LogoLogo
HomePlatformAsk DuploCloudPricing
  • Overview
  • Product Updates
  • Workshops
    • DuploCloud 101 for AWS
      • Create Your Infrastructure and Application
        • 1. Log in to the DuploCloud Portal
        • 2. Create a DuploCloud Infrastructure
        • 3. Create a DuploCloud Tenant
        • 4. Create an EKS Worker Node
        • 5. Deploy an Application
        • 6. Create a Load Balancer
        • 7. Deploy an S3 Bucket
        • 8. Deploy a Database
        • 9. Create an Alarm
      • Daily Operations using DuploCloud
        • 1. Host, Container, and Kubectl Shell
        • 2. Logging
        • 3. Metrics
        • 4. Billing and Cost Management
        • 5. Audit Logs
        • 6 - Tenant and Admin Just-In-Time (JIT) AWS Access
        • 7. CI/CD
        • 8. Security Hub and Dashboard
        • 9. Terraform Mode of Operations
      • Post-workshop Reference Guide
        • Post-Workshop Testing and Documentation Links
        • Connect With Us
        • DuploCloud Whitepapers
        • DuploCloud Terraform Provider
        • DuploCloud AWS Demo Video
  • Getting Started with DuploCloud
    • What DuploCloud Does
    • DuploCloud Onboarding
    • Application Focused Interface: DuploCloud Architecture
      • DuploCloud Tenancy Models
      • DuploCloud Common Components
        • Infrastructure
        • Plan
        • Tenant
        • Hosts
        • Services
        • Diagnostics
      • Management Portal Scope
    • GRC Tools and DuploCloud
    • Public Cloud Tutorials
    • Getting Help with DuploCloud
  • Container Orchestrators
    • Terminologies in Container Orchestration
  • DuploCloud Prerequisites
    • DNS Configuration
  • AWS User Guide
    • Prerequisites
      • Route 53 Hosted Zone
      • ACM Certificate
      • Shell Access for Containers
      • VPN Setup
      • Connect to the VPN
    • AWS Quick Start
      • Step 1: Create Infrastructure and Plan
      • Step 2: Create a Tenant
      • Step 3: Create an RDS Database (Optional)
      • Creating an EKS Service
        • Step 4: Create a Host
        • Step 5: Create a Service
        • Step 6: Create a Load Balancer
        • Step 7: Enable Additional Load Balancer Options (Optional)
        • Step 8: Create a Custom DNS Name (Optional)
        • Step 9: Test the Application
      • Creating an ECS Service
        • Step 4: Create a Task Definition for an Application
        • Step 5: Create the ECS Service and Load Balancer
        • Step 6: Test the Application
      • Creating a Native Docker Service
        • Step 4: Create an EC2 Host
        • Step 5: Create a Service
        • Step 6: Create a Load Balancer
        • Step 7: Test the Application
    • AWS Use Cases
      • Creating an Infrastructure and Plan for AWS
        • EKS Setup
          • Enable EKS endpoints
          • Enable EKS logs
          • Enable Cluster Autoscaler
        • ECS Setup
          • Enable ECS logging
        • Add VPC endpoints
        • Security Group rules
        • Upgrading the EKS version
      • Creating a Tenant (Environment)
        • Setting Tenant session duration
        • Setting Tenant expiration
        • Tenant Config settings
      • Hosts (VMs)
        • Adding Hosts
        • Connect EC2 instance
        • Adding Shared Hosts
        • Adding Dedicated Hosts
        • Autoscaling Hosts
          • Autoscaling Groups (ASG)
            • Launch Templates
            • Instance Refresh for ASG
            • Scale to or from Zero
            • Spot Instances for AWS
          • ECS Autoscaling
          • Autoscaling in Kubernetes
        • Configure Auto-reboot
        • Create Amazon Machine Image (AMI)
        • Hibernate an EC2 Host
        • Snapshots
        • Taints for EKS Nodes
        • Disable Source Destination Check
      • Auditing
      • Logs
        • Enable Default-Tenant logging
        • Enable Non-Default Tenant logging
        • Configure Logging per Tenant
        • Display logs
        • Create custom logs
      • Diagnostics and Metrics
        • Metrics Setup
        • Metrics Dashboard
        • Kubernetes Administrator dashboard
      • Faults and Alerts
        • Alert notifications
        • Automatic alert creation
        • Automatic fault healing
        • SNS Topic Alerts
