AI Node Catalog

Add a DataFusion SQL session to an agent for data analysis capabilities

7 in2 outSecurity 8/10

Agent from Model

Creates an Agent object from a model Bit with configuration

5 in1 outSecurity 5/10

Lazy Register Function Tools

Indexes referenced Flow-Like functions into a vector DB so agents can discover tools via semantic search at runtime, keeping the context window lean.

3 in2 outSecurity 5/10

Register Function Tools

Adds referenced Flow-Like functions as callable tool references to an Agent

1 in1 outSecurity 5/10

Register KG Traverse Tool

Registers a knowledge graph traversal tool on the agent so it can query the graph mid-conversation

4 in1 outSecurity 6/10

Register MCP Tools

Adds Model Context Protocol (MCP) server tools to an Agent

3 in1 outSecurity 5/10

Register Memory

Gives the agent autonomous access to persistent memory tools (_memory_search, _memory_store, _memory_compress)

2 in1 outSecurity 7/10

Register Remote MCP Tools

Adds a connected app's MCP event as agent tools. Uses a short-lived app-to-app token (valid ~15 minutes) that is refreshed on every run.

6 in1 outSecurity 6/10

Register Thinking Tool

Enables Rig's built-in Thinking tool for reasoning capabilities

1 in1 outSecurity 5/10

Set Agent System Prompt

Sets the system prompt for an Agent to guide its behavior

Embed Document

Creates an embedding vector for a document string using a cached embedding model

Embed Image

3 in2 outSecurity unrated

Embeds an image using a loaded model

Embed Query

3 in2 outSecurity unrated

Embeds a query string using a loaded model

Load Embedding Model

Loads a model from a Bit

AI Extractor

Uses an LLM plus a JSON schema to extract structured data from free-form text

5 in3 outSecurity 4/10

AI Extractor from History

Extracts structured data by replaying an entire chat history through an LLM

5 in3 outSecurity 4/10

Add Model Headers

Adds custom HTTP headers to a model for use with custom API endpoints

3 in2 outSecurity 5/10

Find Model

Finds the best model based on certain selection criteria

2 in2 outSecurity 9/10

Invoke Model

Invokes the configured model with the provided chat history. Set history streaming off to preserve and replay structured media responses.

3 in5 outSecurity 5/10

Invoke Simple

Invokes an LLM with a system prompt and user prompt, returning text and the full structured response.

5 in7 outSecurity 5/10

Invoke with Tools

Invokes an LLM that can call Flow tools/functions and routes each call to execution pins.

5 in4 outSecurity 5/10

LLM Branch

Routes execution based on an LLM-evaluated yes/no decision

3 in2 outSecurity 5/10

Summarize

Summarizes long text using an LLM with configurable strategies. Supports Map-Reduce (parallel, fast), Refine (sequential, coherent), Hierarchical (structure-aware), Hybrid (parallel + coherent), and Sliding Window (memory-efficient). Optional Chain of Density post-processing for optimal information density.

13 in4 outSecurity 5/10

Local Speech to Text

Transcribes audio locally with an installed any-speech-to-text model bit. Decodes WAV, MP3, FLAC, OGG (Vorbis/Opus), WebM/Opus, M4A/MP4 (AAC) and PCM, including browser MediaRecorder output (Chrome WebM/Opus, Safari MP4/AAC).

6 in5 outSecurity 5/10

Local Text to Speech

Generates WAV speech locally with an installed any-tts model bit.

11 in3 outSecurity 5/10

Speech to Text

Transcribes or translates audio with an existing provider Bit.

4 in5 outSecurity 5/10

Text to Speech

Generates speech audio with an existing provider Bit and writes it to FlowPath.

5 in3 outSecurity 5/10

Google STT Options

Creates typed speech-to-text options for Gemini and Vertex audio transcription.

Google TTS Options

Creates typed text-to-speech options for Gemini and Vertex speech models.

Hugging Face TTS Options

Creates typed text-to-speech options for Hugging Face speech models.

3 in1 outSecurity 10/10

Mistral TTS Options

Creates typed text-to-speech options for Mistral speech models.

OpenAI-Compatible STT Options

Creates typed speech-to-text options for OpenAI-compatible providers.

OpenAI-Compatible TTS Options

Creates typed text-to-speech options for OpenAI-compatible providers.

xAI STT Options

Creates typed speech-to-text options for xAI transcription models.

xAI TTS Options

Creates typed text-to-speech options for xAI speech models.

