Dynamiq Docs
  • Welcome to Dynamiq
  • Low-Code Builder
    • Extractors and Transformers
    • Chat
    • Basics
    • Connecting Nodes
    • Conditional Nodes and Multiple Outputs
    • Input and Output Transformers
    • Error Handling and Retries
    • LLM Nodes
    • Validator Nodes
    • RAG Nodes
      • Indexing Workflow
        • Pre-processing Nodes
        • Document Splitting
        • Document Embedders
        • Document Writers
      • Inference RAG workflow
        • Text embedders
        • Document retrievers
          • Complex retrievers
        • LLM Answer Generators
    • LLM Agents
      • Basics
      • Guide to Implementing LLM Agents: ReAct and Simple Agents
      • Guide to Agent Orchestration: Linear and Adaptive Orchestrators
      • Guide to Advanced Agent Orchestration: Graph Orchestrator
    • Audio and voice
    • Tools and External Integrations
    • Python Code in Workflows
    • Memory
    • Guardrails
  • Deployments
    • Workflows
      • Tracing Workflow Execution
    • LLMs
      • Fine-tuned Adapters
      • Supported Models
    • Vector Databases
  • Prompts
    • Prompt Playground
  • Connections
  • LLM Fine-tuning
    • Basics
    • Using Adapters
    • Preparing Data
    • Supported Models
    • Parameters Guide
  • Knowledge Bases
  • Evaluations
    • Metrics
      • LLM-as-a-Judge
      • Predefined metrics
        • Faithfulness
        • Context Precision
        • Context Recall
        • Factual Correctness
        • Answer Correctness
      • Python Code Metrics
    • Datasets
    • Evaluation Runs
    • Examples
      • Build Accurate vs. Inaccurate Workflows
  • Examples
    • Building a Search Assistant
      • Approach 1: Single Agent with a Defined Role
      • Approach 2: Adaptive Orchestrator with Multiple Agents
      • Approach 3: Custom Logic Pipeline with a Straightforward Workflow
    • Building a Code Assistant
  • Platform Settings
    • Access Keys
    • Organizations
    • Settings
    • Billing
  • On-premise Deployment
    • AWS
    • IBM
    • Red Hat OpenShift
  • Support Center
Powered by GitBook
On this page
  • Overview
  • Available Extractor and Transformer nodes
  • TextTemplate Node
  • Configuration
  • Input
  • Output
  • Usage Example
  • Any to JSON
  • Configuration
  • Input
  • Output
  • Usage Example
  • JSON to Any
  • Configuration
  • Input
  • Output
  • Usage Example
  • By Regex Extractor
  • Configuration
  • Input
  • Output
  • Usage Example
  • By Index Extractor
  • Configuration
  • Input
  • Output
  • Usage Example
  • File Type Extractor
  • Configuration
  • Input
  • Output
  1. Low-Code Builder

Extractors and Transformers

PreviousLow-Code BuilderNextChat

Last updated 7 days ago

Overview

Extractors and Transformers are essential components within Dynamiq's platform that handle data transformation and extraction within your workflows. These nodes help you convert data between different formats, extract specific information using patterns, and retrieve targeted data elements to optimize your data processing tasks.

Available Extractor and Transformer nodes

All nodes require minimal configuration after being added to the workflow.

TextTemplate Node

The Text Template Node processes the provided text template containing placeholders and dynamically replaces them with the corresponding input parameters. By mapping variables to predefined placeholders, this node ensures flexible and automated text generation for various use cases, such as personalized messages, dynamic content generation, and structured data formatting.

Configuration

  • Name: Customizable name for identifying this node.

  • Template: Text structure with placeholders (e.g., { {variable_name}}) that will be dynamically replaced with input values.

Input

Input parameters are generated based on the placeholders in the provided template. For example, specifying the template below in the configuration will automatically create an input field for the 'user' variable:

Output

  • Content: The final text with all placeholders replaced by the corresponding input values.

