Azure DeepSeek LLM icon

Azure DeepSeek LLM

Interact with DeepSeek LLM on Azure AI Foundry

Actions2

LLM Chain

AI-generated

Overview

This node interacts with the Azure DeepSeek LLM (Large Language Model) service to process text inputs using a specified language model. It is designed to send a text prompt to the DeepSeek LLM and receive generated text responses. This is useful for scenarios such as text generation, summarization, or any natural language processing task where a language model is required.

Use Case Examples

  1. Generating a summary of a given text input.
  2. Creating a continuation or response based on a user-provided prompt.
  3. Customizing the output by adjusting model parameters like temperature and max tokens.

Properties

Name Meaning
Text The input text to be processed by the language model.
Options Additional parameters to customize the LLM request, including model selection, sampling temperature, maximum token length, and request timeout.

Output

JSON

  • text - The generated text output from the language model.
  • content - Same as text; the content generated by the model.
  • _fullResponse - The complete raw response object returned from the Azure DeepSeek LLM API.

Dependencies

  • Requires an Azure DeepSeek API key credential for authentication and access to the Azure AI Foundry service.

Troubleshooting

  • Timeout errors may occur if the request takes too long; increase the request timeout setting to resolve.
  • Network errors can happen if the Azure endpoint is unreachable; verify network connectivity and endpoint URL.
  • API errors from Azure DeepSeek LLM will include error messages; check the error details for troubleshooting.

Discussion