Advanced Orchestration
Advanced Orchestration Assistant and Application
Start
Start Node: The starting node of the workflow, used to set the information required to initiate the workflow.
Input: Simply understood as pre-defining the basic information (input parameters) needed for the LLM to complete a task. When in use, the LLM will remember these information requirements and automatically call these pre-set parameters when it detects the timing to initiate a task during a conversation, placing the parameters in the corresponding positions to start the entire process.
You can define the required input variable names.
Model
Model: Calls the large language model to generate responses using variables and prompts.
Input: Select an existing model from the dropdown menu and choose input variable names.
Message: Provides high-level guidance for the conversation.
User Message: Provides instructions, queries, or any text-based input to the model.
💡 Tip: You need to connect to the preceding node first to select variables from other nodes as input variables for the current node.
Skills
Currently, three default skills can be added to advanced orchestration: Web Search, Text-to-Image, Webpage Reading.
You can input the preceding node variables as their query or URL inputs and obtain corresponding output variables.
Code
Code: Write code to process input variables and generate return values.
Input: Used to receive externally passed variables, serving as the entry point for the data required for code execution and providing raw data for subsequent code processing.
Code Configuration: Set parameters related to code execution (e.g., maximum runtime) and provide a code writing area to write logic for processing input variables.
Output: After processing the input data, the code outputs the results in the form of specified variables, serving as the exit for the code processing results.
Selector
Selector: Plays a conditional judgment role in process orchestration. It connects multiple downstream branches and determines the execution path based on the set conditions.
Conditional Branches: Multiple conditions can be set, such as "if - priority 1." By configuring referenced variables, selecting conditions (e.g., equal to, greater than, comparison logic), and comparison values, it determines whether the condition is met. If met, the corresponding branch process is executed.
Knowledge Base
Input: By defining variable names and setting parameter values, it provides original data such as retrieval keywords for knowledge base searches.
Knowledge Base: Select a specific knowledge base as the search scope. The system will search for matching information within this scope.
Maximum Recall Quantity: You can set the maximum number of matching results returned from the knowledge base to avoid excessive data.
Output: Outputs the matching information retrieved from the knowledge base in the form of specified variables for use in subsequent processes.
Intent Recognition
Intent Recognition: A key step in natural language processing, this module analyzes user input to determine their true intent and match preset options.
Model: Select the model used for intent recognition, which determines the capability and effectiveness of intent recognition.
Intent Matching: Pre-enter user intent descriptions as matching criteria or add other intents. The system will determine which preset intent the user input matches.
Advanced Settings: You can set system prompt content and reference input variables to optimize prompt effects. You can also set the number of historical memory entries to allow the model to refer to past conversation information and improve recognition accuracy.
Text
Text: Mainly used for processing string-type variable formats.
Input: You can define variable names and reference parameter values to provide original string data for subsequent text processing.
String Concatenation: Provides a text editing area where you can use variable names to reference input variables as needed and perform operations such as concatenating multiple strings.
File Processing
File Processing: A functional module for operations such as searching file content.
Input: By defining variable names and referencing parameter values, it provides input information such as retrieval keywords as the basis for file content searches.
File: You can add files to be processed to this node to determine the scope of the search.
