Welcome to Transactional Machine Learning (TML) and TML Solution Studio (TSS) Documentation!

Building Real-Time Solutions to Process the World’s Real-Time data with, entity-based, TML and Multi-Agentic AI

TSS is a revolutionary platform for building, entity-based, enterprise-ready, process-driven, advanced, scalable, intelligent real-time TML solutions with NO CODE using Pre-Written 10 Apache Airflow DAGs To Speed Up TML Solution Builds - within minutes - what can take organizations up to 6 months to build.

IDC estimates that 30% of global data will be real-time data by 2025 - so learning how to process real-time data with TML is becoming critical.

Here are the TSS Screens:

TML solutions can process any real-time data from devices and systems. The real-time data are ingested using RESTful, gRPC, MQTT APIs or localfile on the file system.

Important

All TML solutions are containerized with Docker (scale with Kubernetes), come with automated documentation about the solution, automated commits to Github for real-time logging, and automated real-time dashboard for visualization using websockets.

TML solutions can be deployed on the cloud (with Internet) or on-premise (without Internet) to process unlimited real-time data globally. TML solutions can run on any cloud infrastructure - anywhere.

PDF Version

Tip

A PDF version of this documentation can be found here.

Watch The TSS Youtube Videos

Video Name	YouTube URL
TSS Video:	Youtube Video
Managing TML Projects (Creating, deleting, copying and stopping):	Youtube Video See details here Lets Start Building a TML Solution
Scaling TML Solutions with Kubernetes	Youtube Video See details here Scaling TML Solutions with Kubernetes
Storing Secure Passwords in Kubernetes	Youtube Video Describes how to store secure passwords in Kubernetes to make your TML solutions more secure and in compliance with IT security standards.
Running TML Projects in TSS:	Youtube Video Describes how to run a TML project. See details here Lets Start Building a TML Solution
Ingesting Real-Time Data into TML Solutions:	Youtube Video Describes how to ingest real-time data using: MQTT, RESTful API, gRPC API or Local file. See here STEP 3: Produce to Kafka Topics
How To Create Amazing TML Real-Time Dashboards:	Youtube Video Describes how to create TML real-time dashboards using websockets, and no third-party tools. See here TML Real-Time Dashboards and, STEP 7: Real-Time Visualization: tml-system-step-7-kafka-visualization-dag
TML Examples Video:	YouTube Video Describes examples shown here: TML Solution Examples
TML JSON Criteria Creator:	YouTube Video Describes Json Criteria creation for Json Processing shown here: JSON PROCESSING
Zoom student meeting at Seneca Polytechnic:	YouTube Video Zoom meeting to students to show how to run Examples 1 nand 3 with data streaming to a MQTT broker in HiveMQ. See here TML Solution Examples
TML Step 1 Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 1: Get TML Core Params: tml_system_step_1_getparams_dag
TML Step 2 Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 2: Create Kafka Topics: tml_system_step_2_kafka_createtopic_dag
TML Step 3 Dag Configurations:	Refer to Ingesting Real-Time Data into TML Solutions: STEP 3: Produce to Kafka Topics
TML Step 4 Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 4: Preprocesing Data: tml-system-step-4-kafka-preprocess-dag
TML Step 4a and 4c for RTMS Dag Configurations:	YouTube Video Describes key parameter configurations for the RTMS solution: STEP 4a: Preprocesing Data: tml-system-step-4a-kafka-preprocess-dag STEP 4c: Preprocesing 3 Data: tml-system-step-4c-kafka-preprocess-dag
TML Step 4b Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 4b: Preprocesing 2 Data: tml-system-step-4b-kafka-preprocess-dag
TML Step 5 Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 5: Entity Based Machine Learning : tml-system-step-5-kafka-machine-learning-dag
TML Step 6 Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 6: Entity Based Predictions: tml-system-step-6-kafka-predictions-dag
TML Step 7 Dag Configurations:	Refer to How To Create Amazing TML Real-Time Dashboards: STEP 7: Real-Time Visualization: tml-system-step-7-kafka-visualization-dag
TML Step 8 Dag:	Step 8 Dag for docker container - Does not require any configurations. See STEP 8: Deploy TML Solution to Docker : tml-system-step-8-deploy-solution-to-docker-dag
TML Step 9 Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 9: PrivateGPT and Qdrant Integration: tml-system-step-9-privategpt_qdrant-dag
TML Step 9b Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 9b: Multi-Agentic Agentic A: tml-system-step-9b-agenticai-dag
TML Step 10 Dag Configurations:	YouTube Video Describes key parameter configurations in: STEP 10: Create TML Solution Documentation: tml-system-step-10-documentation-dag

Important

TML Solution Studio (TSS)

You will learn how to use the TML Solution Studio (TSS) Container to build advanced, scalable, end-end real-time TML solutions easily with little to no- code. The TSS redefines how complex real-time solutions can be built by anyone, using pre-written Apache Airflow TML DAGs, that are integrated Github, AI (PrivateGPT), Docker, and Kubernetes, with automated online documentation of your entire solution.

