Wiro - Seed-V2 Mini LLM icon

Wiro - Seed-V2 Mini LLM

Explore the Seed-V2 Mini LLM by ByteDance, designed for efficient AI inference and NLP tasks. P

Wiro - Seed-V2 Mini LLM

AI-generated

Overview

This node integrates with the Seed-V2 Mini LLM by ByteDance via the Wiro API to perform natural language processing tasks. It allows users to input a prompt along with optional parameters such as image URLs for visual context, user and session IDs for chat history, system instructions, and various model tuning parameters like temperature, top-p, penalties, and reasoning depth. The node sends these inputs to the Wiro API, waits for the task to complete by polling the API, and returns the generated response. This node is useful for applications requiring AI-driven text generation, chatbots, or contextual language understanding with optional visual input.

Use Case Examples

  1. Generating AI responses based on user prompts with optional visual context.
  2. Building chatbots that maintain session and user history for personalized interactions.
  3. Performing NLP tasks with configurable model parameters to control output randomness and reasoning depth.

Properties

Name Meaning
Input Image URL Optional. Multiple image files separated by semicolon for visual understanding.
Prompt Required. The main text input for the model to process.
User ID Optional. Required for chat history. Numeric or string ID to identify the user.
Session ID Optional. Required for chat history. Numeric or string ID to identify the session.
System Instructions Optional. System-level instructions for the model to guide its behavior.
Temperature Optional. Controls randomness of the output. Range [0, 2]. Default is 1.
Top P Optional. Nucleus sampling threshold controlling diversity. Range [0, 1]. Default is 0.7.
Frequency Penalty Optional. Penalizes repeated tokens by frequency. Range [-2, 2]. Default is 0.
Presence Penalty Optional. Encourages new topics. Range [-2, 2]. Default is 0.
Max Completion Tokens Optional. Maximum number of output tokens including chain-of-thought. Range [0, 65536]. Default is 65536.
Reasoning Effort Optional. Controls reasoning depth of the model. Default is medium.
Thinking Type Optional. Enable or disable deep thinking mode. Default is enabled.

Output

JSON

  • taskid - The unique identifier of the task submitted to the Wiro API.
  • message - The response message or output generated by the Seed-V2 Mini LLM.
  • status - The status of the task, indicating if it completed successfully or failed.

Dependencies

  • Wiro API key and secret for authentication

Troubleshooting

  • If the node throws an error indicating missing or invalid task ID or socket access token, verify that the Wiro API credentials are correct and the API is reachable.
  • Polling may fail or timeout if the task takes too long or the socket access token is invalid; ensure network connectivity and valid tokens.
  • Incorrect or missing required parameters like prompt may cause the API to reject the request; ensure all required inputs are provided.

Links

Discussion