Skip to main content

LVM Call Tool

The LVM Call Tool allows users to interact with a language or vision model (LVM) by providing a prompt, media URL, and model ID. Users can also configure guardrails validators to ensure the quality and relevance of the model's output. This guide will walk you through the steps to effectively use this tool.

Steps to Use the LVM Call Tool​

Step 1: Access the Tool​

  • Click on Add User Step.
  • From the available options, select the LVM Call Tool.

Step 2: Input the Prompt​

You need to provide a prompt for the LVM. You have two options for entering the prompt:

  • Manual Entry: Type the entire prompt directly into the input field.
  • User Input Variable: Use a user input variable to dynamically provide the prompt. Use the syntax {{variable_name}} to access the value of an input variable. For example, if there is an input parameter named “promptText”, you can access its value using {{promptText}}.

Step 3: Input the Media URL​

You need to provide the URL of the media to be processed by the LVM. You have two options for entering the media URL:

  • Manual Entry: Type the URL of the media directly into the input field.
  • User Input Variable: Use a user input variable to dynamically provide the media URL. To use input variables within your media URL, use the syntax {{variable_name}} to access the value of an input variable. For example, if there is an input parameter named “mediaURL”, you can access its value using {{mediaURL}}.

Step 4: Select the Model​

Choose the model from the available list of models that have the capability to respond to media files.

Step 5: Configure Guardrails Validators (Optional)​

You can set up guardrails validators to ensure the model's output meets certain criteria. Set up validators based on your specific needs. This may include rules for output quality, relevance, or other criteria.

Step 6: Execute the LVM Call​

Once you have entered the prompt, media URL, and model ID, initiate the LVM call:

  1. Run the tool: Click the Run button to start the LVM call process.
  2. Results: The tool will process your request and interact with the model based on the provided inputs.

Step 7: View the Output​

The output from the LVM will be displayed in the results section. The results will be presented in a structured format, often in plain text or JSON, depending on the nature of the output.

Step 8: Utilize the Results​

You can now use the LVM's output for further processing, analysis, or integration into your application.

Tips for Effective Use​

  • Clear Prompts: Provide clear and specific prompts to get the most relevant output from the model.
  • Correct URLs: Ensure the media URL is correct and accessible to avoid errors during the processing.
  • Appropriate Model ID: Choose the model ID that best fits your use case for accurate results.
  • Effective Guardrails: Apply guardrails validators to ensure the quality and relevance of the output.

If you have any questions or need further assistance, please contact the helpdesk([email protected]).