TSS enables TML solutions to be developed WITHOUT WRITING ANY CODE - ONLY CONFIGURATIONS TO DAGS - dramatically accelerating real-time solution builds.

Transactional Machine Learning (TML) Overview

Important

Transactional Machine Learning (TML): The Machine Learning and AI Platform for Real-Time Data Streams

TML Is Based On the Belief that “Fast data requires fast machine learning and AI for fast decision-making” that provides a faster way to build advanced, scalable, cost- effective and secure real-time solutions that can be built by anyone.

TML gives rise in the industy to a Data Stream Scientist versus a Data Scientist in conventional machine learning (CML).

Transactional Machine Learning (TML) using Data Streams and AutoML is a platform for building and streaming cloud native (or on-prem) solutions using Apache Kafka or Redpanda as the data backbone, with Kubernetes and Docker as core infrastucture components, running on Confluent, AWS, GCP, AZURE, for advanced machine learning solutions using transactional data to learn from, and provide insights, quickly and continuously to any number of devices and humans in any format!

TML Book Details Found Here: Springer (Publisher) site

TML Video: Watch the Youtube Video

Apply data preprocessing and auto machine learning to data streams and create transactional machine learning (TML) solutions that are:

1. frictionless: require minimal to no human intervention

2. elastic: machine learning solutions that can scale up or down using Kubernetes to control or enhance the number of data streams, algorithms (or machine learning models) and predictions instantly and continuously.

Note

TML is ideal when data are highly erratic (nonlinear) and you want the machine to learn from the latest dataset by creating sliding windows of training datasets and auto creating micro-machine learning models quickly, that can be easily scaled, managed and the insights used immediately from any device! There are many TML use cases such as:

1. IoT: Capture real-time, fast, data, and build custom micro-machine learning models for every IoT device specific to the environment that the device operates in and predict failures, optimize device settings, and more.

2. IoT Edge: TML is ideal for edge devices with No Internet connections. Simply use the On-Prem version of TML software, with On-Prem Kafka and create large and powerful, real-time, edge solutions.

3. HealthCare: TML is ideal for health data processing for patients, payers, and providers. Open access to health data has been mandated by CMS, which opens up enormous opportunities for TML.

4. Banking/Finance Fraud Detect: Detect fraud using unsupervised learning on data streams and process millions of transactions for fraud - see the LinkedIn blog

5. Financial Trading: Use TML to analyse stock prices and predict sub-second stock prices!

6. Pricing: Use TML to build optimal pricing of products at scale.

7. Oil/Gas: Use TML to optimize oil drilling operations sub-second and drill oil wells faster and cheaper with minimal downtime

8. SO MUCH MORE…

The above usecases are not possible with conventional machine learning methods that require frequent human interventions that create lots of friction, and not very elastic.

By using Apache Kafka On-Premise many advanced, and large, TML usecases are 80-90% cheaper than cloud-native usecases, mainly because storage, compute, Egress/Ingress and Kafka partitions are localized. Given Compute and Storage are extremely low-cost On-Premise solutions with TML are on the rise. TML On-Prem is ideal for small companies or startups that do not want to incur large cloud costs but still want to provide TML solutions to their customers.

Strengthen your knowledge of the inner workings of TML solutions using data streams with auto machine learning integrated with Apache Kafka. You will be at the forefront of an exciting area of machine learning that is focused on speed of data and algorithm creation, scale, and automation.

