Alibaba Cloud Model Studio:Workflow application

Start/End

• When to use

  • When designing a workflow, determine the structure and content of input/output parameters and fill them into the Start/End nodes.

• How to use

  • Start node

    Component	Description
    Variable Name	The name of the input parameter. Subsequent nodes can call the variable by its name.
    Type	The data type of the input parameter. Ccurrently, it only supports String, Boolean, and Number. If you need to pass in Array or Object, you need to parse it yourself before the workflow.
    Description	The description of the input parameter, used to explain the purpose of the parameter.

    Note

    In addition to custom variables, the application also has some built-in utility variables:

    • query

      The user's query. Used to receive the prompt variable from API calls or text sent by users in the test window.

    • historyList (only in dialog workflows)

      The conversation history list, used for the application to automatically maintain conversation history records and provide multi-round conversation experience.

    • imageList (only in dialog workflows)

      The image list, used to store images uploaded by users in the test window. Currently only supports storing a single image.

  • End node

    Component	Description
    Output Mode	The format of the output parameters. Valid values: Text Output and JSON Output.
    Text Box (in text output mode)	You can freely arrange the paragraph format of the output content, supporting text input or variable references, suitable for unstructured content.
    Variable Name/Variable Value (in JSON output mode)	Output content must be arranged according to JSON format. You can customize variable names and support text input or variable references, suitable for structured content.
    Response	Only effective when calling the application via API, used to decide whether to output the node content. To understand the purpose of this component, see Control node content using "Response".

Knowledge Base

• Why use it

  Imagine you have an enormous "knowledge repository" containing massive documents, FAQs, and product information. This node helps you extract the "most relevant" content from this massive information, preparing for subsequent AI Q&A.

• Function and usage

  • Retrieves one or more knowledge bases to obtain relevant document chunks. This allows the LLM to read more context and provide more professional or accurate answers. Often used in conjunction with LLM nodes.

  • Commonly used when building dialog workflows or intelligent customer service systems.

• Parameters

  Parameter	Parameter Description
  Input	content: You can directly input text or reference variables output from previous nodes.
  	imageList: Supports image search. You can directly input image links or reference variables output from previous nodes.
  Select Knowledge Base	Specify which knowledge bases to search in (supports multiple selections).
  Output	Name the result variable of this node, such as kbResult.

• Output structure example:

  {
    "rewriteQuery": "...",
    "chunkList": [
      {
        "score": 0.36,
        "documentName": "Document Name",
        "title": "Document Title",
        "content": "Related Content Fragment",
        "imagesUrl": "Image URL"
      }
    ]
  }

  The commonly used part here is chunkList, which contains document chunks and similarity scores.

LLM

• Why use it

  The LLM can understand language, generate text, analyze images, and participate in multi-round conversations. You can use it to write copy, summarize text, or analyze image content (if a VL model is used).

• Features

  • It can process one input at a time or batch process large amounts of data.

  • You can use different LLMs based on performance, speed, or other characteristics.

• Parameters

  Parameter	Parameter Description
  Mode	Single Mode: Fast search version with a lower search ratio and without query rewriting.
  	Batch Mode: The node will run multiple times. Each time it runs, an item from the list is sequentially assigned to the batch variable. This process will continue until all items in the list have been processed or the maximum number of batches has been reached. Batch Configuration: Maximum Number of Batches: The upper limit for batch iterations. Valid range: 1 to 100. The default value for regular users: 100. Note The actual number depends on the minimum length of the arrays in the user's input. If there are no input variables, it depends on the number of batches configured. Number of Parallel Runs: The concurrency limit of batch processing. If you set this value to 1, all tasks are executed in series. Valid range: 1 to 10.
  Model Configuration	Choose a suitable LLM and configure model parameters . For a list of supported models, see Supported models. When selecting a VL model: Model Input Parameters: Use vlImageUrl to reference a variable or enter image URLs. Image Source: Choose from Image Set or Video Frame. Image Set: The model considers uploaded images independent from each other and will match the images and queries for understanding. Video Frame: The model considers the uploaded images from the same video and understands the images sequentially as a whole. The number of video frames must be no less than four.
  Parameter Configuration	Temperature: Adjusts content diversity. Higher values increase randomness and uniqueness, while lower values yield more predictable and consistent results.
  	Maximum Reply Length: The maximum text length generated by the model, not including the prompt. This limit varies by model, and the exact maximum may differ.
  System Prompt	Defines the role, task, and output format of a model. For example, "You are a math expert, specializing in solving math problems. Please output the math problem-solving process and results in the specified format."
  User Prompt	Set up the prompt template and insert variables. The model will generate content based on this configuration.
  Output	The variable name for the output of the node. Subsequent nodes can identify and process the variable by its name.

