ZebClient
Zebware.comCustomer Portal
  • ZebClient Documentation
  • Product Overview
    • Introduction to ZebClient
    • Functional Overview
    • Product Components
    • Data Flows
    • Data Striping
  • USE CASES
    • ZebClient Analytics
      • Architecture
        • Data Pipeline
        • Data Storage
        • Consumption
      • Deploy a ZebClient Advanced Cluster
        • Step 0 - Setup
      • FAQ
  • Planning & Getting Started
    • How to Choose your Deployment Mode
    • Deployment Modes and Tuning
    • Performance
    • License
    • Order Your ZebClient License
    • Pricing
  • Installation
    • Types of Installations
    • Guided Installation
      • ZebClient with Azure Blob Storage
        • Defining Backend with Azure Blob Storage
        • Mounting ZebClient with Azure Blob Storage
      • ZebClient with AWS S3
        • Defining Backend with AWS S3
        • Mounting ZebClient with AWS S3
      • Mount Additional Agent Node
    • Kubernetes
      • Azure Quickstart Guide
      • ZebClient CSI
      • ZebClient Helm
      • ZebClient Terraform
    • Virtual Machines
      • Azure Installation Guide
        • Installing Using Terraform
        • Uninstalling Using Terraform
    • Checking Installation
    • Running First Test
  • Management HOW-TOS
    • Add a New Agent VM into an Existing Cluster
    • Retrieve Cluster Log Files
    • CloudFormation Deployments
      • Understanding our CloudFormation Template
      • Uninstalling Using CloudFormation
    • Command-line Interface
  • Operations & Monitoring
    • Importing Your Data
    • Inlets
      • Data from External S3 Bucket
    • System Recovery Guide
      • Restore KeyDB Backup from S3
    • Port a Deploy
    • Add Resources to a Cluster
      • Add Application Node to Existing Machine (Manually)
      • Add Application Node to Existing Machine (via zc-cli)
      • Add New Application Node
      • Add Jumpbox
    • Verifying License Validity
    • Monitoring Your ZebClient Cluster with Netdata
Powered by GitBook
On this page
  1. USE CASES
  2. ZebClient Analytics
  3. Architecture

Consumption

PreviousData StorageNextDeploy a ZebClient Advanced Cluster

Last updated 1 year ago

Using LLM for Text to SQL Query on Data

Default the SQL-LLM is used for Text-to-SQL on ZebClient Analytics the open-source distributed framework designed for Machine Learning (ML) models that runs natively on Kubernetes.

The integration of SQL-LLM within ZebClient Analytics allows anyone from consumers to data engineers to run the same text prompts to generate text to sql analytical queries on data generated or updated by running data pipelines

1. Scalability: SQL-LLM allows users to train large machine learning models at scale in a distributed manner, ensuring they can handle larger datasets and more complex models within the ZebClient Analytics environment. This is particularly beneficial when dealing with big data processing pipelines or handling multiple ML model training tasks concurrently.

2. Flexibility: SQL-LLM supports various machine learning frameworks like TensorFlow, PyTorch, and Scikit-learn, allowing users to choose the most appropriate framework for their specific project requirements within ZebClient Analytics. This flexibility caters to different use cases while maintaining a consistent development environment.

3. Integrated training and deployment: The integration of SQL-LLM within ZebClient Analytics enables users to train and deploy machine learning models directly from their data processing pipelines, streamlining the entire ML model lifecycle within the platform. This eliminates the need for separate tools or infrastructure for model training and deployment, saving development time and reducing operational overhead.

4. Monitoring and logging: SQL-LLM provides integrated monitoring and logging capabilities, enabling users to track their ML model training progress and performance metrics in real-time within ZebClient Analytics. This visibility into the model training process allows users to identify issues early on and make informed decisions regarding model iterations and improvements.

5. Resource management: The integration of SQL-LLM within ZebClient Analytics simplifies resource management for machine learning model training tasks by automatically provisioning and scaling Kubernetes resources as needed. This ensures efficient utilization of resources, reducing costs and improving overall operational efficiency.

6. Continuous delivery: By offering integrated model training and deployment capabilities within ZebClient Analytics through SQL-LLM, users can implement continuous delivery pipelines for their ML models. This allows them to quickly deploy new or updated models into production environments, ensuring that they always have access to the latest AI functionality in their applications.

7. Collaboration: The integration of SQL-LLM within ZebClient Analytics enables users to collaborate on machine learning model development projects more effectively by providing a centralized platform for training, testing, and deploying ML models. This improved communication and feedback can lead to faster development cycles and higher-quality ML solutions.

8. Integration with other tools: The integration of SQL-LLM within ZebClient Analytics allows users to leverage its capabilities alongside other popular data engineering and ML tools like Kubeflow, Airflow, and Jupyter Hub. Users can design complex AI and ML pipelines that incorporate model training and deployment tasks using these integrated tools, creating a more comprehensive development experience within the platform.

Ollama