Contents

• 1. QUICK START: Run TWO TML Solutions Right Now!
  • 1.1. QUICK START: TML Solution with Real-Time Entity Based Processing
    • 1.1.1. Run this docker command
    • 1.1.2. View The Real-Time Dashboard
  • 1.2. QUICK START: Another TML Soluton with Real-Time Entity Based Processing AND Machine Learning
    • 1.2.1. Run this docker command
    • 1.2.2. View Another Real-Time Dashboard
• 2. TML Book
• 3. TML Solution Studio (TSS) Container
  • 3.1. TML Solution Container Global Deployment
  • 3.2. TSS Pre-Requisites
  • 3.3. TSS Contains a TML Dev Environment
  • 3.4. TSS Docker Run Command
  • 3.5. How To Use the TML Solution Container
  • 3.6. TSS Code Editor
  • 3.7. TSS Demo Github, Docker and Readthedocs Site Credentials
  • 3.8. Readthedocs Documentation URL
  • 3.9. Common Docker and TMUX Commands
  • 3.10. TSS Logging
• 4. TML REST API Endpoints and Examples
  • 4.1. TML Server Plugin Container
  • 4.2. Reference Architecture
    • 4.2.1. TML API Quick Reference
  • 4.3. API For Kafka Topic Creation
  • 4.4. API For Preprocessing / ML / Predictions
  • 4.5. API For AI and Agentic AI
  • 4.6. API For Reading or Consuming Data From Kafka Topics
  • 4.7. API For Writing or Producing Raw Data to Kafka Topics
  • 4.8. Industrial API For Ingesting Data From SCADA and MQTT
  • 4.9. API For System Maintenance
  • 4.10. RUN The TML Server Plugin Container
  • 4.11. Docker Run Parameters
  • 4.12. POST /api/v1/createtopic
  • 4.13. POST /api/v1/preprocess
  • 4.14. POST /api/v1/ml
  • 4.15. POST /api/v1/predict
  • 4.16. POST /api/v1/consume
  • 4.17. POST /api/v1/jsondataline
  • 4.18. POST /api/v1/jsondataarray
  • 4.19. POST /api/v1/external_payload
  • 4.20. POST /api/v1/terminatewindow
  • 4.21. POST /api/v1/health
  • 4.22. POST /api/v1/ai
  • 4.23. POST /api/v1/agenticai
  • 4.24. POST /api/v1/scada_modbus_read
  • 4.25. POST /api/v1/scada_modbus_carryover
  • 4.26. POST /api/v1/mqtt_subscribe
    • 4.26.1. TML Endpoint Example
  • 4.27. STEP 1: Run the TML Server Plugin Container
  • 4.28. STEP 2: Download IoT Demo Data
  • 4.29. Step 3: Send some data to the TML Server Line by Line
  • 4.30. Step 3b: Send some data to the TML Server in Batch
  • 4.31. Step 4: Visualize The Output in a Dashboard
  • 4.32. TML Endpoint Examples
  • 4.33. Output Results
  • 4.34. Visualization Of ML Models and Agentic AI Agents
  • 4.35. Pre-requisites:
  • 4.36. TML Processing Using SCADA and MQTT
  • 4.37. What TML Adds On Top of SCADA/MQTT
  • 4.38. SCADA Example
  • 4.39. Step 1: Run the SCADA Simulator
  • 4.40. Step 2: Write Data to the SCADA Simulator
  • 4.41. Step 3: Read the Data in SCADA
  • 4.42. Send a cURL to TML to Read From SCADA
  • 4.43. Step 4: Output JSON
  • 4.44. SCADA Separator Intelligence Dashboard
  • 4.45. MQTT Example
  • 4.46. Step 1: Subscribe to the MQTT Topic
  • 4.47. Send a cURL to TML to Read From MQTT:
  • 4.48. Step 2: Stream Data to the MQTT Cluster
  • 4.49. Step 3: TML Process Data
  • 4.50. Step 4: Perform Machine Learning/AI/Agentic AI
• 5. TML Solution Templates
  • 5.1. The Solution Template Naming Conventions
    • 5.1.1. For example:
  • 5.2. Here are the solution templates provided
  • 5.3. 1. Solution Template: solution_template_processing_ai_dag_grpc.py
  • 5.4. 2. Solution Template: solution_template_processing_ai_dag_mqtt.py
  • 5.5. 3. Solution Template: solution_template_processing_ai_dag_restapi.py
  • 5.6. 4. Solution Template: solution_template_processing_ai_dag.py
  • 5.7. 5. Solution Template: solution_template_processing_dag_grpc.py
  • 5.8. 6. Solution Template: solution_template_processing_dag_mqtt.py