  Note

  To integrate the application into your business through API, see Application calling.

• LLM node in dialog workflows

  • Different from the LLM node of task-based workflows, the LLM node of dialog workflows supports multi-round conversations.

    Round Configuration: The application collects the variables from previous rounds specified in Context and passes them as input parameters to the LLM.

    

  • Context: The context required by the LLM. The default ${System Variables.historyList} represents the input and output of the application from previous rounds. Other parameters refer to the variables from previous rounds.

    

• Text model example

  Click Test and enter Chip Engineer as the query:

  

  Sample output:

  

• Visual model example

  The model supports accepts either a single image or multiple images and supports input as URL and base64.

  Note

  Directly input a single image, such as https://****.com/****.jpg.

  Input multiple images as a list, such as ["URL", "URL", "URL"].

  Click Test, enter https://****.com/****.jpg as the query.

  

  Sample output:

  

API

• Definition

  Call custom API services via POST, GET, PUT, PATCH, DELETE methods, and output the API call results.

  Call Method	Purpose
  POST	Used to submit data to the server to create a new resource.
  GET	Used to retrieve a representation of a resource, without modifying data on the server.
  PUT	Used to update the representation of a specified resource on the server or create a new resource on the server.
  PATCH	Used to partially update a resource on the server.
  DELETE	Used to delete a specified resource from the server.

• Parameters

  Parameter	Description
  API Request URL	The API address to call. Valid values: POST, GET, PUT, PATCH, DELETE.
  Header Settings	Configure Header parameters, setting KEY, VALUE.
  Param Settings	Configure Param parameters, setting KEY, VALUE.
  Body Settings	Valid values: none, form-data, raw, JSON.
  Output	The variable name for the output of the node. Subsequent nodes can identify and process the variable by its name.

  Note

  To integrate the application into your business through API, see Application Call.

• Node example

  Using the POST method to call an interface.

  

Intent Classification

• Definition

  Intelligently classify and match based on intent descriptions, selecting one path to execute.

• Parameter

  Parameter	Description
  Input	Enter the variables to be processed in this node. You can reference variables of preceding nodes or the Start node, or enter the variable values.
  Model Configuration	Select Qwen-Plus.
  Intent Configuration	Configure different intent categories and corresponding descriptions. The model matches subsequent links based on the descriptions. For example: "Math problems" and "Weather Q&A".
  Other Intents	If no other intents are matched, this link is matched.
  Intent Mode	Single Selection: The LLM selects and outputs the most appropriate intent from Intent Configuration. Multiple Selection: The LLM selects and outputs all matching intents from Intent Configuration.
  Thinking Mode	Speed Mode: This mode does not output the thinking process to improve its speed. Suitable for simple scenarios. Effect Mode: This mode thinks step by step to output more accurate answers.
  Advanced Configurations	You can provide additional prompts to the model as advanced configurations, where you can input more conditions or examples to make the model's classification more in line with your requirements. Example Suppose you are developing a customer service system for an e-commerce platform, and users may ask various questions about order inquiries, returns, and payments. To ensure accurate classification by the model, you can add relevant prompts and examples in the advanced configuration. Please classify the intent based on the following examples: Example 1: User input "I want to return the coat I just bought", classified as "Return". Example 2: User input "Please help me check the shipping status of the order", classified as "Order Inquiry". Conditions: Only process queries related to orders, ignore payment and technical issues. Effect: User input: "When can the book I ordered on your website last week be delivered to my home?" Classification result: "Order Inquiry" In this example, the advanced configuration guides the model to classify "query delivery time" as the "Order Inquiry" intent by providing specific classification examples, while also limiting the classification scope and excluding other unrelated issues.
  Context	When Context is enabled, the system will automatically record historical conversation in the Message format. When calling the model, the context will be passed in, and the model will generate based on the context content. This configuration item is only available in the intent classification node of dialog workflows. Note When Context is enabled, the variable passed in this node must be of the List type.
  Output	The name of the variable processed by this node. Subsequent nodes can identify and process the variable by its name.