Clear History

Clears all messages from a ChatHistory

From Messages

Creates a Chat History from Messages

Get System Prompt

Extracts the first system-level message from a chat history for downstream use

1 in2 outSecurity 10/10

History From String

Creates a ChatHistory Struct from String (as User Message)

Make History

Creates a ChatHistory struct

Pop Message from History

Removes and returns the last message in a chat history

2 in4 outSecurity 10/10

Push Message

Appends a chat message to the end of a history

Set History Frequency Penalty

Stores the frequency penalty parameter used by LLM sampling

Set History N

Stores how many completions to request in downstream LLM calls

Set History Presence Penalty

Stores the presence penalty parameter used for discouraging repetition

Set History Temperature

Stores the sampling temperature used for later LLM invocations

Set History Thinking

Stores the thinking level that downstream model invocations should use

Set History Top P

Stores the nucleus sampling (top-p) parameter alongside the chat history

Set History User

Updates the user identifier stored alongside the chat history

Set Max Tokens

Stores the maximum completion tokens allowed for future calls

Set Response Format

Configures the structured response format expected from later LLM calls

Set Seed

Stores an optional randomness seed alongside the chat history

Set Stop Words

Stores one or more stop sequences to truncate future completions

Set Stream

Stores whether downstream LLM invocations should stream tokens

Set System Message

Creates or replaces the system prompt within a chat history before invoking an LLM

AI/Generative/History/Message

Extract Content

Extracts text content from a chat message, flattening multi-part payloads

1 in6 outSecurity 10/10

Make Message

AI/Generative/History/Message

Creates a chat message with text, image, audio, video, or document content and optional tool metadata

10 in1 outSecurity 10/10

Push Content

AI/Generative/History/Message

Appends text, image, audio, video, or document parts onto a chat message

10 in2 outSecurity 10/10

Generate Image

AI/Generative/Image

Generates one image with an existing provider Bit and writes it to FlowPath.

5 in4 outSecurity 5/10

AWS Bedrock Image Options

Creates typed image options for AWS Bedrock image models.

6 in1 outSecurity 10/10

Google Imagen Options

Creates typed image options for Google AI Studio and Vertex Imagen models.

Hugging Face Image Options

Creates typed image options for Hugging Face text-to-image models.

OpenAI Image Options

Creates typed image options for OpenAI and Azure OpenAI image generation.

OpenRouter Image Options

Creates typed image options for OpenRouter image-output models.

Together Image Options

Creates typed image options for Together text-to-image models.

xAI Image Options

Creates typed image options for xAI image generation.

AI/Generative/Preferences

Make Preferences

Creates a BitModelPreference struct used to guide model selection

AI/Generative/Preferences

Set Model Hint

Adds a soft preference hint for downstream model selection

AI/Generative/Preferences

Set Preference Weight

Adjusts the relative weight for a specific capability preference

4 in2 outSecurity 10/10

AWS Bedrock Model

Prepares a Bit for AWS Bedrock model endpoints

Anthropic Model

Prepares a Bit for Anthropic's Claude API using the provided credentials

Atlas Cloud Model

Builds a model served by Atlas Cloud, a full-modal AI inference platform exposing a single OpenAI-compatible API (DeepSeek, Qwen, GLM, Kimi, MiniMax and more)

Cohere Model

Prepares a Bit for Cohere's API using the supplied credentials

Deepseek Model

Prepares a Bit for Deepseek's API using the provided credentials

Galadriel Model

Prepares a Bit for Galadriel's verified endpoint using the provided credentials

Gemini Model

Prepares a Bit for Google Gemini endpoints using the provided credentials

Groq Model

Prepares a Bit for Groq's API using the supplied endpoint and key

Huggingface Model

Builds the Huggingface model based on certain selection criteria

4 in2 outSecurity 6/10

Hyperbolic Model

Builds the Hyperbolic model based on certain selection criteria

LM Studio Model

Connects to a locally running LM Studio server via its OpenAI-compatible API

3 in2 outSecurity 9/10

MiniMax Model

Prepares a Bit for the MiniMax API using the provided credentials

Mira Model

Builds the Mira model based on certain selection criteria

Mistral Model

Builds the Mistral model based on certain selection criteria

4 in2 outSecurity 6/10

Moonshot AI Model

Builds the Moonshot AI model based on certain selection criteria

4 in2 outSecurity 4/10

Mozilla any-llm Model

Builds a model via the Mozilla any-llm gateway (OpenAI-compatible). Supports both self-hosted gateways and the managed platform at any-llm.ai

Ollama Model

Builds the Ollama model based on certain selection criteria

3 in2 outSecurity 8/10

OpenAI Model

Prepares a Bit for OpenAI or Azure OpenAI endpoints with the provided credentials

OpenRouter Model

Builds the OpenRouter model based on certain selection criteria

Perplexity Model

Builds the Perplexity model based on certain selection criteria

Together AI Model

Builds the Together AI model based on certain selection criteria

Vertex AI Model

Prepares a Bit for Google Vertex AI Gemini endpoints using ADC or service account credentials

6 in2 outSecurity 5/10

VoyageAI Model

Builds the VoyageAI model based on certain selection criteria

4 in2 outSecurity 6/10

xAI Model

Builds the xAI model based on certain selection criteria

Chunk From String

Wraps an arbitrary string in a synthetic streaming chunk

Last Content

Extracts the content string from the last assistant message in a response

1 in8 outSecurity 10/10

Last Message

Extracts the last assistant message from a response

1 in2 outSecurity 10/10

Make Response

Creates an empty Response struct for manual composition

0 in1 outSecurity 10/10

Push Chunk

Appends a streaming chunk onto a response

Response From String

Wraps a plain string into a synthetic LLM response object for downstream tooling.

