Python Code:

import subprocess
from flask import Flask, jsonify
app = Flask(__name__)

# Function to check MySQL status
def check_mysql_status():
try:
result = subprocess.run(['sudo', 'systemctl', 'status', 'mysqld'], capture_output=True, text=True)
return result.stdout
except subprocess.CalledProcessError as e:
return str(e)

# Function to check Zookeeper status
def check_zookeeper_status():
try:
result = subprocess.run(['sudo', 'systemctl', 'status', 'zookeeper'], capture_output=True, text=True)
return result.stdout
except subprocess.CalledProcessError as e:
return str(e)

# Function to check Kafka status
def check_kafka_status():
try:
result = subprocess.run(['sudo', 'systemctl', 'status', 'kafka'], capture_output=True, text=True)
return result.stdout
except subprocess.CalledProcessError as e:
return str(e)

# Flask API route to get MySQL status
@app.route('/status/mysql', methods=['GET'])
def get_mysql_status():
status = check_mysql_status()
return jsonify({'service': 'MySQL', 'status': status})

# Flask API route to get Zookeeper status
@app.route('/status/zookeeper', methods=['GET'])
def get_zookeeper_status():
status = check_zookeeper_status()
return jsonify({'service': 'Zookeeper', 'status': status})

# Flask API route to get Kafka status
@app.route('/status/kafka', methods=['GET'])
def get_kafka_status():
status = check_kafka_status()
return jsonify({'service': 'Kafka', 'status': status})

if __name__ == "__main__":
app.run(host='0.0.0.0', port=5000)

Explanation:

• subprocess.run: Executes the systemctl commands to check the status of MySQL, Zookeeper, and Kafka. The capture_output=True argument captures the output, while text=True ensures the output is returned as a string.
• Flask: Provides an API endpoint for each service, which the UI can call to check the respective statuses.
• Routes: Each API route (/status/mysql, /status/zookeeper, /status/kafka) responds to a GET request and returns the status of the requested service in JSON format.

Running the API:

To run the Flask API, ensure Flask is installed:

pip install Flask

To Start the Application:

python your_script_name.py

Creating the UI:

For the UI, you can use any front-end technology (HTML, React, etc.) and have buttons that call these API endpoints to display the status of each service.

For example:

• A button for MySQL could call /status/mysql.
• A button for Kafka could call /status/kafka.
• A button for Zookeeper could call /status/zookeeper.

Note on Permissions:

Ensure that the user running the Python script has the appropriate permissions to run the systemctl commands using sudo. You may need to modify the sudoers file to allow passwordless sudo for these commands.

Connecting to an Oracle MySQL Database and Invoking a Stored Procedure using Python

In this entry, we will explore how to use Python to connect to an Oracle MySQL database and invoke a stored procedure. This is particularly useful when you're looking to interact with your database programmatically—whether it's for inserting data, querying, or managing business logic through stored procedures.

We will walk through a Python script that connects to the database, generates some random test data, in this case telemetry data for school busses, and invokes a stored procedure to insert the data into multiple tables. Below is the full Python code, and we’ll break down each part of the code in detail to help you understand how it works.

This assumes that you have Oracle MySQL Running, a stored procedure to call, and the proper credentials to access your database, you can modify this script and use a stored procedure of your own!

Here's the full Python script that connects to the MySQL database, generates random test data, and calls the stored procedure InsertEvents.

Script:

import mysql.connector

from mysql.connector import errorcode

import random

import datetime

# Database connection parameters

config = {

    'user': 'yourusername',

    'password': 'yourpassword',

    'host': 'ip address of vm running mysql',

    'port': port you are using,

    'database': 'name of your mysql database',

}

# Function to generate random test data

def generate_test_data():

    asset_id = random.randint(1000, 9999)

    happened_at_time = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')

    latitude = round(random.uniform(-90, 90), 6)

    longitude = round(random.uniform(-180, 180), 6)

    heading_degrees = random.randint(0, 360)

    accuracy_meters = round(random.uniform(0.5, 20.0), 2)

    geofence = 'TestGeofence' + str(random.randint(1, 100))

    gps_speed = round(random.uniform(0, 30), 2)

    ecu_speed = round(random.uniform(0, 30), 2)

    return (asset_id, happened_at_time, latitude, longitude, heading_degrees, accuracy_meters, geofence, gps_speed, ecu_speed)

# Function to insert event data by calling the stored procedure InsertEvents

def insert_event_data(cursor, data):

    try:

        cursor.callproc('InsertEvents', data)

        print(f"Successfully inserted event for asset_id {data[0]}")

    except mysql.connector.Error as err:

        print(f"Error: {err}")

        return False

    return True

# Main function to connect to the database and insert events

def main():

    try:

        # Connect to the database

        cnx = mysql.connector.connect(**config)

        cursor = cnx.cursor()

        # Ask the user how many events to generate

        num_events = int(input("Enter the number of events to generate: "))