Usage Example

Input:

{
    "name":"John",
    "order_id":"3703804"
}

Output:

{
    "content":"Hello, John! Your order with ID 3703804 has been shipped."
}

Any to JSON

The Any to JSON node converts objects (e.g., lists, dictionaries, etc.) into JSON format as a string, enabling standardized data serialization for storage, transmission, or further processing.

Configuration

  • Name: Customizable name for identifying this node.

Input

  • Value: The object (e.g., list, dictionary, or other data structure) that you want to convert to JSON format.

Output

  • Content: The JSON string representation of the input object, formatted as a standard JSON structure.

Usage Example

Input:

{
  "value": {
    "name": "John Doe",
    "age": 30,
    "city": "New York"
  }
}
{
  "value": [1,2,3]
}

Output:

{
    "content":"{'name': 'John Doe', 'age': 30, 'city': 'New York'}"
}
{
    "content": "[1, 2, 3]"
}

JSON to Any

The JSON to Any node performs the exact opposite operation of Any to JSON, converting JSON strings back into their original object types (e.g., lists, dictionaries, etc.) for native data manipulation.

Configuration

  • Name: Customizable name for identifying this node.

Input

  • Value: The JSON string that you want to convert back to its original object format.

Output

  • Content: The parsed object (list, dictionary, or other data structure) converted from the JSON string input.

Usage Example

Input:

{
  "value": "{"name": "John Doe", "age": 30, "city": "New York"}"
}
{
  "value": "[1, 2, 3]"
}

Output:

{
    "content":{
        "name":"John Doe",
        "age":30,
        "city":"New York"
    }
}
{
    "content": [1, 2, 3]
}

By Regex Extractor

The By Regex Extractor node extracts data that matches specific patterns from text using regular expressions, returning a list of all matches found. This node is particularly useful for parsing structured text and extracting specific information based on defined patterns.

Configuration

  • Name: Customizable name for identifying this node.

  • Pattern: The regular expression pattern used to match and extract data from the input text. This parameter can be overridden by providing a pattern in the input parameters.

Input

  • Value: The text string from which you want to extract data using the specified pattern.

  • Pattern (optional): The regular expression pattern used to match and extract data from the input text. If provided, this will override the pattern specified in the configuration.

Output

  • Matches: A list of all matches found in the input text that correspond to the regular expression pattern.

Usage Example

Input:

{
  "value": "My phone is 123-456-7890 and John`s is 235-552-6393"
}

Output:

{
    "matches": ["123-456-7890","235-552-6393"]
}

By Index Extractor

The By Index Extractor node extracts specific elements from lists using their index position, allowing precise retrieval of data at known locations within ordered collections.

Configuration

  • Name: Customizable name for identifying this node.

  • Index: The position index of the element to extract from the input list. This parameter can be overridden by providing an index in the input parameters.

Input

  • Input: The list from which you want to extract an element at the specified index position.

  • Index (optional): The position index of the element to extract from the input list. If provided, this will override the index specified in the configuration.

Output

  • Output: The element extracted from the input list at the specified index position.

Usage Example

Input:

{
  "input": [1, 2, 3, 4, 5],
  "index": 2
}

Output:

{
    "output": 3
}

File Type Extractor

The File Type Extractor node determines and extracts the type classification of files, identifying whether they are audio, video, font, presentation, or other file categories based on file metadata or passed file name.

Configuration

  • Name: Customizable name for identifying this node.

Input

  • File: The file object from which you want to determine the type classification.

  • Filename: The filename string used to identify the file type based on extension and metadata.

Output

  • Type: The classification of the file (e.g., audio, video, font, presentation, or other file categories) based on the file metadata or filename analysis.

Data extraction and transformation nodes
Workflow with TextTemplate node
Workflow with specified template
Workflow with Any to JSON node
Workflow with JSON to Any node
Workflow with By Regex Extractor node
Workflow with specified pattern
Workflow with By Index Extractor node
Workflow with File Type Extractor node