AI/Generative/Response/Chunk

Get Token

Extracts the latest streamed token from a response chunk

AI/Generative/Response/Message

Get Content

Extracts the text content field from a response message

1 in8 outSecurity 10/10

Get Role

AI/Generative/Response/Message

Extracts the author role string from a response message

Generate Video

AI/Generative/Video

Generates video with an existing provider Bit and writes it to FlowPath.

8 in4 outSecurity 5/10

OpenAI Sora Options

Creates typed video options for OpenAI Sora models.

Replicate Video Options

Creates typed video options for Replicate video models.

Runway Options

Creates typed video options for Runway models.

6 in1 outSecurity 10/10

Vertex Veo Options

Creates typed video options for Google Vertex Veo models.

fal Video Options

Creates typed video options for fal.ai video models.

AI/Generative/Video/Provider

Replicate Video Model

Builds a Replicate video generation provider Bit.

AI/Generative/Video/Provider

Runway Video Model

Builds a Runway video generation provider Bit.

AI/Generative/Video/Provider

fal Video Model

Builds a fal.ai queued video generation provider Bit.

Abort

AI/GitHub/Copilot/Chat

Aborts the current message processing

Send Message

AI/GitHub/Copilot/Chat

Sends a message to Copilot and waits for complete response. Supports history input for context.

4 in4 outSecurity 7/10

Stream Message

AI/GitHub/Copilot/Chat

Sends a message to Copilot and streams the response. Supports history input and matches Model Invoke interface.

4 in6 outSecurity 7/10

Local Client Config

Builds a local Copilot client configuration (stdio-based). Requires 'copilot' CLI to be installed and in PATH, or specify the CLI path explicitly.

2 in1 outSecurity 8/10

Server Client Config

Builds a server/remote Copilot client configuration (TCP-based)

2 in1 outSecurity 6/10

Start Local Client

Starts a local Copilot client using stdio. Requires 'copilot' CLI installed.

2 in4 outSecurity 8/10

Start Server Client

Starts a server/remote Copilot client using TCP

2 in4 outSecurity 6/10

Stop Client

Gracefully stops a running Copilot client (local or server)

Custom Agent Config

Configures a custom agent

4 in1 outSecurity 8/10

Infinite Session Config

Configures infinite session with automatic context compaction

3 in1 outSecurity 10/10

Provider Config (BYOK)

Configures a custom provider (Bring Your Own Key)

3 in1 outSecurity 5/10

System Message Config

AI/GitHub/Copilot/Session

Configures the system message for the session

2 in1 outSecurity 9/10

MCP HTTP Server

AI/GitHub/Copilot/MCP

Configures an HTTP/SSE MCP server for remote tool integration

3 in1 outSecurity 6/10

MCP Local Server

AI/GitHub/Copilot/MCP

Configures a local/stdio MCP server for tool integration

4 in1 outSecurity 7/10

Create Session

Creates a new Copilot chat session

3 in2 outSecurity 8/10

Destroy Session

AI/GitHub/Copilot/Session

Destroys a Copilot session

AI/GitHub/Copilot/Session

Session Builder

Builds a complete Copilot session configuration with all options

11 in1 outSecurity 10/10

Tool Config

AI/GitHub/Copilot/Tools

Configures an agent tool with parameters

3 in1 outSecurity 8/10

Tool List Builder

AI/GitHub/Copilot/Tools

Combines multiple tools into a list for session configuration

Client Status

Checks if a Copilot client is connected and ready

1 in2 outSecurity 10/10

Get Auth Status

Gets the authentication status of the Copilot client

1 in2 outSecurity 8/10

Get Models

Lists available Copilot models

1 in1 outSecurity 8/10

Get Version

Gets the version of the Copilot CLI

Load Model

Load Trained ML Model from Path

2 in2 outSecurity 7/10

Load Model (Binary)

Load Trained ML Model from Path using fast binary format (Fory)

2 in2 outSecurity 7/10

Predict

Predict with Machine Learning Model

4 in1 outSecurity 6/10

Prediction Class/Label

1 in2 outSecurity unrated

Extract class_idx and label from predictions.

Save Model

Save Trained ML Model to Path

3 in1 outSecurity 7/10

Save Model (Binary)

Save Trained ML Model to Path using fast binary format (Fory)

3 in1 outSecurity 7/10

Teachable Machine

6 in2 outSecurity unrated

Image classification using Teachable Machine models.

Fit Novelty Detection (One-Class SVM)

Fit a One-Class SVM on normal observations only. Predictions flag whether a new row is an inlier (1) or an outlier (0).

6 in3 outSecurity 6/10

Train Classifier (AdaBoost)

Fit/Train an AdaBoost classifier using multi-class SAMME boosting over shallow Decision Trees. Each learner focuses on the rows its predecessors got wrong, so boosting usually beats a single tree on weak signal, but it is far more sensitive to label noise and outliers than Random Forest. Estimators is a maximum, not a guarantee: boosting stops early once a learner is no better than random guessing.

6 in3 outSecurity 6/10

Train Classifier (Decision Tree)

Fit/Train a Decision Tree classifier. Native multi-class support with interpretable rules.

