Node categories
Text operations
Process and analyze text content
Document operations
Work with documents and files
Image operations
Analyze visual content
Data operations
Transform and enrich data
Custom Agent
Create custom agents with advanced capabilities powered by Model Context Protocol (MCP) tools.| Node | Description |
|---|---|
| Custom Agent | Create custom Agent with advanced capabilities |
Custom Agent node
Learn more about configuring Custom Agent nodes
AI Text Operations
Process, analyze, and generate text content.| Node | Description | Use cases |
|---|---|---|
| Text Transformation | Modify text tone, complexity or formatting for better clarity or style | Rewriting, simplification, tone adjustment |
| Text Understanding | Analyze text to determine sentiment, topics, intent, language and named entities | Sentiment analysis, topic classification, entity extraction |
| Text Generation | Generate new text such as summaries, completions, translations or paraphrases | Summaries, translations, content creation |
| Text Extraction | Extract structured information, keywords or metadata from text | Data extraction, keyword identification |
Configuration options
- Model selection - Choose the LLM for processing
- Temperature - Control creativity vs consistency
- Max tokens - Limit output length
- System prompt - Define behavior and constraints
AI Document Operations
Process documents to extract data, generate reports, or understand content.| Node | Description | Use cases |
|---|---|---|
| Document Generation | Automatically build reports or complete templates based on given inputs | Report generation, template completion |
| Document Extraction | Identify and extract structured data, entities or metadata from documents | Form processing, invoice data extraction |
| Document Understanding | Analyze documents to extract meaning, topics, sentiment, or important information | Document classification, content analysis |
| Extract Data from File | Extract text and data from documents and images with configurable extraction strategies | OCR, PDF text extraction, image data extraction, signature detection |
Extract Data from File
Learn more about configuring extraction strategies, image extraction, and signature detection
Configuration options
- Document type - Specify expected document format
- Schema definition - Define expected output structure
- Field mapping - Map extracted fields to data model
- Confidence threshold - Minimum score for extractions
AI Image Operations
Analyze and understand visual content.| Node | Description | Use cases |
|---|---|---|
| Image Description | Generate captions or extract detailed information from visual content | Alt text generation, image cataloging |
| Image Analysis | Recognize objects, emotions and scenes in images for contextual understanding | Object detection, scene classification, damage assessment |
Configuration options
- Detection confidence - Minimum threshold for detections
- Output format - Structured data or natural language
- Detail level - Brief or comprehensive analysis
AI Data Operations
Transform, enrich, and generate structured data.| Node | Description | Use cases |
|---|---|---|
| Data Enrichment | Add annotations, context or relationships to enhance raw data value | Data augmentation, context addition |
| Data Generation | Produce synthetic or structured data using templates and logic-based rules | Test data generation, data augmentation |
| Data Transformation | Clean, normalize, aggregate, or restructure datasets into usable formats | Data cleaning, format conversion |
Configuration options
- Schema definition - Define input/output structure
- Transformation rules - Specify data mapping logic
- Validation rules - Ensure output data quality
Combining nodes
Connect nodes in workflows to create processing pipelines:Best practices
Start simple
Start simple
Begin with a single node and add complexity incrementally. Test each addition before moving on.
Use appropriate nodes
Use appropriate nodes
Choose nodes based on your input type - use Document nodes for files, Text nodes for strings, Image nodes for visuals.
Handle errors
Handle errors
Include fallback paths for when nodes fail or return low-confidence results.
Monitor performance
Monitor performance
Track execution times and accuracy metrics to identify bottlenecks and improvement opportunities.