  • 5.9. 7. Solution Template: solution_template_processing_dag_restapi.py
  • 5.10. 8. Solution Template: solution_template_processing_dag.py
  • 5.11. 9. Solution Template: solution_template_processing_ml_ai_dag_grpc.py
  • 5.12. 10. Solution Template: solution_template_processing_ml_ai_dag_mqtt.py
  • 5.13. 11. Solution Template: solution_template_processing_ml_ai_dag_restapi.py
  • 5.14. 12. Solution Template: solution_template_processing_ml_ai_dag.py
  • 5.15. 13. Solution Template: solution_template_processing_ml_dag_grpc.py
  • 5.16. 14. Solution Template: solution_template_processing_ml_dag_mqtt.py
  • 5.17. 15. Solution Template: solution_template_processing_ml_dag_restapi.py
  • 5.18. 16. Solution Template: solution_template_processing_ml_dag.py
  • 5.19. How To Read a Solution Template
    • 5.19.1. 1. import files
    • 5.19.2. 2. tasks to execute
    • 5.19.3. 3. tasks groupings
  • 5.20. Running A Solution Container
• 6. Scaling TML Solutions with Kubernetes
  • 6.1. Auto-Generated YAML Files
  • 6.2. Example Kubernetes Run From Applying YAML Files
  • 6.3. Scaling with NGINX Ingress and Ingress Controller
  • 6.4. Making Secure TLS Connection with gRPC
    • 6.4.1. Here are the Steps to follow.
      • 6.4.1.1. Step 1: Get Server Certificates
      • 6.4.1.2. Step 2: Apply the Server Certificates to Kubernetes Cluster
      • 6.4.1.3. Step 3: Apply the secret-tls to Kubernetes Cluster
  • 6.5. Using gRPcurl to Write Data to the TML gRPC Server
    • 6.5.1. Run the gRPCurl Commands
    • 6.5.2. Send data to the sever:
  • 6.6. How To Store Secure Passwords in Kubernetes
  • 6.7. NVIDIA GPU On Windows WSL
  • 6.8. Installing minikube
  • 6.9. Confirming CUDA Installation in Kubernetes (minikube)
  • 6.10. Minikube Setup Command
  • 6.11. Mounting Local Filesystem in Minikube
  • 6.12. Scaling EXAMPLE: Scaling Cybersecurity with privateGPT solution
• 7. TML Solution Building
  • 7.1. Why Do I Need TML?
  • 7.2. Where Is TML Used?
  • 7.3. TML Solutions Can Be Built In 10 Steps Using Pre-Written DAGs (Directed Acyclic Graphs)
  • 7.4. Where Do I Start?
  • 7.5. Pre-Written 10 Apache Airflow DAGs To Speed Up TML Solution Builds
    • 7.5.1. DAG Solution Process Explanation
    • 7.5.2. DAG Table
    • 7.5.3. STEP 1: Get TML Core Params: tml_system_step_1_getparams_dag
      • 7.5.3.1. DAG STEP 1: Parameter Explanation
    • 7.5.4. STEP 2: Create Kafka Topics: tml_system_step_2_kafka_createtopic_dag
      • 7.5.4.1. DAG STEP 2: Parameter Explanation
    • 7.5.5. STEP 3: Produce to Kafka Topics
      • 7.5.5.1. Four Ways to Ingest Data Into Your TML Solution Container
      • 7.5.5.2. STEP 3a: Produce Data Using MQTT: tml-read-MQTT-step-3-kafka-producetotopic-dag
      • 7.5.5.3. DAG STEP 3a: Parameter Explantion
      • 7.5.5.4. STEP 3a.i: MQTT CLIENT
      • 7.5.5.5. MQTT Reference Architecture
      • 7.5.5.6. STEP 3b: Produce Data Using RESTAPI: tml-read-RESTAPI-step-3-kafka-producetotopic-dag
      • 7.5.5.7. STEP 3b: Parameter Explanation
      • 7.5.5.8. STEP 3b.i: REST API CLIENT
      • 7.5.5.9. STEP 3b.i: REST API CLIENT: Explanation
      • 7.5.5.10. REST API Reference Architecture
      • 7.5.5.11. STEP 3c: Produce Data Using gRPC: tml-read-gRPC-step-3-kafka-producetotopic-dag
      • 7.5.5.12. STEP 3c: Parameter Explanation
      • 7.5.5.13. STEP 3c.i: gRPC API CLIENT
      • 7.5.5.14. STEP 3c.i: gRPC API CLIENT: Explanation
      • 7.5.5.15. gRPC Reference Architecture
      • 7.5.5.16. STEP 3d: Produce Data Using LOCALFILE: tml-read-LOCALFILE-step-3-kafka-producetotopic-dag
      • 7.5.5.17. Core Parameter Explanation
      • 7.5.5.18. Producing Data Using a Local File
      • 7.5.5.19. Local File Reference Architecture