        • System Settings Flags
      • AWS Console link
      • Just-in-Time (JIT) Access
      • Billing and Cost management
        • Enable billing data
        • View billing data
        • Apply cost allocation tags
        • DuploCloud License Usage
        • Configure Billing Alerts
      • Resource Quotas
      • Big Data and ETL
      • Custom Resource tags
    • AWS Services
      • Containers and Services
        • EKS Containers and Services
          • Allocation Tagging
        • ECS Containers, Task Definitions and Services
        • Passing Configs and Secrets
        • Container Rollback
        • Docker Registry credentials
      • Load Balancers
        • Target Groups
        • EKS Load Balancers
        • ECS Services and Load Balancers
        • Native Docker Load Balancers
      • Storage
        • Storage Class and PVCs
        • GP3 Storage Class
      • API Gateway
      • Batch
      • CloudFront
      • Databases
        • AWS ElastiCache
        • AWS DynamoDB database
        • AWS Timestream database
        • RDS database
          • IAM authentication
          • Backup and restore
          • Sharing encrypted database
          • Manage RDS Snapshots
          • Add and manage RDS read replicas
            • Add Aurora RDS replicas
          • Add monitoring interval
          • Enable or disable RDS logging
          • Restrict RDS instance size
          • Add parameters in Parameter Groups
          • Manage Performance Insights
      • Data Pipeline
      • Elastic Container Registry (ECR)
        • Sharing ECR Repos
      • Elastic File System (EFS)
        • Mount an EFS in an EC2 instance
      • EMR Serverless
      • EventBridge
      • IoT (Internet of Things)
      • Kafka Cluster
      • Kinesis Stream
      • Lambda Functions
        • Configure Lambda with Container Images
        • Lambda Layers
      • Managed Airflow
      • NAT Gateway for HA
      • OpenSearch
      • Probes and Health Check
      • S3 Bucket
      • SNS Topic
      • SQS Queue
      • Virtual Private Cloud (VPC) Peering
      • Web App Firewall (WAF)
    • AWS FAQ
    • AWS Systems Settings
      • AWS Infrastructure Settings
      • AWS Tenant Settings
    • AWS Security Configuration Settings
      • Tenant Security settings
      • Infrastructure Security settings
      • System Security settings
      • AWS Account Security settings
      • Vanta Compliance Controls
  • GCP User Guide
    • Container deployments
      • Container orchestration features
      • Key DuploCloud concepts
    • Prerequisites
      • Docker Registry
      • Service Account Setup
      • Cloud DNS Zone
      • Certificates for Load Balancer and Ingress
      • Initial Infrastructure Setup
      • Tools Tenant
        • Enable Kubectl Shell
      • Docker
        • Docker Registry Credentials (Optional)
        • Shell Access for Docker (Optional)
      • VPN
        • VPN Setup
        • Connect to the VPN
      • Managed SSL Certificates with Certificate Manager (Optional)
    • GCP Quick Start
      • Step 1: Create Infrastructure and Plan
      • Step 2: Create a Tenant
      • Create a Service with GKE Autopilot
        • Step 3: Create a Service
        • Step 4: Create a Load Balancer
        • Step 5: Test the Application
      • Create a Service with GKE Standard
        • Step 3: Create a Node Pool
        • Step 4: Create a Service
        • Step 5: Create a Load Balancer
        • Step 6: Test the Application
    • GCP Use Cases
      • Creating an Infrastructure and Plan for GCP
        • Creating a GKE Autopilot Cluster
        • Creating GKE Standard Cluster
        • Kubectl token and config
        • Upgrading the GKE version
      • Creating a Tenant (Environment)
        • Tenant expiry
        • Tenant Config settings
      • Hosts (VMs)
      • GKE Maintenance Windows
      • Cost management for billing
        • Export Billing to BigQuery
        • Manage cross project billing in GCP
    • GCP Services
      • Containers and Services
      • GKE Containers and Services
        • Allocation Tagging
        • Docker Registry credentials
        • Container Rollback
        • Passing Config and Secrets
      • GCP Databases
        • Cloud SQL
        • Firestore Database