7 in2 outSecurity 6/10

Train Classifier (K-Nearest Neighbours)

Fit a K-Nearest-Neighbours classifier. Non-parametric and instance based: the fitted model embeds a verbatim copy of the whole training set instead of learned coefficients, so every training row (and any personal data in it) travels with the model, is written into every saved model file and can be reconstructed by anyone holding it. Treat the model with the same care as the source table.

4 in2 outSecurity 3/10

Train Classifier (Logistic Regression)

Fit/Train a Logistic Regression classifier with L2 regularization. Handles binary and multi-class targets and yields interpretable coefficients plus calibrated probabilities. The solver expects features on a comparable scale - fit a Feature Scaler first if your columns have very different ranges.

8 in2 outSecurity 6/10

Train Classifier (Multinomial Naive Bayes)

Fit/Train a Multinomial Naive Bayes classifier, the standard baseline for text and other count data. Features must be non-negative counts or TF-IDF weights, which is what the Fit TF-IDF Vectorizer node produces. Native multi-class support and a single pass over the data.

Train Classifier (Naive Bayes)

Fit/Train a Gaussian Naive Bayes classifier. Native multi-class support - no need for One-vs-All.

2 in2 outSecurity 6/10

Train Classifier (Random Forest)

Fit/Train a Random Forest classifier: many Decision Trees, each grown on a bootstrapped sample of the rows and a random subset of the features, combined by majority vote. Far more robust to overfitting than a single tree, at the price of interpretability. Model size and fit time grow linearly with Ensemble Size, so a forest of 500 trees costs roughly 500x a single tree.

8 in2 outSecurity 6/10

Train Classifier (SVM)

Fit/Train Support Vector Machines (SVM) for Multi-Class Classification

5 in2 outSecurity 6/10

Fit Clustering (Gaussian Mixture)

AI/ML/Clustering

Fit/Train a Gaussian Mixture Model. Soft clustering with per-component covariances and mixture weights, fitted by Expectation-Maximization.

10 in3 outSecurity 6/10

Train Clustering (DBSCAN)

AI/ML/Clustering

Fit/Train DBSCAN Density-Based Clustering

4 in3 outSecurity 6/10

Train Clustering (KMeans)

AI/ML/Clustering

Fit/Train KMeans Clustering

K-Fold Split

Generate K train/test splits for cross-validation. Each fold uses (K-1)/K data for training and 1/K for validation, and runs the connected fold branch once per fold.

6 in4 outSecurity 6/10

Sample Dataset

Random sample N records or a ratio from a dataset

5 in2 outSecurity 6/10

Shuffle Dataset

Shuffle dataset rows randomly

3 in1 outSecurity 6/10

Split Dataset

Split a dataset into training and testing subsets

5 in1 outSecurity 6/10

Stratified Split

Split a dataset into training and testing subsets, keeping every class at its original proportion in both subsets

7 in1 outSecurity 6/10

Accuracy

Calculate classification accuracy by comparing predictions to actual values

4 in2 outSecurity 8/10

Confusion Matrix

Build confusion matrix and calculate precision, recall, and F1 score

4 in2 outSecurity 8/10

ROC-AUC & Log Loss

Threshold-free evaluation of a binary classifier: area under the ROC curve, log loss and the curve points. This is the payoff for Logistic Regression producing calibrated probabilities instead of bare class labels.

5 in4 outSecurity 8/10

Regression Metrics

Calculate MSE, RMSE, MAE, and R² for regression predictions

4 in2 outSecurity 8/10

Silhouette Score

Evaluate clustering quality: how much closer each sample sits to its own cluster than to the nearest other one (-1 to +1)

5 in4 outSecurity 8/10

Feature Importance

Extract per-feature importance from a Decision Tree, Random Forest or AdaBoost model

3 in4 outSecurity 10/10

Get Centroids

Extract cluster centroids from a trained KMeans model

Get Coefficients

Extract coefficients and intercept from a trained Linear Regression model

Model Info

2 in3 outSecurity unrated

Get general information about any ML model

Extract Keypoint

2 in5 outSecurity unrated

Extract a specific keypoint from a pose by index or name

Feature Extraction

4 in3 outSecurity unrated

Extract feature vectors from images using ONNX models

Feature Similarity

Compare two feature vectors using cosine similarity or L2 distance

Image Classification

7 in2 outSecurity unrated

Image Classification with ONNX-Models. Download models from: MobileNetV2 (https://github.com/onnx/models/tree/main/validated/vision/classification/mobilenet), SqueezeNet (https://github.com/onnx/models/tree/main/validated/vision/classification/squeezenet), ResNet (https://github.com/onnx/models/tree/main/validated/vision/classification/resnet), EfficientNet (https://github.com/onnx/models/tree/main/validated/vision/classification/efficientnet-lite4)

Load ONNX

2 in4 outSecurity unrated

Load ONNX Model from Path

Model Info

2 in4 outSecurity unrated

Get ONNX model metadata (inputs, outputs, shapes)