    • 7.5.6. STEP 4: Preprocesing Data: tml-system-step-4-kafka-preprocess-dag
      • 7.5.6.1. Preprocessing Types
    • 7.5.7. Data Cleaning
    • 7.5.8. STEP 4: Preprocesing Data Dag: tml-system-step-4-kafka-preprocess-dag
      • 7.5.8.1. Preprocessed Variable Naming Standard
      • 7.5.8.2. Preprocessed Sample JSON Output
      • 7.5.8.3. Preprocessed Sample JSON Output: Explanations
    • 7.5.9. STEP 4a: Preprocesing Data: tml-system-step-4a-kafka-preprocess-dag
    • 7.5.10. STEP 4b: Preprocesing 2 Data: tml-system-step-4b-kafka-preprocess-dag
    • 7.5.11. STEP 4c: Preprocesing 3 Data: tml-system-step-4c-kafka-preprocess-dag
      • 7.5.11.1. Core Parameters in Step 4c
    • 7.5.12. STEP 5: Entity Based Machine Learning : tml-system-step-5-kafka-machine-learning-dag
      • 7.5.12.1. Entity Based Machine Learning By TML
      • 7.5.12.2. Additional Details on Machine Learning
      • 7.5.12.3. Classification Models: Details on the Processlogic field
      • 7.5.12.4. Machine Learning Trained Model Sample JSON Output
      • 7.5.12.5. Machine Learning Trained Model Sample JSON Output: Explanations
    • 7.5.13. TML Physical Location of Machine Learning Models
    • 7.5.14. Entity 53 Trained Algorithm Information
      • 7.5.14.1. How TML Optimizes ML Models and Acheives High Forecast Accuracy
    • 7.5.15. STEP 6: Entity Based Predictions: tml-system-step-6-kafka-predictions-dag
  • 7.6. Machine Learning Prediction Sample JSON Output
    • 7.6.1. STEP 7: Real-Time Visualization: tml-system-step-7-kafka-visualization-dag
  • 7.7. Visualization DAG Parameter Explanation
    • 7.7.1. STEP 8: Deploy TML Solution to Docker : tml-system-step-8-deploy-solution-to-docker-dag
    • 7.7.2. STEP 9: PrivateGPT and Qdrant Integration: tml-system-step-9-privategpt_qdrant-dag
  • 7.8. STEP 9 DAG Core Parameter Explanation
  • 7.9. Vector Dimensions
  • 7.10. privateGPT Processing Explanation
  • 7.11. Using Qdrant VectorDB for Local Document Analysis
  • 7.12. TML, PrivateGPT and Qdrant Example Scenarios
  • 7.13. STEP 9b: Multi-Agentic Agentic A: tml-system-step-9b-agenticai-dag
  • 7.14. STEP 9b DAG Core Parameter Explanation
  • 7.15. Example of 9b Configuration Parameters
  • 7.16. STEP 9b: Agents’ Tools
  • 7.17. STEP 10: Create TML Solution Documentation: tml-system-step-10-documentation-dag
  • 7.18. Example Of Setting Docker Instructions in Step 10
  • 7.19. Creating Your Own DAG
  • 7.20. Github Push Issues
  • 7.21. Example TML Solution Container Reference Architecture
  • 7.22. Lets Start Building a TML Solution
  • 7.23. STEP 0. Go into tml-airflow folder
  • 7.24. STEP 0. tml-airflow -> dags -> tml-solutions
  • 7.25. STEP 1. Click the file: CREATETMLPROJECT.txt - you will see the following as shown in figure below:
  • 7.26. STEP 1. Type the name of your project
    • 7.26.1. Creating a Project
  • 7.27. STEP 1. You just created a TML Project and committed to Github. Congratulations!
  • 7.28. Deleting a Project
  • 7.29. STEP 2. Click the folder: myawesometmlproject-3f10
  • 7.30. STEP 2. Confirm Your New Project Was Created in TSS and Committed to Github
    • 7.30.1. Stopping a Running Project
    • 7.30.2. Copying A Previous Project
  • 7.31. STEP 3. Make Parameter Modifications to Your Project’s TML DAGs
  • 7.32. STEP 4. Choose the Solution Template You Want to Run
    • 7.32.1. Project Solution Template Run
      • 7.32.1.1. Parameter Changes to TML DAGs
  • 7.33. STEP 5. Run Your Solution
  • 7.34. STEP 6: Go To the Solution Documentation
  • 7.35. STEP 7: Your Solution Docker Run Command
  • 7.36. STEP 8: Stream Your Solution Dashboard
