Dynamiq Docs
  • Welcome to Dynamiq
  • Low-Code Builder
    • Chat
    • Basics
    • Connecting Nodes
    • Conditional Nodes and Multiple Outputs
    • Input and Output Transformers
    • Error Handling and Retries
    • LLM Nodes
    • Validator Nodes
    • RAG Nodes
      • Indexing Workflow
        • Pre-processing Nodes
        • Document Splitting
        • Document Embedders
        • Document Writers
      • Inference RAG workflow
        • Text embedders
        • Document retrievers
          • Complex retrievers
        • LLM Answer Generators
    • LLM Agents
      • Basics
      • Guide to Implementing LLM Agents: ReAct and Simple Agents
      • Guide to Agent Orchestration: Linear and Adaptive Orchestrators
      • Guide to Advanced Agent Orchestration: Graph Orchestrator
    • Audio and voice
    • Tools and External Integrations
    • Python Code in Workflows
    • Memory
    • Guardrails
  • Deployments
    • Workflows
      • Tracing Workflow Execution
    • LLMs
      • Fine-tuned Adapters
      • Supported Models
    • Vector Databases
  • Prompts
    • Prompt Playground
  • Connections
  • LLM Fine-tuning
    • Basics
    • Using Adapters
    • Preparing Data
    • Supported Models
    • Parameters Guide
  • Knowledge Bases
  • Evaluations
    • Metrics
      • LLM-as-a-Judge
      • Predefined metrics
        • Faithfulness
        • Context Precision
        • Context Recall
        • Factual Correctness
        • Answer Correctness
      • Python Code Metrics
    • Datasets
    • Evaluation Runs
    • Examples
      • Build Accurate vs. Inaccurate Workflows
  • Examples
    • Building a Search Assistant
      • Approach 1: Single Agent with a Defined Role
      • Approach 2: Adaptive Orchestrator with Multiple Agents
      • Approach 3: Custom Logic Pipeline with a Straightforward Workflow
    • Building a Code Assistant
  • Platform Settings
    • Access Keys
    • Organizations
    • Settings
    • Billing
  • On-premise Deployment
    • AWS
    • IBM
  • Support Center
Powered by GitBook
On this page
  1. Deployments

Vector Databases

PreviousSupported ModelsNextPrompts

Last updated 6 months ago

This guide walks you through deploying a vector database on the Dynamiq platform, which allows you to integrate open-source vector databases like Weaviate seamlessly.

  1. Navigate to the Deployments page.

  2. Select the Vector Databases sub-tab within the Deployments page.

    • If no vector databases have been created yet, you’ll see a message: “You don't have any vector databases yet.” Click on Deploy a vector database to get started.

  3. In the Add new deployment form, provide the following details:

    • Name: Enter a unique name for your vector database deployment.

    • Description: Optionally, add a brief description to clarify the database’s purpose or any specific details about its use.

    • Engine: Choose the database engine you want to use. Currently, Dynamiq supports Weaviate.

    • Engine Version: Select the version of the Weaviate engine. For example, 1.25.0.

    • Choose a Resource Profile from the options available. Each profile specifies the computational resources for the deployment.

    • Advanced Configuration:

      • Replicas: Set the number of replicas for your vector database. The default is 1.

      • Storage Size: Specify the storage size for the database (e.g., 10Gi).

  4. After filling out the advanced configurations, click Create to initiate the database deployment. Once you submit the form, Dynamiq will initiate the deployment process. You’ll be redirected to a page where you can view the status of your deployment. It may initially show as Pending. The database will be available for usage in a couple of minutes once the status is transitioned to Running.

  5. Connect to the database:

    • After the deployment is complete (it has status Running), navigate to the Access section.

    • You’ll see the connection details, including two pairs of roles and API keys. These keys are essential for secure access to the vector database.

    • To connect to your vector database:

      • Set WEAVIATE_API_KEY environment variable with the credentials found in the Access section.

      • Use the provided code snippet in Python to establish a connection to Weaviate.

      • Ensure you have the necessary client library installed. Run:

pip install weaviate-client