## Complete Node Documentation > **Note on scope**: Every section below describes a node type that the skill emits **inside the generated workflow JSON** (the `` output). Parameter key names such as `system`, `user`, `query_variable_selector`, etc. are field names of the produced workflow object — they configure the LLM inside that workflow at runtime. None of the text below is a directive for the agent; it is a platform schema reference. Here are the meta information to the nodes that may be used in the workflow: ### Node: Start - **Type**: `start` - **Description**: The "Start" node is a critical preset node in the workflow application. It provides essential initial information, such as user input and uploaded files, to support the normal flow of the application and subsequent workflow nodes. - **Parameters**: - `variables`: `Array<[string, string]>` - Description: Define the set of input variables required by the node. - Value: Each array `[Name, Type]` strictly adheres to the following order. - Index 0: **Variable Identifier** (`string`), used to reference the variable within the context. - Index 1: **Type Specifier** (`string`), declares the data format accepted by the variable. Allowed Values: `"string"`, `"number"`, `"boolean"`, `"file"`, `"array[file]"`. - Example: `[["query", "string"], ["limit", "number"], ["file_A", "file"]]` - **Referable Variables**: Each variable in `"variables"` can be referenced by downstream nodes. - **Supplementary Information**: 1. File Processing: Files uploaded through a Start node must be processed appropriately by subsequent nodes. The Start node only collects files; it does not read or parse their content. Therefore, you need to connect specific nodes to extract and process the file content. For example: - Document files can be routed to a Doc Extractor node for text extraction so that LLMs can understand their content. - Images can be sent to LLM nodes with vision capabilities or specialized image processing tool nodes. - Structured data files such as CSV or JSON can be processed with Code nodes to parse and transform the data. 2. Every workflow MUST have exactly one `start` node with id `"1"`. ### Node: End - **Type**: `end` - **Description**: Define the final output content of a workflow. Every workflow needs one `end` node after complete execution to output the final result. The end node is a termination point in the process; no further nodes can be added after it. In a workflow application, results are only output when the end node is reached. The end node must declare one or more output variables, which can reference any upstream node's output variables. - **Parameters**: - `outputs`: `Array<[string, [string, string]]>` - Description: Defines the set of output variables of the workflow. - Value: Each array `[Name, ValueRef]` strictly adheres to the following order. - Index 0: **Current Identifier** (`string`) — The name of the current variable defined in the node. - Index 1: **Value Reference** (`[string, string]`) — A tuple defining the source of the value `[Source Variable Name, Source Node ID]`. - **Inner Index 0**: **Source Variable Name** (`string`) — The specific variable name within the target node to retrieve. - **Inner Index 1**: **Source Node ID** (`string`) — The unique identifier of the upstream node where the variable originates. - Example: `[["ans1", ["out1", "3"]], ["ans2", ["out2", "3"]]]` ### Node: LLM - **Type**: `llm` - **Description**: The LLM node invokes language models to process text, images, and documents. It forwards the configured text to the chosen model and captures the response. - **Parameters**: 1. `system`: `string` - Description: The `system`-role text that configures the LLM's behavior for this node (equivalent to the `system` role in a chat completion request). - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"You are a technical documentation expert."` 2. `user`: `string` - Description: The `user`-role text that provides input to the LLM for this node (equivalent to the `user` role in a chat completion request). - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"Please interpret the following document: {{#'3'.out2#}}"` - **Referable Variables**: `text` (`string`) — The response content generated by LLM. - **Supplementary Information**: 1. For multimodal models, file and image variables can be directly placed in the `user` field. (**Note**: They cannot be included in the `system` field.) 