  • 7.37. STEP 9: TML Solution Built in Less than 2 Minutes
  • 7.38. Project Action Commands Summary
• 8. TML Solution Examples
  • 8.1. Real-Time IoT Data Preprocessing Example
    • 8.1.1. Solution DAG Code: solution_preprocessing_dag-myawesometmlsolution-3f10
      • 8.1.1.1. TML Dag Parameter Changes To Be Made For: solution_preprocessing_dag-myawesometmlsolution-3f10
      • 8.1.1.2. Successful Run Screen
  • 8.2. Solution Documentation Example
  • 8.3. Github Commits
  • 8.4. Real-Time IoT Data Preprocessing With Secondary Preprocessing and With Map Example
    • 8.4.1. Solution DAG Code: solution_preprocessing_dag-iotsolution-3f10
      • 8.4.1.1. TML Dag Parameter Changes To Be Made For: solution_preprocessing_dag-iotsolution-3f10
      • 8.4.1.2. Successful Run Screen
  • 8.5. Solution Documentation Example
  • 8.6. Real-Time IoT Data Preprocessing With RESTAPI, Secondary Preprocessing and With Map Example
    • 8.6.1. Solution DAG Code: solution_preprocessing_dag_restapi-iotsolution-restapi-3f10
      • 8.6.1.1. TML Dag Parameter Changes To Be Made For: solution_preprocessing_dag_restapi-iotsolution-restapi-3f10
      • 8.6.1.2. Successful Run Screen
      • 8.6.1.3. Solution Documentation Example
  • 8.7. Real-Time IoT Data Preprocessing With gRPC, Secondary Preprocessing and With Map Example
    • 8.7.1. Solution DAG Code: solution_preprocessing_dag_grpc-iotsolution-grpc-3f10
      • 8.7.1.1. TML Dag Parameter Changes To Be Made For: solution_preprocessing_dag_grpc-iotsolution-grpc-3f10
      • 8.7.1.2. Successful Run Screen
      • 8.7.1.3. Solution Documentation Example
  • 8.8. Real-Time IoT Data Preprocessing and Machine Learning Example
    • 8.8.1. Solution DAG Code: solution_preprocessing_ml_dag-myawesometmlsolutionml-3f10
      • 8.8.1.1. TML Dag Parameter Changes To Be Made For: solution_preprocessing_ml_dag-myawesometmlsolutionml-3f10
  • 8.9. Cybersecurity Solution with PrivateGPT, MQTT, HiveMQ
    • 8.9.1. Solution DAG Code: solution_preprocessing_ai_mqtt_dag-cybersecuritywithprivategpt-3f10
      • 8.9.1.1. TML Dag Parameter Changes To Be Made For: solution_preprocessing_ai_mqtt_dag-cybersecuritywithprivategpt-3f10
    • 8.9.2. DAG Successful Run
    • 8.9.3. The Dashboard with PrivateGPT
    • 8.9.4. The HiveMQ Cluster
    • 8.9.5. Solution Documentation
    • 8.9.6. Solution Docker Container
• 9. TML Solution Studio’s Tight Integration with GitHub
  • 9.1. Push To and Pull From Local and Remote Github Branches
  • 9.2. Viewing Local and Remote Github Branches
  • 9.3. Github Logs
• 10. TML Solution Components
  • 10.1. 1. TML Components: Three Binaries
  • 10.2. 2. TML Component: One Core Python Library
  • 10.3. 3. TML Component: Apache Kafka
  • 10.4. 4. TML Component: Docker Containers
  • 10.5. 5. TML Component: Kubernetes
  • 10.6. 6. TML Component: PrivateGPT for Generate AI
  • 10.7. 7. TML Component: TML Solution Studio Container
  • 10.8. How The TML Components Are Integrated
• 11. Copying TML Project(s) From Others Git Repo
  • 11.1. You Want to Copy ALL TML Projects From Another Users Git Repo
  • 11.2. You Want to Copy SPECIFIC TML Projects From Another Users Git Repo
• 12. Set Up Readthedocs
  • 12.1. STEP 1: Create a Readthedocs Account
  • 12.2. STEP 2: Generate API Token
  • 12.3. STEP 3: Add Token in TSS Docker Run Command
• 13. Set Up HiveMQ
  • 13.1. Step 1: Setup a Free HiveMQ Account
  • 13.2. Step 2: Create a FREE Serverless Cluster
  • 13.3. Step 3: Cluster Details
  • 13.4. Step 4: Create MQTT Username and Password
• 14. Set Up Personal Access Tokens in Github
  • 14.1. Generating Personal Access Tokens in Github: Explanation
    • 14.1.1. Permissions For Your Token