Object Detection

6 in2 outSecurity unrated

Object Detection in Images with ONNX-Models. Download models from: TinyYOLOv2 (https://github.com/onnx/models/tree/main/validated/vision/object_detection_segmentation/tiny-yolov2), YOLO (https://github.com/onnx/models/tree/main/validated/vision/object_detection_segmentation), SSD-MobileNet (https://github.com/onnx/models/tree/main/validated/vision/object_detection_segmentation/ssd-mobilenetv1)

Pose Estimation

5 in2 outSecurity unrated

Detect human poses and keypoints using ONNX models. Download models from: YOLOv8-Pose (https://docs.ultralytics.com/models/yolov8/), MoveNet (https://tfhub.dev/google/movenet/), HRNet (https://github.com/OAID/TengineKit)

Semantic Segmentation

Segment images into semantic classes using ONNX models. Download models from: DeepLabV3 (https://github.com/onnx/models/tree/main/validated/vision/object_detection_segmentation/duc), FCN (https://github.com/onnx/models/tree/main/validated/vision/object_detection_segmentation/fcn)

Session Info

1 in4 outSecurity unrated

Get information about a loaded ONNX session

Unload ONNX

Release ONNX model from cache to free memory

Audio to Mel Spectrogram

Convert audio to mel spectrogram for speech models

Load Audio

2 in4 outSecurity unrated

Load audio file for processing

Resample Audio

Resample audio to target sample rate

Trim Audio

Trim audio to speech segments from VAD

Voice Activity Detection

6 in3 outSecurity unrated

Detect speech segments in audio. Download Silero VAD model from: https://github.com/snakers4/silero-vad/raw/master/src/silero_vad/data/silero_vad.onnx

Batch Image Inference

AI/ML/ONNX/Batch

Run ONNX inference on multiple images in batches

6 in3 outSecurity unrated

Analyze Faces

4 in3 outSecurity unrated

Detect faces and extract embeddings, gender and age using a face_id analyzer

Compare Faces

4 in4 outSecurity unrated

Compare two face embeddings for similarity

Crop Faces

Crop detected faces from image

Face Detection

6 in3 outSecurity unrated

Detect faces in images. Download models from: UltraFace (https://github.com/onnx/models/tree/main/validated/vision/body_analysis/ultraface), RetinaFace (https://huggingface.co/arnabdhar/retinaface-onnx), SCRFD (https://huggingface.co/onnx-community/scrfd_10g_bnkps)

Face Embedding

Extract face embedding for recognition. Download models from: ArcFace (https://huggingface.co/onnx-community/arcface_torch/tree/main), FaceNet (https://huggingface.co/rocca/facenet-onnx)

Load Face Analyzer

11 in2 outSecurity unrated

Load a face_id analyzer (SCRFD detector + ArcFace embedder + gender/age). Weights are verified and cached when a session identity is first built; equivalent analyzers reuse process-wide sessions.

Unload Face Analyzer

Release a cached face analyzer and its three ONNX sessions. Equivalent analyzer handles share the same cache entry and are invalidated together.

8 in4 outSecurity unrated

Named Entity Recognition

AI/ML/ONNX/NLP

Extract named entities (persons, organizations, locations, dates, etc.) from text using ONNX models. Supports BERT, RoBERTa, and other transformer-based NER models with automatic tokenization. Download models from: BERT-base-NER (https://huggingface.co/dslim/bert-base-NER), Multilingual NER (https://huggingface.co/Davlan/bert-base-multilingual-cased-ner-hrl), spaCy NER (https://huggingface.co/spacy). Text longer than the model's window is split into overlapping chunks rather than truncated, so entities are found throughout a long document. Download tokenizer.json and config.json from the same model repository — config.json carries the id2label mapping that names the entity types and the sequence length the model accepts.

Zero-Shot NER (GLiNER)

AI/ML/ONNX/NLP

Extract entities for any labels you name at runtime, with no fixed label set and no retraining. Load a GLiNER ONNX export (e.g. https://huggingface.co/onnx-community/gliner_small-v2.1, gliner_multi-v2.1, gliner_medium_news-v2.1, gliner_multi_pii-v1, NuNER_Zero) plus the tokenizer.json from the same repository. For models with a fixed label set, use the Named Entity Recognition node instead.

9 in4 outSecurity unrated

Crop Text Regions

AI/ML/ONNX/OCR

Crop detected text regions from image for recognition

Text Detection

AI/ML/ONNX/OCR

Detect text regions in images. Download models from: CRAFT (https://huggingface.co/quocanh34/craft_text_detection_onnx), DBNet (https://huggingface.co/Xenova/dbnet_resnet50_onnx), EAST (https://www.dropbox.com/s/r2ingd0l3zt8hxs/frozen_east_text_detection.tar.gz)

Text Recognition

AI/ML/ONNX/OCR

Recognize text from cropped text regions. Download models from: CRNN (https://huggingface.co/Xenova/crnn_onnx), TrOCR (https://huggingface.co/microsoft/trocr-base-printed), PaddleOCR (https://huggingface.co/aapot/paddleocr-onnx)

