Dynamiq Docs
  • Welcome to Dynamiq
  • Low-Code Builder
    • Extractors and Transformers
    • 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
    • Red Hat OpenShift
  • Support Center
Powered by GitBook
On this page
  • Adding a New Prompt
  • Updating Existing Prompts

Prompts

PreviousVector DatabasesNextPrompt Playground

Last updated 7 months ago

Prompts, in the Dynamiq platform, are reusable templates. Each prompt is versioned - versioning enables prompt reusability while preserving previous versions, which can be crucial for testing and iterative development.

Adding a New Prompt

To add a new prompt:

  1. Navigate to the Prompts page and select Add new prompt.

  2. Fill out the form on the right panel:

    • Name: Enter a descriptive name for the prompt.

    • Specify the prompt’s template in the Prompt section. You can choose between two views:

      • Visual: A user-friendly interface for inputting text.

      • Raw: JSON format for more complex prompt structures.

    • Add a new prompt message by clicking Add message

      • Each message must have a Role:

        • User: Represents input coming from the user.

        • Assistant: Represents AI assistant.

        • System: Represents system message.

      • The Content section may include not only regular text but also contain dynamic fields. To use dynamic fields using {{...}} syntax (e.g., {{question}}), which will be replaced at runtime based on provided data.

  3. Once all fields are filled out, click Create to save the prompt. The system will automatically assign a version v1 to the new prompt. Future updates to the prompt will result in new versions (e.g., v2), which allows tracking changes over time and maintaining backward compatibility.

Updating Existing Prompts

To update an existing prompt:

  1. Navigate to the Prompts page.

  2. Find the prompt you wish to update and click the Edit icon next to it. This will open the prompt's configuration panel on the right side.

  3. Modify necessary fields.

  4. Once your updates are complete, click Update to save the changes. This action will automatically create a new version (e.g., from v2 to v3) and store it in the Versions tab.