    • 14.1.2. Fine-Grained Tokens
• 15. TML Real-Time Logs
  • 15.1. Log Example
• 16. TML Core Technology Integration
  • 16.1. 1. Apache Kafka
  • 16.2. 2. Apache Airflow
  • 16.3. 3. TML Binaries
  • 16.4. 4. TML Python Library
  • 16.5. 5. TML GenAI With PrivateGPT and Qdrant Vector DB
  • 16.6. 6. TMUX (Terminal Multiplexing)
  • 16.7. 7. MariaDB (MySQL)
  • 16.8. 8. Docker
  • 16.9. 9. Kubernetes
  • 16.10. 10. Github
  • 16.11. 11. Python and DAGs (Directed Acylic Graphs)
• 17. TML Real-Time Dashboards
  • 17.1. Running Dashboards
    • 17.1.1. Creating Your Own Dashboards
  • 17.2. Dashboard Template
  • 17.3. Dashboard Template: Code Explanation
  • 17.4. More Dashboard Examples
• 18. MAADSTML Python Library API
• 19. RealFlow Control AI: Sub-Millisecond Physics-TML Fusion
  • 19.1. RealFlow Control AI Dashboard
  • 19.2. Why RealFlow?
    • 19.2.1. 12,500x Computational Speedup
    • 19.2.2. The Global Bias Ledger
    • 19.2.3. Green AI Architecture
  • 19.3. Core Methodology: The Fusion Framework
    • 19.3.1. The Fusion Equation
  • 19.4. Technical Deep Dive
    • 19.4.1. Sub-Millisecond Quadrature Physics
  • 19.5. Self-Healing Gaussian Processes
  • 19.6. Dashboard Operations
  • 19.7. Level 5 Autonomous Control
  • 19.8. Getting Started
• 20. FAQ: TML Simulator
• 21. TML Simulator
  • 21.1. Executive Summary
  • 21.2. Why TML Simulator Is Industry‑Leading
  • 21.3. TML Simulator Can Process
  • 21.4. The Fundamental Physics / Math
    • 21.4.1. 1. Gas‑Velocity versus Souders‑Brown Limit
    • 21.4.2. 2. Droplet‑Settling in the Gravity Section
    • 21.4.3. 3. Vessel‑Holdup and Time‑Stepping
    • 21.4.4. Why This Is Production‑Grade
    • 21.4.5. Light Code Overview (For Technical Review)
    • 21.4.6. Why This Is Industry‑Leading
      • 21.4.6.1. **
  • 21.5. Appendix:
  • 21.6. TML Simulator Solution Reference Architecture
  • 21.7. TML RealFlow Control AI Solution
  • 21.8. Standard Vessel Configuation Template for TML Simulator
    • 21.8.1. 1. vessels — “every vessel matters”
    • 21.8.2. 2. flows — “every internal pipe”
    • 21.8.3. What every company must provide per flow:
    • 21.8.4. 3. solver — “run time range”
    • 21.8.5. What every company must provide:
    • 21.8.6. 4. physics — “global constants”
    • 21.8.7. 5. Minimal “anything‑goes” version
      • 21.8.7.1. **
• 22. Mapping the SCADA Tags To Vessel Physics
  • 22.1. 1. What the SCADA fields give us:
  • 22.2. 2. Mapping SCADA tags to physics inputs
    • 22.2.1. CORE Mappings For Each Vessel
      • 22.2.1.1. **
  • 22.3. What TML Carryover Solution is Predicting
  • 22.4. 2. Why this is better than using only the empirical or only the physics
    • 22.4.1. 3. Practical “deployment stages” you can document
    • 22.4.2. Summary
  • 22.5. Vessel Configuration: Example of 20 Vessels
  • 22.6. Vessel Configuration: Example of 150 Vessels
  • 22.7. TML RealFlow Solution
  • 22.8. Customers’ Advantages:
• 23. 1D Souders-Brown and 3D CFD
  • 23.1. Core Physics Approach
  • 23.2. When Each Wins: 1D vs 3D
  • 23.3. Hybrid Reality (Industry Practice)
  • 23.4. Industry Perspective
  • 23.5. Computational Reality
  • 23.6. Network Scale
  • 23.7. Engineering Truth
  • 23.8. Carryover Details
  • 23.9. Flowsheet: 1D Souders-Brown and 3D CFD
  • 23.10. Units Table
  • 23.11. Vessel and Model Variables
    • 23.11.1. Scada Raw Measurements
  • 23.12. Fluid Properties
  • 23.13. Physics/Derived
  • 23.14. Simulator Arrays
  • 23.15. Analytics Features
  • 23.16. Payload Key Fields
• 24. TML Performs Entity Level Machine Learning and Processing
  • 24.1. What does entity level processing and machine learning mean?