Colorize Depth

AI/ML/ONNX/Vision

Convert depth map to rainbow-colored visualization

Depth Estimation

AI/ML/ONNX/Vision

Estimate depth from a single image using ONNX models. Download models from: MiDaS (https://github.com/isl-org/MiDaS/releases), DPT (https://huggingface.co/Intel/dpt-large/tree/main), Depth Anything (https://huggingface.co/depth-anything/Depth-Anything-V2-Small/tree/main)

4 in3 outSecurity unrated

Depth to Point Cloud

AI/ML/ONNX/Vision

Convert depth map to 3D point cloud coordinates

Ordinal Metrics

Evaluate predictions for an ordered target with distance-aware metrics. Plain accuracy is inadequate here: it treats "predicted high when the truth was medium" exactly as harshly as "predicted low", so a model that is reliably one level off scores like one that guesses. Quadratic weighted kappa is the standard headline metric because it weights every miss by how far off it was and corrects for chance agreement, but it answers only one of three questions: the linear kappa and the macro-averaged error say how far off the model is under a different cost structure and on the rare levels, while Kendall's tau-b and the Spearman correlation say whether it orders the rows correctly at all.

5 in12 outSecurity 8/10

Train Ordinal Model (Adjacent Category)

Fit/Train an ordinal model that compares each level with the one directly below it: `log( P(level k+1) / P(level k) ) = contrast_k + x . beta`. Its coefficients answer `what does one more unit of this feature do to my rating?` - `exp(coefficient)` is the factor on the odds of scoring one level higher rather than staying put, the same factor at every step. That is NOT what Train Ordinal Model (Proportional Odds) reports: a cumulative coefficient is the log odds ratio of everything AT OR BELOW a cut point against everything above it, pooling levels instead of comparing two neighbours. The same fitted number therefore means different things in the two families, and since one shared coefficient applies once per step here, the bottom-to-top effect is (levels - 1) times the per-step effect. Pick this for ratings, severity grades and Likert answers, where the question really is about one step; pick proportional odds when the question is about crossing a threshold (`does this case escalate past level 2?`). Fitted by penalized maximum likelihood over all levels jointly, so per-level probabilities are calibrated and the Predict node returns a confidence. Scale your features first with the Fit Feature Scaler node: this is a gradient fit, and unscaled columns make it converge slowly or not at all.

7 in5 outSecurity 6/10

Train Ordinal Model (Continuation Ratio)

Fit/Train a continuation-ratio model on an ORDERED target that is really a process that can halt. It fits K-1 sub-models, where sub-model k answers `given this row reached level k, did it STOP there?`, so the model describes a progression through the levels instead of placing cut points on a latent scale. Reach for it when the levels are genuinely sequential and each one had to be passed to get to the next: escalation tiers, disease stages, how far a signup funnel got, how far an incident escalated before it was contained. Each sub-model carries its own coefficient vector, so nothing assumes proportional odds, and the per-level probabilities are exact by the chain rule rather than differences of two fits. The cost is strictness: because each sub-model is conditioned on having reached its level, EVERY level must occur in the training data, middle ones included. Scale your features first with the Fit Feature Scaler node: these are gradient fits, and unscaled columns make them converge slowly or not at all.

8 in5 outSecurity 6/10

Train Ordinal Model (Frank & Hall)

Fit/Train an ordinal model by decomposition: the ordered target is cut K-1 times (`is the level above this cut?`) and each cut is handed to an ordinary binary classifier, with the predicted level read back as the number of cuts answered yes. This is the one ordinal trainer here that is not linear in the features, so reach for it when the boundary between levels bends in a way the Proportional Odds and Ridge trainers cannot follow. The price is that the K-1 sub-models are fitted independently: there is no single latent scale, no coefficient vector to read a direction off, and no calibrated per-level probabilities - use Proportional Odds when you need those. Every declared level must occur in the training data at the bottom and at the top of the ordering, otherwise a cut has only one class and cannot be fitted. A Random Forest base is the sturdiest choice and by far the costliest: each cut grows its own full forest, so training costs K-1 forests and the saved model carries every tree of every one of them.

4 in3 outSecurity 6/10

Train Ordinal Model (Neural CORAL/CORN)

Fit/Train a NEURAL ordinal model on a target whose levels are ORDERED (1 < 2 < ... < 5, or low < medium < high). This is the only trainer in the catalog that is BOTH non-linear in the features AND yields calibrated, rank-consistent per-level probabilities: Frank & Hall is non-linear but votes with K-1 independent classifiers and therefore carries no probability model, while every other ordinal node here is linear in the features. A small network feeds one of two rank-consistent heads, CORAL or CORN, and both are built so that P(y > k) can never rise with k for ANY parameter values — so the level probabilities are non-negative and sum to 1 with nothing patched up afterwards. THE HONEST LIMIT: leave Hidden Layers EMPTY and CORAL becomes exactly Train Ordinal Model (Proportional Odds) with Loss = AllThreshold and Margin = Logistic, and CORN becomes exactly Train Ordinal Model (Continuation Ratio) — the same objective in the same parameters. The hidden layers are the entire contribution, so if your problem is linear in the features prefer those nodes: convex objective, no seed dependence, readable coefficients, better tested. Reach for this one when the level is genuinely not monotone in the features (a boundary that bends back on itself, which no linear ordinal model can represent at all). Two costs come with the network: it has far more parameters than a linear model and so needs far more rows — check the Architecture output — and the objective is not convex, so the Seed changes the fit. Scale your features first with the Fit Feature Scaler node; unscaled columns make this converge slowly or not at all.