        # Generate and insert the specified number of test events

        for _ in range(num_events):

            test_data = generate_test_data()

            if insert_event_data(cursor, test_data):

                cnx.commit()

            else:

                cnx.rollback()

        cursor.close()

        cnx.close()

    except mysql.connector.Error as err:

        if err.errno == errorcode.ER_ACCESS_DENIED_ERROR:

            print("Something is wrong with your username and/or password")

        elif err.errno == errorcode.ER_BAD_DB_ERROR:

            print("Database does not exist or is not reachable")

        else:

            print(err)

if __name__ == "__main__":

    main()

Inserting data using the stored procedure:

The insert_event_data() function calls the stored procedure InsertEvents and passes in the data.

cursor.callproc('InsertEvents', data): This method invokes the stored procedure InsertEvents with the data tuple as input parameters.

If the procedure is successful, a success message is printed; otherwise, an error message is displayed.

Connecting to the MySQL Database:

The main () function handles the database connection and inserts a user-specified number of events.

The mysql.connector.connect(**config) establishes a connection to the MySQL database using the provided configuration.

The script asks the user to input the number of events they wish to generate (this will prompt the user in the console).

It then generates the random data and inserts it by invoking the stored procedure. The transactions are committed or rolled back based on whether the insertion was successful.

To run the script:

Make sure your database connection parameters are correct.

Ensure that the stored procedure, like InsertEvents, is defined in your MySQL database.

Run the Python script, which will prompt you to enter the number of events to generate and insert them into the database.

Wrapping up:

This script demonstrates a simple yet powerful way to connect to an Oracle MySQL database using Python and invoke a stored procedure. With a little adjustment, you can use it for various operations, such as fetching data, updating records, or automating tasks. By leveraging Python and MySQL Connector, you can efficiently manage your data and workflows, at no cost! Remember that you can create an always free account in Oracle Cloud Infrastructure (OCI), and provision an always free Compute instance, I recommend Linux and then running MySQL and Python there, all free!

Oracle Rest Dataservices (ORDS) - An Introduction, Use Cases and Examples

Oracle Rest Dataservices (ORDS) is truly an underrated feature of the Oracle Database, and now with it being an embedded feature in the Cloud Autonomous Databases, it's truly a feature that is a MUST!

Click on the images to zoom in!

So what? How is it useful? Well, here is a use case where Oracle Integration Cloud is interfacing with Visual Builder to push and pull data from the VBCS Business Objects (BO's) using the REST API layer on the BO's. This is a real use case that many Oracle clients have, specially those that implemented OIC and VBCS back in the Gen 1 days, and using the REST support at the BO layer was the best approach to integrate with VBCS.

In the above we can see that the individual calls to update BO attributes can take a long time, because OIC is iterating through a lot of data, making decisions and making updates. There's also plenty of opportunities for disruption during the API chains, and retriggering is far too complex.

Let us know observe the same scenario, but utilizing ORDS instead:

As noted above, this is far simpler, performs better, less failure points, easier to maintain and support, this is the power of ORDS!

It is a perfect match for VBCS because visual builder wants to speak REST, and ORDS provides an excellent opportunity for that to happen while also taking advantage of the power of the stored procedures to manipulate the BO's at the database level without hitting the VBCS middle tier and relying on complex API interactions.

Below are some additional use cases:

To expand further on the above:

VBCS calls a logging/audit stored procedure exposed as REST via ORDS, to log exceptions being raised in the action chains in VBCS (blocks of code), because right now we have to have user sessions and capture the problem real time via dev tools, unless the message is being handled and shown to the user on the screen, and a lot of them are not, so this is a great way to be proactive and see trends of errors and warnings from user activity.

Many are in the process of replacing BIP reports being used as custom API’s and called from VBCS (which is a common pattern that many have used), by instead utilizing ERP/HCM API’s where feasible, but there's always cases where we will still need to use BIP in this manner, because API support doesn't have the columns or filters required, or the API may just not exist, as an example.

My recommendation here is to instead schedule the BIP extracts and load the data to the VBCS ATP (if you have your own tenant database for VBCS, which you should), then create stored procedures to retrieve it from VBCS via REST, and that way you do not hammer ERP/HCM via the BIP layer, and just hit it once when the scheduled job runs instead. If you don't use VBCS but extract data out of ERP/HCM into your own downstream database, you can do the same rather than allowing direct API traffic into ERP/HCM, and this isn't limited to BIP extracts. Meaning, you can extract data from Fusion using BICC, and other means better than BIP, into a warehouse or data lake and then use ORDS to create an API layer for systems, if the frequency of data needs align.

Lastly, the below talks about the simplicity of deploying ORDS assets, which is very important due to stringent requirements from TO Security around code quality scanning and vulnerabilities with tools like SonarQube. Since ORDS and APEX when exported are just SQL and PLSQL files, there's not much to be concerned about, unlike with high code frameworks with extensive projects with hundreds of files in the build artifacts).

ORDS is an excellent tool on it's own right, and when paired with APEX it can do wonders, but that's a topic for another day!