        • Managed Redis
      • Load Balancers
      • Cloud Armour
      • Cloud Credentials
      • Cloud Functions
      • Cloud Run Service
      • Cloud Scheduler
      • Cloud Storage
      • Node Pools
      • Pub/Sub
      • Virtual Private Cloud (VPC) Peering
      • GCP Security Command Center
    • GCP FAQs
    • GCP Systems Settings
      • GCP Infrastructure Settings
      • GCP Tenant Settings
    • GCP Security Settings
      • Infrastructure Security settings
      • GCP Account Security settings
  • Azure User Guide
    • Container deployments
      • Container orchestration features
      • Key DuploCloud concepts
    • Prerequisites
      • Program DNS Entries
      • Import SSL certificates
      • Provision the VPN
      • Connect to the VPN
      • Managed Identity Setup
    • Azure Quick Start
      • Step 1: Create Infrastructure and Plan
      • Step 2: Create a Tenant
      • Step 3: Create Agent Pools
      • Step 4: Create a Service
      • Step 5: Create a Load Balancer
      • Step 6: Test the Application
    • Azure Use Cases
      • Creating an Infrastructure and Plan for Azure
        • AKS initial setup
        • Kubectl token and config
        • Encrypted storage account
        • Upgrading the AKS version
      • Creating a Tenant (Environment)
        • Tenant expiry
        • Tenant Config settings
      • Hosts (VMs)
        • Autoscaling for Hosts
          • Autoscaling Azure Agent Pools
        • Shared Hosts
        • Availability Sets
        • Snapshots
      • Logs
      • Metrics
      • Faults and alerts
        • Alert notifications
      • Azure Portal link
      • Billing and Cost management
        • Enable billing data
        • Viewing billing data
    • Azure Services
      • Containers and Services
        • AKS Containers and Services
          • Allocation Tagging
        • Docker Registry Credentials
        • Container Rollback
        • Passing Configs and Secrets
      • Agent Pools
        • Spot Instances for AKS Agent Pools
      • Azure Container Registry (ACR)
      • Databases
        • MSSQL Server database
        • PostgreSQL database
        • PostgreSQL Flexible Server
        • MySQL Server database
          • Azure Managed SQL Instances
        • MySQL Flexible Server
        • Redis database
      • Docker Web Application
      • Databricks
      • Data Factory
      • Infra Secrets
      • Key Vault
      • Load Balancers
      • Public IP Address Prefix
      • Serverless
        • App Service Plans and Web Apps
        • Function Apps
      • Service Bus
      • Storage Account
      • Subscription
      • VM Scale Sets
    • Azure FAQ
    • Azure Systems Settings
      • Azure Infrastructure Settings
      • Azure Tenant Settings
    • Azure Security Settings
      • Tenant Security Settings
  • Kubernetes User Guide
    • Kubernetes Quick Start
    • Kubectl
      • Local Kubectl Setup
        • Kubectl Shell
      • Kubectl Shell
        • Enable Kubectl Shell for GKE
        • Enable Kubectl Shell for AKS
      • Kubectl Tokens and Access Management
      • Read-only Access in Kubernetes
      • Mirantis Lens
    • Configs and Secrets
      • Setting Kubernetes Secrets
      • Creating a Kubernetes ConfigMap
      • Setting Environment Variables (EVs) from a ConfigMap or Secret
      • Mounting ConfigMaps and Secrets as files
      • Using Kubernetes Secrets with Azure Storage connection data
      • Creating the SecretProviderClass Custom Resource to mount secrets
      • Managing Secrets and ConfigMaps access for readonly users (AWS and GCP)
    • Jobs
    • CronJobs
    • DaemonSet
    • Helm Charts
    • Ingress Loadbalancer
      • EKS Ingress
      • GKE Ingress
      • AKS Shared Application Gateway
        • Using an Azure Application Gateway SSL policy with Ingress
    • InitContainers and Sidecar Containers
    • HPA
    • Pod Toleration
    • Kubernetes Lifecycle Hooks
    • Kubernetes StorageClass and PVC
      • Native Azure Storage Classes
    • Import an External Kubernetes Cluster
    • Managed Service Accounts (RBAC)
    • Create a Diagnostics Application Service
  • Security and Compliance
    • Control Groups
    • Isolation and Firewall
      • Cloud Account
      • Network Segmentation
      • IAM