11 in5 outSecurity 6/10

Train Ordinal Model (Proportional Odds)

Fit/Train a proportional-odds model on a target whose levels are ORDERED (1 < 2 < ... < 5, or low < medium < high). Use this instead of a classifier, which treats the levels as unrelated names and so counts predicting `low` for `high` as no worse than predicting `medium`. Use it instead of a regressor, which treats the levels as real numbers and so invents distances the levels do not carry (`high` is not exactly twice `medium`). The model learns one coefficient vector plus ordered cut points, which keeps predictions monotone in the score and, under the default loss, yields calibrated per-level probabilities. Link Function, Loss and Margin widen it to the whole threshold-model family, up to support vector ordinal regression, while Free Features relaxes the shared coefficient into one slope per cut point. Scale your features first with the Fit Feature Scaler node: this is a gradient fit, and unscaled columns make it converge slowly or not at all.

11 in6 outSecurity 6/10

Train Ordinal Model (Ridge)

Fit/Train an ordinal model the cheap way: ridge-regress the level rank on the features, then cut the score at thresholds learned from the training distribution instead of rounding it. Closed-form, so it stays fast exactly where the proportional-odds model gets expensive - many levels, many features, or when you just want a quick ordinal baseline to beat. It also degrades gracefully when the proportional-odds assumption does not hold. Unlike the proportional-odds model it yields no probabilities: you get the predicted level and the latent score behind it, nothing calibrated.

4 in4 outSecurity 6/10

Apply Transform

AI/ML/Preprocessing

Apply a fitted transformer (Feature Scaler, TF-IDF) to a table, writing one vector per row. A Feature Scaler replays the exact offsets and scales learned at fit time, so applying it to train and test gives both the same statistics. TF-IDF is different: linfa recomputes the inverse document frequencies from the table being transformed, so vectors are only comparable within a single Apply Transform run.

4 in1 outSecurity 6/10

Fit Feature Scaler

AI/ML/Preprocessing

Learn per-feature offsets and scales from a training table. Distance- and gradient-based models (Logistic Regression, Elastic Net, SVM, KNN, Gaussian Mixture) only behave when their features share a scale.

5 in4 outSecurity 7/10

Fit TF-IDF Vectorizer

AI/ML/Preprocessing

Learn a vocabulary from a text column and turn documents into numeric vectors weighted by term frequency times inverse document frequency. Feed the fitted vectorizer to Apply Transform to vectorize a column, then train a classifier such as Multinomial Naive Bayes on the result. Tokenization always uses the built-in regex tokenizer, because a custom tokenizer function cannot be persisted and would make the saved model unloadable.

10 in3 outSecurity 6/10

PCA Reduction

AI/ML/Reduction

Principal Component Analysis for dimensionality reduction

t-SNE Reduction

AI/ML/Reduction

t-Distributed Stochastic Neighbor Embedding. Projects high-dimensional vectors into 2-3 dimensions for visualization and writes the embedding back into the source table. t-SNE is transductive, so it produces no reusable model.

6 in1 outSecurity 6/10

Train Regression (Linear)

Fit/Train Linear Regression Model

2 in2 outSecurity 6/10

Train Regressor (GLM / Tweedie)

Fit/Train a Generalized Linear Model. Pick the distribution that matches the target: Normal for unbounded values, Poisson for counts, Gamma for positive skewed amounts, Inverse Gaussian for heavy tails.

8 in2 outSecurity 6/10

Train Regressor (K-Nearest Neighbours)

Fit a K-Nearest-Neighbours regressor that averages the target of the nearest training rows. Non-parametric and instance based: the fitted model embeds a verbatim copy of the whole training set instead of learned coefficients, so every training row (and any personal data in it) travels with the model, is written into every saved model file and can be reconstructed by anyone holding it. Treat the model with the same care as the source table.

4 in2 outSecurity 3/10

Train Regressor (Ridge/Lasso/ElasticNet)

Fit/Train a penalized linear regression model. Ridge shrinks all coefficients, Lasso drives irrelevant ones to exactly zero (feature selection), Elastic Net mixes both.

8 in3 outSecurity 6/10

Train Regressor (SVM)

1 in1 outSecurity unrated

Fit/Train a Support Vector Regressor. Learns non-linear targets through a kernel, with epsilon-SVR or nu-SVR.

9 in3 outSecurity 6/10

Prediction Score

AI/ML/Teachable Machine

Extract score from predictions.

Auto Classifier

Automatically finds the best classification model. Cross-validates Naive Bayes, Decision Tree, Logistic Regression, Random Forest and SVM, then retrains the winner on the full dataset. The reported Best Model Type can be fed straight into Grid Search to tune it further.

