FreeLim icon

FreeLim

逆向LLM

Overview

This node implements a conversational text completion feature for the 阿里通义 (Ali Tongyi) resource, specifically supporting the "对话补全" (dialogue completion) operation. It allows users to send a series of messages with roles (user, assistant, system) to an AI model or intelligent agent and receive a generated response that continues or completes the conversation.

Common scenarios include:

  • Building chatbots that simulate human-like conversations.
  • Automating customer support interactions.
  • Creating virtual assistants that respond contextually based on prior messages.
  • Generating dialogue content for applications such as games or interactive stories.

For example, a user can provide a sequence of messages representing a conversation history, and the node will generate the next assistant reply, optionally simplifying the output or using specific voice options for text-to-speech synthesis.

Properties

Name Meaning
模型 (assistantId) The model or intelligent agent identifier to use for generating responses. Can be any string; if unknown, any value can be used.
消息 (messages) A collection of message objects forming the conversation history. Each message includes:
- 文本 (content): The message text to send.
- 角色 (role): The role shaping the model's response behavior, options are 用户 (user), 助手 (assistant), 系统 (system).
简化输出 (simplify) Boolean flag indicating whether to return a simplified version of the response instead of raw data. Defaults to true.
语音列表 (voice) Selection of voice for text-to-speech output. Supports official voices from a predefined list or custom cloned voices. Required when text-to-speech is enabled.

Output

The node outputs JSON data containing the AI-generated response completing the dialogue based on the input messages. If text-to-speech is enabled, it may also output audio data corresponding to the selected voice.

  • json: Contains the structured response from the AI model, typically including the generated message text and possibly metadata.
  • Binary data (if applicable): Represents synthesized speech audio matching the generated text, using the chosen voice.

Dependencies

  • Requires access to the 阿里通义 API or service endpoint capable of processing conversational completions.
  • Uses an internal router module (./actions/router) to handle the execution logic.
  • For voice selection, supports querying a list of official and cloned voices via a search method (ttsListSearch).
  • May require appropriate API credentials or authentication tokens configured in n8n to authorize requests.

Troubleshooting

  • Missing or invalid model identifier: Providing an incorrect or empty model ID might cause the API to reject the request or produce unexpected results. Verify the model name or use a known valid identifier.
  • Improper message formatting: Messages must include both content and role fields. Omitting these or using unsupported roles could lead to errors or poor responses.
  • Text-to-speech issues: If TTS is enabled but no valid voice is selected, the node may fail to generate audio output. Ensure a voice is chosen from the official list or a valid cloned voice string is provided.
  • API connectivity problems: Network issues or invalid credentials can cause failures. Check API keys and network access.
  • Simplify option confusion: When simplify is true, the output is a condensed version which might omit some details present in the raw response. Set to false if full data is needed.

Links and References


This summary is based solely on static analysis of the provided source code and property definitions without runtime execution.

Discussion