      • Security Groups
      • VPN
      • WAF
    • Access Management
      • Authentication Methods
      • Cloud Console, API and CLI
      • VM SSH
      • Container Shell
      • Kubernetes Access
      • Permission Sets
    • Encryption
      • At Rest Encryption
      • In Transit encryption
    • Tags and Label
    • Security Monitoring
      • Agent Management
      • SIEM
      • Vulnerabilities
      • Hardening Standards (CIS)
      • File Integrity Monitoring
      • Access Monitoring
      • HIDS
      • NIDS
      • Inventory Monitoring
        • Inventory Reports
      • Antivirus
      • VAPT (Pen Test)
      • AWS Security HUB
      • Alerting and Event Management
    • Compliance Frameworks
    • Security and Compliance Workflow
  • Terraform User Guide
    • DuploCloud Terraform Provider
    • DuploCloud Terraform Exporter
      • Install Terraform Exporter
      • Generate Terraform
      • Using Generated Code
      • Troubleshooting Guide
    • Terraform FAQ
  • Automation and Tools
    • DuploCtl CLI
    • Supported 3rd Party Tools
    • Automation Stacks
      • Clone from a Tenant
      • Create a deploy template
      • Deploy from a template
      • Customize deploy templates
  • CI/CD Overview
    • Service Accounts
    • GitHub Actions
      • Configure GitHub
      • Build a Docker image
      • Update a Kubernetes Service
      • Update an ECS Service
      • Update a Lambda function
      • Update CloudFront
      • Upload to S3 bucket
      • Execute Terraform
    • CircleCI
      • Configure CircleCI
      • Build and Push Docker Image
      • Update Service
    • GitLab CI/CD
      • Configure Gitlab
      • Build a Docker image
      • Update a service
    • Bitbucket Pipelines
      • Configure Bitbucket
      • Build a Docker image
      • Update the Service with Deploy Pipe
    • Azure Pipelines
      • Configure Azure DevOps
      • Build a Docker image from Azure DevOps
      • Update a Service
      • Troubleshooting
    • Katkit
      • Environments
      • Link repository
      • Phases
      • Katkit config
      • Advanced functions
    • ArgoCD
  • User Administration
    • User Logins
    • User access to DuploCloud
    • User Email Notifications
    • API tokens
    • Session Timeout
    • Tenant Access for Users
      • Add Tenant access over a VPN
      • Read-only access to a Tenant
      • Cross-tenant Access
      • Deleting a Tenant
    • VPN access for users
    • Database access for users
    • SSO Configuration
      • Azure SSO Configuration
      • Okta Identity Management
    • Login Banner/Button Customization
  • AI Suite
    • AI HelpDesk
      • Ticket
      • Out of the Box Agents
    • AI Studio
      • Agent
      • Tools
      • VectorDB
      • Developers
    • FAQ
  • Observability
    • Standard Observability Suite
      • Setup
        • Logging Setup
          • Custom Kibana Logging URL
        • Metrics Setup
        • Auditing
          • Custom Kibana Audit URL
      • Logs
      • Metrics
    • Advanced Observability Suite
      • Architecture
      • Dashboards
        • Administrator Dashboard
        • Tenant Dashboard
        • Customizing Dashboards
      • Logging with Loki
      • Metrics with Mimir
      • Tracing with Tempo
      • Profiles with Pyroscope
      • Alerts with Alert Manager
      • Service Level Objectives (SLOs)
      • OTEL Stack Resource Requirements
      • Application Instrumentation
      • Custom Metrics
      • Terraform
    • Faults and Alerts
      • Alert notifications
      • Automatic alert creation
    • Auditing
    • Web App Firewall (WAF)
  • Runbooks
    • Configuring Egress and Ingress for AKS Ingress Controllers in Private Networks
    • Configuring Retool to SSH into a DuploCloud Host with a Static IP Address for Secure Remote Database
  • FAQs
  • Extras
    • FluxCD
    • Deploying Helm Charts
    • Setting up SCPs (Service Control Policies) for DuploCloud
    • BYOH
    • Delegate Subdomains
    • Video Transcripts
      • DuploCloud AWS Product Demo
      • DuploCloud Azure Product Demo
      • DuploCloud GCP Product Demo
      • DevOps Deep Dive - Abstracting Cloud Complexity
      • DuploCloud Uses Infrastructure-as-Code to Stitch Together DevOps Lifecycle
Powered by GitBook
LogoLogo