7 in4 outSecurity 6/10

Auto Ordinal

Automatically finds the best model for a target whose levels are ORDERED (1 < 2 < ... < 5, or low < medium < high). Cross-validates the ordinal families - Proportional Odds and Ordered Probit, the all-threshold model and its support-vector form, Ordinal Ridge, Continuation Ratio and Adjacent Category, plus an optional rank-consistent neural family that is off by default because it costs far more than all the others combined - on identical folds, ranks them by an ordinal metric that knows how far a miss was, then retrains the winner on the full data. Use this rather than Auto Classifier, which resolves the target without its order and ranks by accuracy or macro-F1, scoring a five-level miss exactly like a one-level one. Every candidate here is a gradient or a least-squares fit on the raw columns, so scale your features with the Fit Feature Scaler node first: unscaled columns change which family wins, not just how fast it converges.

12 in5 outSecurity 6/10

Grid Search

Exhaustive search over parameter combinations with cross-validation. Returns the best parameters found. Model Type accepts the same names the Auto Classifier reports as its best model, so the two nodes chain directly.

4 in3 outSecurity 6/10

Ordinal Grid Search

Exhaustively searches the hyperparameters of ONE ordinal model family with cross-validation, for a target whose levels are ORDERED (1 < 2 < ... < 5, or low < medium < high). Every combination in the Parameter Grid is scored on the SAME folds and ranked by an ordinal metric that knows how far a miss was. Use this rather than Grid Search, which resolves the target without its order and tunes against accuracy, scoring a five-level miss exactly like a one-level one. Model Type accepts the names Auto Ordinal reports as its best model, so the usual chain is Auto Ordinal to pick the family, then this node to tune it. Every family here is a gradient or a least-squares fit on the raw columns, so scale your features with the Fit Feature Scaler node first: unscaled columns change which hyperparameters win, not just how fast they converge.

7 in6 outSecurity 6/10

Build Memory Context

Assembles retrieved memory records into a token-budgeted context string for injection into agent system prompts

4 in3 outSecurity 9/10

Compress Memory

Compresses old memory observations into a summary using an LLM, then replaces them in the store. Runs the embedding model to store the summary vector.

4 in4 outSecurity 7/10

Create Memory Config

Creates a MemoryConfig that bundles database, embedding model, and tuning parameters for all memory nodes

7 in1 outSecurity 8/10

Optimize Memory

Runs LanceDB maintenance on the memory table: flush buffered writes, compact fragments, prune old versions, and rebuild indices. Run periodically or after bulk writes.

3 in1 outSecurity 10/10

Search Memory

Searches the memory store using the configured recall strategy (recent, relevance, or hybrid)

4 in3 outSecurity 7/10

Store Memory

Embeds text and stores it as a memory observation in the configured LanceDB table

4 in2 outSecurity 7/10

KG Extract

AI/Memory/Graph

Extracts entities (nodes) and relationships (edges) from text using an LLM, returning structured arrays ready for graph insertion

5 in6 outSecurity 6/10

KG Retrieve

AI/Memory/Graph

Retrieves context from a knowledge graph: embeds the query, finds matching nodes, then expands N hops to build structured context

7 in6 outSecurity 7/10

KG Summarize

AI/Memory/Graph

Converts a subgraph (nodes + edges) into a natural-language summary for LLM consumption

5 in4 outSecurity 8/10

Character Chunk Text

AI/Preprocessing

Splits raw text locally using simple character-based chunking

5 in2 outSecurity 9/10

Chunk Text

AI/Preprocessing

Splits long text into sized/overlapping chunks using the cached embedding model's splitter

6 in2 outSecurity 9/10

AI Extract Document

Extracts text and content from documents using AI for enhanced image descriptions and OCR.

8 in2 outSecurity 5/10

AI Extract Documents

Extracts text and content from multiple documents using AI in parallel.

8 in2 outSecurity 5/10

AI Keywords

Extracts keywords from text using an LLM. The AI understands context and semantics, providing high-quality keyword extraction for complex or domain-specific content.

5 in2 outSecurity 4/10

Extract Content Sections

Intelligently segments document into thematic sections with summaries, tracking content across non-contiguous pages. Ideal for large document corpora.

Extract Document

Extracts text and content from documents (PDF, DOCX, XLSX, images, etc.) and converts to markdown.

Extract Documents

Extracts text and content from multiple documents in parallel.

PII Mask (AI)

Masks Personally Identifiable Information using an LLM. Can detect contextual PII like names, addresses, and sensitive information that regex patterns might miss.

6 in4 outSecurity 7/10

Pages to Markdown

Combines an array of document pages into a single markdown string.

RAKE Keywords

Extracts keywords from text using the RAKE (Rapid Automatic Keyword Extraction) algorithm. RAKE is a domain-independent algorithm that extracts significant phrases by analyzing word frequency and co-occurrence.

Summarize Document

Creates an intelligent summary of document pages using AI with configurable strategies and detail levels. Handles long documents via chunked summarization with multiple strategy options.

12 in2 outSecurity 5/10

YAKE Keywords

Extracts keywords from text using YAKE (Yet Another Keyword Extractor). YAKE is an unsupervised automatic keyword extraction method that uses statistical features from the text itself.