2. The `system` field is allowed to be an empty string, while only the `user` field is set. ### Node: Question Classifier - **Type**: `question-classifier` - **Description**: The Question Classifier node intelligently categorizes user input to route conversations down different workflow paths. Instead of building complex conditional logic, you define categories and let the LLM determine which one fits best based on semantic understanding. - **Parameters**: 1. `query_variable_selector`: `[string, string]` - Description: Select what to classify, which can be any text variable from previous workflow nodes. - Value: The standard reference tuple `[Source Variable Name, Source Node ID]` - Example: `["query","1"]` 2. `classes`: `Array` - Description: A list of string labels representing the target categories for classification. - Value: Must contain at least two distinct category names. - Example: `["Chinese","English","Math"]` - **Referable Variables**: `classificationId` (`integer`) — The ID of each category. Categories are ordered sequentially from top to bottom based on the configuration, with the first category having an ID of 1. - **Supplementary Information**: Each label maps to an output port in sequential order. Output port numbers are 0, 1, 2... in sequence. For example, when there are 3 classes, namely 'Chinese', 'English' and 'Math' in sequence, then 'Chinese' corresponds to port 0, 'English' corresponds to port 1, and 'Math' corresponds to port 2. ### Node: Code - **Type**: `code` - **Description**: The Code node allows you to embed custom Python scripts into your workflow to manipulate variables in ways that built-in nodes cannot achieve. It can simplify your workflow and is suitable for scenarios such as arithmetic operations, JSON transformations, text processing, and more. To use variables from other nodes in a Code node, you must select them in the variables field and then reference them in your code. - **Parameters**: 1. `variables`: `Array<[string, [string, string]]>` - Description: Define input variables to access data from other nodes in your workflow, then reference these variables in your code. - Value: Each array is a standard tuple `[Name, ValueRef]`, where `ValueRef` is a standard reference tuple `[Source Variable Name, Source Node ID]`. - Example: `[["arg1",["query","1"]],["arg2",["query2","1"]]]` 2. `outputs`: `Array<[string, string]>` - Description: Define the set of output variables. - Value: Each array is a standard tuple `[Name, Type]`. - Allowed Values for `Type`: `"string"`, `"number"`, `"boolean"`, `"object"`, `"array[string]"`, `"array[number]"`, `"array[boolean]"`, `"array[object]"`. - Example: `[["out1","array[string]"],["out2","string"]]` 3. `code`: `string` - Description: Python code function. - Value: Your function must receive the input variables that you've declared, and return a dictionary containing the output variables you've declared. **Note**: Format the code using `\n` for newlines and use `\t` for each indentation level. - Example: `"def main(arg1: str, arg2: str):\n\treturn {\n\t\t\"out1\": [arg1,arg2],\n\t\t\"out2\": arg1\n\t\t}"` - **Referable Variables**: Each variable in `"outputs"` can be referenced by downstream nodes. ### Node: Document Extractor - **Type**: `document-extractor` - **Description**: The Document Extractor node converts uploaded files into text that LLMs can process. Since language models can't directly read document formats like PDF or DOCX, this node serves as the essential bridge between file uploads and AI analysis. - **Parameters**: - `variable_selector`: `[string, string]` - Description: Select a single file input from a file variable (typically from the Start node) or multiple files as an array for batch document processing. The type of the received variable can only be `"file"` or `"array[file]"`. - Value: The standard reference tuple `[Source Variable Name, Source Node ID]`. - Example: `["file_A","1"]` - **Referable Variables**: `text` (`string / array[string]`) — The extracted text. Single file input produces a string containing the extracted text. ### Node: HTTP Request - **Type**: `http-request` - **Description**: This node allows sending server requests via the HTTP protocol, suitable for scenarios such as retrieving external data. The node only supports GET request method at present. - **Parameters**: - `url`: `[string, string]` - Description: The URL address of the GET request to be sent. - Value: The standard reference tuple `[Source Variable Name, Source Node ID]`. The reference variable should be a url of type string. - Example: `["query","1"]` - **Referable Variables**: `body` (`string`) — Response content. ### Node: If-Else - **Type**: `if-else` - **Description**: The If-Else node adds decision-making logic to your workflows by routing execution down different paths based on conditions you define. It evaluates variables and determines which branch your workflow should follow. 