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
  • Deploying Workflows
  • Using Deployed Workflows
  • Testing Deployed Workflows
  1. Deployments

Workflows

PreviousDeploymentsNextTracing Workflow Execution

Last updated 5 months ago

This guide covers how to deploy, test, and manage workflows on the Dynamiq platform. It provides instructions on creating deployments, using workflows via API, tracking and tracing operations, and reviewing deployment history.

Deploying Workflows

  • Navigate to the Deployments tab:

    • From the main navigation menu, select Deployments.

    • In the Workflows section, click Deploy a workflow to deploy the workflow.

  • Select deployment type:

    • In the side panel, choose Workflow. This option allows you to deploy workflows and integrate them into your application using API.

  • Configure the workflow deployment:

    • Name: Assign a meaningful name to your deployment to help identify it in the future.

    • Description: Optionally, add a description for better context on the deployment's purpose.

    • Source Workflow: Select the workflow you want to deploy from the dropdown menu.

    • Source Version: Choose the version of the workflow to deploy. This helps manage different workflow iterations and ensures consistent deployment.

    • Runtime: Choose the appropriate runtime version. The platform will default to the latest version if not specified.

  • Create Deployment:

    • Once configured, click Create to deploy the workflows. The new deployment will be listed under Deployments with its status and details.

Using Deployed Workflows

Once your workflow is deployed. Go to the Endpoint tab. You will see a Python code example to interact with it. The provided code sample illustrates how to make a request to the endpoint, including options for configuring request headers, payload, and handling streaming responses if enabled.

All workflow deployments are private. You will need to use the access key to access the deployment. The example code snippet in the Endpoint tab shows how to include the authorization token using DYNAMIQ_ACCESS_KEY environment variable.

Testing Deployed Workflows

Navigate to the Test tab within the deployment details. This interface allows you to interact with the deployed workflow by sending inputs and viewing responses directly in the UI.

In the Input section of the Test tab, you can provide a JSON object to simulate data being sent to the workflow's endpoint. This input should follow the expected schema defined by your workflow. Once you’ve entered the input data:

  1. Click Run: This triggers the workflow to process the input and returns the result.

  2. Observe the Output: The Result section displays the JSON output generated by the workflow.

The platform provides a real-time response, allowing you to iteratively test various inputs and review how the workflow handles them.