Unify AI is a comprehensive AI operations node that provides a suite of machine learning and AI capabilities directly within automation workflows.

Overview

Unify AI is a comprehensive AI operations node that provides a suite of machine learning and AI capabilities directly within automation workflows. Its actions span document processing, text and semantic analysis, ML model lifecycle management, computer vision, and code analysis — enabling automations to incorporate AI processing without building custom model infrastructure.

Document Processing

Actions for reading, extracting, and chunking content from documents and files for downstream AI processing such as embedding generation, RAG pipelines, and summarization.

• Read PDF File Pages — Extracts text content from PDF files on a per-page basis, returning structured page-level data suitable for chunking and indexing

• Read File — Reads content from a file (e.g., txt, docx) and returns the raw text for processing

• Chunk File (Docling) — Splits a single document into semantic chunks using Docling's layout-aware chunking strategy, producing output ready for embedding

• Chunk Files (Docling) (Batch) — Processes multiple files in batch, chunking each and returning all chunks as a unified list for bulk indexing workflows

• Document Tampering Detection — Detects edits made to a PDF after it was issued, and recovers the original text where a word was changed

• SSN Masking — Masks Social Security numbers in a PDF file

Text and Semantic Analysis

Actions for splitting text into manageable segments and generating embeddings for NLP pipelines.

• Text Splitter — Splits text into chunks of a maximum size using the algorithm you choose: Recursive Character, Token, Character, Language aware, Code, Semantic, Passthrough, Tree-Sitter Code Chunker or Parent-Child. The Semantic algorithm uses an embedding model (default sentence-transformers/all-mpnet-base-v2).

• Call Embedding Async — Generates embeddings for a text by calling the UnifyAI embedding model asynchronously

ML Operations

Actions for fine-tuning and deploying custom machine learning models within the UnifyApps AI infrastructure.

• Model Fine Tuning Job — Schedules a recurring fine-tuning job for a fine-tuned model you have already set up. You choose how often it runs (every N minutes, minimum 5).

• Deploy Fine Tuned Model — Deploys a completed fine-tuned model to an inference endpoint, making it available for use in Call LLM Model or Execute Prompt actions

Note: Fine-tuning jobs may take significant time to complete. Use the workflow's run monitoring tools to track job status for long-running fine-tuning operations.

Computer Vision

Actions for image-based AI processing. For video, use the Video by UnifyApps node.

• Extract Face Embedding — Generates a vector embedding representing the facial features in an image, suitable for face matching, verification, and identity management workflows

• Image Converter — Converts images between formats. Output formats: PNG (default), JPEG, JPG, BMP, TIFF and WEBP.

• Remove Image Background — Removes the background from an image

• Remove Image Background (Batch) — Removes the background from a list of images

Code Analysis

Actions for converting source code into structured graph representations for analysis, dependency mapping, and code intelligence applications.

• Transform Python Code to Graph — Parses Python source code and produces a graph representation of its structure (functions, classes, imports, call relationships), enabling static analysis and architecture visualization

• Transform Java Code to Graph — Performs the same graph transformation for Java source code, supporting dependency analysis and refactoring workflows

Notes

Keep the following in mind when using Unify AI:

• Choose the action category (Document Processing, Computer Vision, etc.) that matches the task; the Unify AI node groups actions to make it easier to find the right operation.

• AI processing time varies by input size; design timeout settings and error handlers to account for longer response times when processing large documents or images.

• Validate AI output with an assertion or conditional branch before using it in downstream critical operations; model responses may be unexpected for edge-case inputs.

• Unify AI has no classification or extraction action; for those tasks, use an AI Agent or a prompt instead.

• Computer Vision actions require image inputs; pre-process images with the Files or Utility node to confirm they are in a supported format and within size limits before calling Unify AI.