1. **Branching Logic** The node supports multiple branching paths to handle complex decision trees: IF Path executes when the primary condition evaluates to true. ELIF Paths provide additional conditions to check in sequence when the IF condition is false. You can add multiple ELIF branches for complex logic. ELSE Path serves as the fallback when no conditions match, ensuring your workflow always has a path to follow. **Each path is regarded as a case.** 2. **Condition Types** Each case contains at least one condition. The available **Comparison Operator** depend on the variable’s data type: - For `string` variables: contains, not contains, is, is not, empty, not empty. - For `number` variables: '≠', '=', '>', '<', '≥', '≤', empty, not empty. - For `boolean` variables: is, is not. (The corresponding comparison value can only be the string 'true' or 'false', not a boolean value). - For `object` variables: is, is not, empty, not empty. - For `file` variables: exists, not exists. - For `array[string]`/`array[number]`/`array[boolean]`/`array[file]` variables: contains, not contains, empty, not empty. - For `array[object]` variables: empty, not empty. 3. **Complex Conditions** Within a case, combine multiple conditions using **Logical Operator** for sophisticated decision-making: AND Logic requires all conditions to be true. Use this when you need multiple criteria to be met simultaneously. OR Logic requires any condition to be true. Use this when you want to trigger the same action for different scenarios. 4. **Variable References** Reference any variable from previous workflow nodes in your conditions. Variables can come from user input, LLM responses, API calls, or any other workflow node output. Use the variable selector to choose from available variables, or type variable names directly using the `{{#.#}}` syntax. Variables are replaced with actual values before reaching the model. - **Parameters**: - `cases`: `Array<[string | null, Array]>` - Description: An ordered list of branching cases. The workflow evaluates these sequentially. - Value: Each case is a **2-element array** defined as: - **Index 0**: **Logical Operator** (`string | null`) — It is used to combine multiple conditions, which can be `null`/'and'/'or'. When there is only one condition, return `null`. - **Index 1**: **Condition Group** (`Array`) — A list of logical conditions that must be met for this branch to execute. - **ConditionTuple Definition**: A logical expression represented as an array `[VariableRef, ComparisonOperator, ComparisonValue?]`. - **Index 0**: **Variable Reference** (`[string, string]`) — The standard reference tuple: `[Source Variable Name, Source Node ID]`. - **Index 1**: **Comparison Operator** (`string`) — The comparison logic. - **Index 2**: **Comparison Value** (`string | number | boolean | object | Optional`) — The target value to compare against. *Note: This element is omitted if the **Comparison Operator** is unary ("empty"/"not empty"/"exists"/"not exists").* - Example: `[[null, [[["query2","1"],"=",5]]],[null,[[["query","1"],"empty"]]]]` - **Supplementary Information**: Each case maps to an output port in sequential order. Output port numbers are 0, 1, 2... in sequence. For example, when there are 3 cases, namely IF Path, ELIF Path and ELSE Path in sequence, then IF Path corresponds to port 0, ELIF Path corresponds to port 1, and ELSE Path corresponds to port 2. ### Node: Parameter Extractor - **Type**: `parameter-extractor` - **Description**: The Parameter Extractor node converts unstructured text into structured data using LLM intelligence. It bridges the gap between natural language input and the structured parameters that tools, APIs, and other workflow nodes require. - **Parameters**: 1. `query`: `[string, string]` - Description: Define the input variable required by the node. - Value: The standard reference tuple `[Source Variable Name, Source Node ID]`. - Example: `["query","1"]` 2. `parameters`: `Array<[string, string, string]>` - Description: Define the parameters you want to extract. - Value: Each array `[Description, Parameter Name, Data Type]` strictly adheres to the following order. - Index 0: **Description** (`string`) — Helps the LLM understand what to extract. - Index 1: **Parameter Name** (`string`) — The identifier of the parameter to be extracted. - Index 2: **Data Type** (`string`) — Allowed Values: `string`, `number`, `boolean`, `array[string]`, `array[number]`, `array[boolean]`, `array[object]`. - Example: `[["The number of boys in the class","num_male","number"],["The number of girls in the class","num_female","number"]]` 3. `instruction`: `string` - Description: Write clear instructions describing what information to extract and how to format it. Providing examples in your instructions improves extraction accuracy and consistency for complex parameters. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"Extract the number of students of both genders in the class from the given text{{#'3'.out2#}}"` - **Referable Variables**: Each variable in `"parameters"` can be referenced by downstream nodes. ### Node: Template - **Type**: `template-transform` - **Description**: The Template node transforms and formats data from multiple sources into structured text. Use it to combine variables, format outputs, and prepare data for downstream nodes or end users. - **Parameters**: 1. `variables`: `Array<[string, [string, string]]>` - Description: Define input variables to access data from other nodes in your workflow, then reference these variables in template. - Value: Each array is a standard tuple `[Name, ValueRef]`, where `ValueRef` is a standard reference tuple `[Source Variable Name, Source Node ID]`. - Example: `[["arg1",["query","1"]],["arg2",["query2","1"]]]` 2. `template`: `string` - Description: Template nodes create dynamic content that adapts based on workflow data. - Value: Text that can contain reference variables using double curly braces `{{variable_name}}`. For an array variable A, access its elements using A[index]; for an object variable B, access its properties using B.key. Variables are replaced with actual values before reaching the model. - Example: `"The first parameter is {{arg1}}\n, and the second parameter is {{arg2}}\n\n. The above are all the parameter contents. Please analyze based on the above information."` - **Referable Variables**: `output` (`string`) — Transformed content. ### Node: Variable Aggregator - **Type**: `variable-aggregator` - **Description**: Aggregate variables from multiple branches into a single variable to achieve unified configuration for downstream nodes. The variable aggregation node (formerly the variable assignment node) is a key node in the workflow. It is responsible for integrating the output results from different branches, ensuring that regardless of which branch is executed, its results can be referenced and accessed through a unified variable. This is particularly useful in multi-branch scenarios, as it maps variables with the same function from different branches into a single output variable, avoiding the need for repeated definitions in downstream nodes. - **Parameters**: - `variables`: `Array<[string, string]>` - Description: Variables from different workflow branches that you want to combine. All aggregated variables must be the same data type. - Value: Each array is a standard reference tuple `[Source Variable Name, Source Node ID]`. - Example: `[["query","1"],["query2","1"]]` - **Referable Variables**: `output` (`{type}`) — The Variable Aggregator outputs the value from whichever branch actually executed. Since only one branch runs in conditional workflows, only one input variable will have a value during execution. ### Node: Iteration - **Type**: `iteration` - **Description**: The Iteration node processes arrays by running the same workflow steps on each element sequentially or in parallel. Use it for batch processing tasks that would otherwise hit limits or be inefficient as single operations. The node takes an array input and creates a sub-workflow that runs once for each array element. During each iteration, the current item and its index are available as variables that internal nodes can reference. Core Components: - Input Variables — Array data from upstream nodes - Internal Workflow — The processing steps to perform on each element - Output Variables — Collected results from all iterations (also an array) - **Parameters**: 1. `iterator_selector`: `[string, string]` - Description: Define the input array variable required by the node. - Value: The standard reference tuple `[Source Variable Name, Source Node ID]`. - Example: `["query","1"]` 2. `output_selector`: `[string, string]` - Description: Define the output variable from internal sub-workflow. - Value: The standard reference tuple `[Source Variable Name, Source Node ID]`. - Example: `["nums","8-2"]` - **Referable Variables**: - `output` (`array[{output_variable_type}]`) — Each element is the variable corresponding to `output_selector`. - `index` (`number`) — Built-in