Platform

  • Overview
  • Demo Videos
  • Pricing Guide
  • Documentaiton

Solutions

  • DevOps Automation
  • Compliance
  • Platform Engineering
  • Edge Deployments

Resources

  • Blog & News
  • Customer Stories
  • Webinars
  • Privacy Policy

Company

  • Careers
  • Press
  • Events
  • Contact

© DuploCloud, Inc. All rights reserved. DuploCloud trademarks used herein are registered trademarks of DuploCloud and affiliates

On this page
  • Managed Vector DBs
  • Third-Party Vector DBs
  • Integrating Vector DBs with DuploCloud
  • Prerequisites
  • Integrating a Third-Party Vector DB
  • Integrating a Managed Vector DB
  • Uploading Files
  • Ingesting Files
  • Viewing Ingestion Jobs
  • Using VectorDBs with DuploCloud AI Studio

Was this helpful?

Edit on GitHub
Export as PDF
  1. AI Suite
  2. AI Studio

VectorDB

In the DuploCloud AI Suite, the Vector Database (VectorDB) enables you to upload documents, such as architecture diagrams, runbooks, internal wikis, or API references, that you want the AI agent to use for context during conversations. These documents are transformed into high-dimensional vector representations, which allow the system to retrieve the most relevant content when the agent processes your queries. This enhanced context allows the agent to better understand your cloud environment, use your terminology, and align with your organization’s best practices.

DuploCloud supports two types of Vector DBs:

Managed Vector DBs

DuploCloud deploys and manages Vector DBs directly within your Kubernetes environment, handling setup, environment variables, and connectivity for seamless integration. Supported engines include:

  • Chroma: Lightweight, fast, ideal for local AI workloads.

  • MilvusDB: Scalable for high-performance vector search at large scale.

Use managed Vector DBs if you want to keep all components within your cloud account, prefer zero setup, or don’t have an external vector DB provider.

Third-Party Vector DBs

These are externally hosted vector databases like Pinecone or PostgreSQL that DuploCloud connects to but does not manage or deploy.

Choose third-party Vector DBs if you already use an external provider or need to integrate with specialized vector DB services outside your Kubernetes cluster.

Integrating Vector DBs with DuploCloud

The first step for working with vector databases in DuploCloud is to integrate a Vector DB with the DuploCloud AI Suite. This allows the platform to store and retrieve vectorized content.

Prerequisites

  • You must have access to the AI Suite feature in the DuploCloud Portal.

  • For third-party Vector DBs (e.g., Pinecone), make sure you have your API endpoint and any necessary authentication information.

  • For managed Vector DBs (e.g., Chroma, Milvus), ensure your Kubernetes environment is ready to deploy services.

Integrating a Third-Party Vector DB

To integrate a third-party vector database, such as Pinecone:

  1. In the DuploCloud Platform, navigate to AI Suite → Studio → Vector DBs.

  2. Click Add. The Add Vector Database pane displays.

  1. Complete the following fields:

Name

Enter a friendly name for the Vector DB.

Vector DB Type

Select pinecone for a third-party Vector DB.

API Endpoint

Enter the endpoint URL for your Pinecone instance.

Metadata

Optionally, enter key-value pairs to organize or filter this Vector DB later.

  1. Click Submit to save the Vector DB. Your third-party Vector DB is ready to use immediately.

Integrating a Managed Vector DB

To integrate a DuploCloud-managed Vector DB (Chroma or MilvusDB), add and then deploy the database in the DuploCloud Platform.

Adding a Managed Vector DB

  1. In the DuploCloud Platform, navigate to AI Suite → Studio → Vector DBs.

  2. Click Add. The Add Vector Database pane displays.

  3. Complete the following fields:

Name

Enter a friendly name for the Vector DB.

Vector DB Type

Select your Vector DB type, (e.g., chroma or milvusdb).

Deployment Environment Variables

Optionally, add custom environment variables (e.g., API keys, flags).

Metadata

Optionally, enter key-value pairs for organizing or tagging the Vector DB.

  1. Click Submit to save the Vector DB.

Note: Adding a Managed Vector DB within DuploCloud saves the configuration, but does not deploy the database. Deployment is required before you can upload or ingest files.