  • 24.2. TML Processes Real-Time Data Using Sliding Time Windows
  • 24.3. TML Machine Learning Using Sliding Time Windows
• 25. Real-Time Message Scoring (RTMS): How TML Maintains Past Memory of Events Using Sliding Time Windows in Real-Time
  • 25.1. Importance of RTMS For Cyber Crime Detection
  • 25.2. The RTMS Method
  • 25.3. High-Level Reference Architecture
  • 25.4. Maintaining Past Memory of Real-Time Data Without a Database: Demonstration
  • 25.5. TML Output of RTMS Scores
• 26. Output Explanation
  • 26.1. How TML Accomodates Evolving Threats
  • 26.2. Regular Expressions Example
  • 26.3. RegEx Cheat Sheets
  • 26.4. TML Real-Time Message Scoring (RTMS) vs AI RAG
  • 26.5. How RTMS Integrates with MITRE ATT&CK Framework
  • 26.6. Integrating RTMS with Real-Time AI Using PrivateGPT Containers and MITRE ATT&CK Classification
    • 26.6.1. RTMS Grouped MITRE ATT&CK JSON
  • 26.7. RTMS MITRE ATT&CK Dashboard
  • 26.8. RTMS Solution: Steps to Run It Yourself
  • 26.9. RTMS Solution Architecture
    • 26.9.1. RTMS in Graphical View of TSS Steps
  • 26.10. Summary
• 27. JSON PROCESSING
  • 27.1. Json Path Example
  • 27.2. JSON Message In A Payload
  • 27.3. JSON Criteria Creator
• 28. MAADS-VIPER Environmental Variable Configuration (Viper.env)
• 29. TML and Generative AI
• 30. PrivateGPT Special Containers
• 31. TML and Agentic AI Special Container
• 32. Test The Ollama Model for GPU
• 33. Ollama LLM Model for CPU
• 34. TML and Vision Models
  • 34.1. TML and Vision Models: Sample Code
• 35. TML and Video ChatGPT
  • 35.1. Docker Run Command
  • 35.2. Video ChatGPT Sample Code
• 36. TML API for GenAI Using MAADSTML Python Library
  • 36.1. GenAI With STEP 9
  • 36.2. TML and RAG: A Powerful Combination
  • 36.3. Private GPT Container
  • 36.4. PrivateGPT Container With NO GPU
    • 36.4.1. Installing CUDA For NVIDIA GPU
    • 36.4.2. NVIDIA Common Issues
  • 36.5. To Enable GPU in Kubernetes
  • 36.6. Accessing PrivateGPT With MAADSTML Python API
  • 36.7. Qdrant Vector Database
• 37. TML and Agentic AI
  • 37.1. What is an Agent?
  • 37.2. TML and Agentic AI: A Powerful Combination for Real-Time Data
  • 37.3. TML and Multi-Agentic AI Process Flow in Real-Time: GenAI Reasoning and Actions
  • 37.4. TML and Multi-Agentic AI Solution Reference
    • 37.4.1. Sample Output from TML Multi-Agentic AI Solution
  • 37.5. Building TML and Agentic AI Solutions with TML Solution Studio (TSS)
  • 37.6. TML and (Multi) Agentic AI Architecture
    • 37.6.1. Implementing Complex Workflows with TML and (Multi) Agentic AI
  • 37.7. Advantages of TML with Agentic AI
  • 37.8. EXAMPLE: TML Agentic AI For Drones
• 38. PrecisionOdds AI: The Most Accurate Sports Odds Engine
  • 38.1. Production Bayesian Engine with TML and Multi-Agentic AI for NHL, NBA, NFL, and MLB In-Game Predictions
  • 38.2. The motivation behind PrecisionOdds AI
  • 38.3. TML and Multi-Agentic Framework:
  • 38.4. What PrecisionOdds engine actually does
  • 38.5. Benchmarking PrecisionOdds Against Industry
  • 38.6. The core mathematical model
    • 38.6.1. Player event model
  • 38.7. Team goals and win probability
  • 38.8. From probabilities to betting metrics
  • 38.9. What the model metrics actually mean
  • 38.10. Why these metrics matter for betting outcomes
  • 38.11. Why this beats typical “best-in-market” tools
  • 38.12. Backtesting and business impact
  • 38.13. What the model metrics actually mean
  • 38.14. Interpretation of R̂ from the LSAI model
  • 38.15. Additional Metrics on the Lamdas: Goals, Assists, Penalties and Shot
  • 38.16. Complete Model Performance
  • 38.17. Summary
• 39. Can I Run TML Binaries in Standalone?