  Note

  • This node supports context in dialog workflows.

  • Running this node will consume tokens. The consumption amount will be displayed.

Text Conversion

• Definition

  Used for text content conversion and processing, such as extracting specific content or converting formats, and supports template mode.

• Parameters

  Parameter	Description
  Output Mode	Choose from Text Output and JSON Output.
  Input box	Specify a processing method in which the LLM converts the input into a specific format. You can reference the result of the predecessor nodes through variables. Text Output: Enter / to insert variables. JSON Output: Enter variable name and select Reference or Input.

• Node example

  The following example shows a basic text conversion workflow: After the user enters a keyword. The text conversion node receives this keyword and processes it, producing an appropriate output.

  Click Test and enter Mathematics as the query:

  

  Sample output:

  

Script Conversion

• Definition

  Uses the specified code to convert the input into a specific format or form. The process includes parsing, converting, and formatting for consistency and readability.

• Parameters

  Parameters	Parameter Description
  Input	Enter the variables to be processed in this node. You can reference variables of preceding nodes or the Start node, or enter the variable values.
  Code	The code to convert the input to a specific format for subsequent nodes. In the code, you can reference variables from preceding nodes.
  Output	The name of the variable processed by this node. Subsequent nodes can identify and process the variable by its name.

• Node example

  The following example shows a basic script conversion workflow. The user first inputs two parameters, which are then passed to the Script Conversion node. Inside the node, the code processes these parameters and ultimately generates the required output.

  Click Test and enter Beijing for City and February 10, 2022 for Date:

  

  Sample output:

  

Conditional Judgment

• Definition

  Specify conditions for the Conditional Judgment node. The node selects subsequent link based on the conditions. You can configure and/or conditions. If multiple conditions are met, the links are executed from top to bottom.

• Parameters

  Parameter	Description
  Conditional Branch	Enter the conditional judgment statements.
  Other	Outputs without conditional judgment.

• Node example

  The following example shows a Conditional Judgement workflow. The user inputs two parameters, which are then passed to the Conditional Judgment node. Inside the node, the parameters undergo conditional evaluation, and then the output response is generated through different branches of the text conversion node.

  Click Test and enter 12345 for secret and admin for admin.

  

  Sample output:

  

Function Compute

• Definition

  Authorizes and call custom services in Function Compute.

• Parameters

  Parameter	Description
  Input	Enter the variables to be processed in this node. You can reference variables of preceding nodes or the Start node, or enter the variable values.
  Region	Select one of the regions: Singapore, Kuala Lumpur, Jakarta.
  Service Configuration	Select the service configuration.
  Output	The name of the variable processed by this node. Subsequent nodes can identify and process the variable by its name.

Plugin

• Definition

  Enhances workflow's functionality to perform more sophisticated tasks. Model Studio offers a series of official plug-ins, including Calculator and Image Generation. You can also develop custom plug-ins based on your requirements.

  For more information, see Plugin overview.

Workflow application related

Node related