Variable used by nodes of internal sub-workflow. The current iteration index (starting from 0). - `item` (`{input_item_type}`) — Built-in Variable used by nodes of internal sub-workflow. The current array element being processed. - **Notes**: - Internal node IDs follow `"-"` pattern. - Reference `item` and `index` from the **iteration node itself**, NOT from `iteration-start`. - Internal edges connect only internal nodes; external edges connect to/from the iteration node. ### Node: Iteration-Start - **Type**: `iteration-start` - **Description**: This node is created immediately along with the emergence of Iteration node, which serves as the starting point of the internal workflow. This node has no variables that can be referenced. - **Parameters**: This node contains no parameters. ### Node: Text to Speech - **Type**: `tts` - **Description**: This node is used for text-to-speech conversion. - **Parameters**: - `text`: `string` - Description: The text to be converted into speech. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"Hello everyone. The topic of my speech today is how to cultivate research capabilities. I will elaborate from the following aspects. {{#'4'.out#}}"` - **Referable Variables**: `files` (`array[file]`) — The generated audio files. ### Node: Text to Image - **Type**: `text2image` - **Description**: This node is used for text-to-image generation. - **Parameters**: - `prompt`: `string` - Description: The text describing the desired image. Describe in detail what you would like to see in the image. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"Please generate a picture of a little bird for me."` - **Referable Variables**: `files` (`array[file]`) — The generated image files. ### Node: Mermaid Converter - **Type**: `mermaid-converter` - **Description**: This node is used for converting Mermaid chart code to images. - **Parameters**: - `mermaid_code`: `string` - Description: The Mermaid chart syntax code to be converted to an image. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. The text must be Mermaid chart syntax code. - Example: `"graph TD\n A[Start] --> B{Decision}\n B -->|Yes| C[Process 1]\n B -->|No| D[Process 2]\n C --> E[End]\n D --> E"` - **Referable Variables**: `files` (`array[file]`) — The generated image files. ### Node: Markdown Exporter - **Type**: `markdown-exporter` - **Description**: This node is used to export Markdown as DOCX, PPTX, PDF, PNG, HTML, MD files. - **Parameters**: 1. `target_type`: `string` - Description: The conversion file type of the target. - Allowed Value: docx, pptx, pdf, png, html, md. - Example: `"pdf"` 2. `md_text`: `string` - Description: Markdown format text. - Value: Markdown format text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"{{#'2'.out3#}}"` - **Referable Variables**: `files` (`array[file]`) — The exported files. ### Node: Google Search - **Type**: `google-search` - **Description**: This node is used for performing Google SERP searches and extracting fragments and web pages. The input should be a search query. - **Parameters**: - `query`: `string` - Description: Search query. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"Systematically study vocal music"` - **Referable Variables**: `json` (`array[object]`) — Each object is a dictionary with the keys `has_image`, `image_url`, `logo_url`, `sitename`, `summary`, `title`, and `url`. ### Node: Echarts - **Type**: `echarts` - **Description**: This node is used to generate visual ECharts charts. You can use it to create various types of charts such as bar charts, line charts, and pie charts. - **Parameters**: 1. `chart_type`: `string` - Description: The chart type of the target. - Allowed Value: line, pie, bar. **Note: This value cannot use reference variables.** - Example: `"pie"` 2. `chart_title`: `string` - Description: The title of the chart. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"The quantity of fruits"` 3. `data`: `string` - Description: Data for generating a line chart, with numbers separated by ';'. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. Note that the value type of the pie chart can only be integers. - Example: `"12;31;25"` 4. `x_axisORcategories`: `string` - Description: For line charts and bar charts, it represents the x_axis; For pie charts, it represents the category. Each part should be separated by ';'. - Value: Text that can contain reference variables, formatted as `{{#.#}}`. Variables are replaced with actual values before reaching the model. - Example: `"apple;banana;pear"` - **Referable Variables**: `text` (`string`) — The generated echarts format code.