Deploying a Managed Vector DB

After adding a managed Vector DB, deploy it to make it active and usable.

  1. Navigate to AI Suite → Studio → Vector DBs.

  2. Select the Vector DB from the NAME column.

  3. Select the Deployment tab, and click Deploy. The Deploy pane displays.

  1. Review or complete the deployment fields:

Name

Auto-filled with the Vector DB name; can be customized if desired.

Docker Image

Auto-filled for managed Vector DBs. For third-party Vector DBs, confirm or provide the correct image if applicable.

Deployment Environment Variables

Define any environment variables required for your Vector DB.

Advanced Options

Optional settings such as replicas, service name, network, volumes, and load balancer listeners.

  1. Choose either:

    • Quick Deploy to deploy with default settings immediately.

    • Advanced to customize deployment options before deploying.

  2. If using Advanced Deploy, click Next to navigate through additional configuration screens, then click Create to start deployment. For Quick Deploy, click Quick Deploy.

  3. Monitor the deployment status; it usually takes 4 to 5 minutes. Once complete, the status on the Deployment tab will show Running.

Uploading Files

Upload your source documents or data files to your AWS S3 storage to make your files available for processing and ingestion into the Vector DB.

  1. In the DuploCloud portal, go to AI Suite → Studio → Vector DBs.

  2. Select the Vector DB you want to upload files to from the NAME column.

  3. Select the Uploaded Files tab.

  4. Click Browse. This will open your AWS S3 console where you can select the files you want to upload.

  5. Select the files to upload (Click Upload Files → Add File, select your file(s), and click Open).

  6. Return to the DuploCloud Uploaded Files tab, and click Sync to update the Vector DB’s Uploaded Files list. The uploaded files are displayed on the Uploaded Files tab.

Ingesting Files

Ingesting transforms your uploaded files into vector representations.

  1. In the DuploCloud portal, go to AI Suite → Studio → Vector DBs.

  2. Select the Uploaded Files tab.

  3. Click the checkbox(s) to select one or more files you want to ingest.

  4. Click Ingest. The Trigger Build pane displays.

  5. Configure the fields as needed:

    • Review the Docker Image: This field is prepopulated with the container used for ingestion. You usually do not need to change it unless you're using a custom image.

    • Timeout: Enter the maximum duration (in minutes) for the ingestion job.

    • Custom Meta Data (Optional): Use key-value pairs to customize how the ingestion job processes your data. Common options include:

      • chunk_size: Size of each text chunk in characters (e.g., 1000).

      • chunk-overlap: Number of overlapping characters between chunks (e.g., 100).

  6. Click Submit to trigger the ingestion job. Monitor the ingestion status on the Ingested Jobs tab.

Viewing Ingestion Jobs

After uploading and ingesting documents into a Vector DB, you can monitor the status and output of each job in the Ingestion Jobs tab. This tab provides access to ingestion history, logs, and detailed configuration metadata to help validate behavior and troubleshoot issues.

  • In the DuploCloud portal, go to AI Suite → Studio → Vector DBs.

  • Select the Ingestion Jobs tab.

  • Choose one of the following options:

    • Logs: View output that includes source file paths, chunking progress, chunk IDs, and any success or error messages.

    • Details: Open a structured JSON summary showing Vector DB type and provider, API endpoint, file paths ingested, output directory, chunking configuration, embedding model, and other technical metadata.

Using VectorDBs with DuploCloud AI Studio

PreviousToolsNextDevelopers

Last updated 6 days ago

Was this helpful?

Click the menu icon () next to the job you want to inspect.

To learn how to integrate the files uploaded to your VectorDBs with the DuploCloud AI agent, see the DuploCloud documentation for .

creating AI Agents
The Add Vector Database pane
The Vector DBs page in the DuploCloud AI Suite Studio
The Add Vector Database pane in the DuploCloud Portal
The Deploy pane for the duplo-managed-db Vector DB
The Deployment tab for the Vector DB with status Running
The AWS S3 Console
The Uploaded Files tab in the DuploCloud Platform
The Trigger Build pane
The Ingested Jobs tab in the DuploCloud Platform
The Ingestion Jobs tab with the Logs and Details menu options highlighted
The Logs for an ingested job
The Details for an ingested job