AI Node Catalog

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

7 in2 outSecurity 2/10

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 4/10

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 3/10

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

3 in2 outSecurity 4/10

Embed Image

Embeds an image using a loaded model

3 in2 outSecurity 10/10

Embed Query

Embeds a query string using a loaded model

3 in2 outSecurity 10/10

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 6/10

AI Extractor from History

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

5 in3 outSecurity 6/10

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 1/10

Invoke Model

Invokes the configured model with the provided chat history and streams back chunks.

3 in5 outSecurity 5/10

Invoke Simple

Invokes an LLM with a single system prompt + user prompt and streams back tokens.

4 in5 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 Text to Speech

AI/Generative/Audio

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

11 in3 outSecurity 5/10

Speech to Text

AI/Generative/Audio

Transcribes or translates audio with an existing provider Bit.

4 in5 outSecurity 5/10

Text to Speech

AI/Generative/Audio

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 0/10

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

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 0/10

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

AI/Generative/History/Message

Make Message

Creates a chat message with text or image content and optional tool metadata

AI/Generative/History/Message

Push Content

Appends text or image parts onto a chat message

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 0/10

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 0/10

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

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

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 1/10

Mira Model

Builds the Mira model based on certain selection criteria

Mistral Model

Builds the Mistral model based on certain selection criteria

Moonshot AI Model

Builds the Moonshot AI model based on certain selection criteria

4 in2 outSecurity 6/10

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 2/10

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

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

Last Message

Extracts the last assistant message from a response

Make Response

Creates an empty Response struct for manual composition

0 in1 outSecurity 0/10

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

AI/Generative/Response/Message

Get Role

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 0/10

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 3/10

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 3/10

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 2/10

Server Client Config

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

2 in1 outSecurity 4/10

Start Local Client

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

2 in4 outSecurity 2/10

Start Server Client

Starts a server/remote Copilot client using TCP

2 in4 outSecurity 4/10

Stop Client

Gracefully stops a running Copilot client (local or server)

Custom Agent Config

Configures a custom agent

4 in1 outSecurity 2/10

Infinite Session Config

Configures infinite session with automatic context compaction

3 in1 outSecurity 0/10

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 1/10

MCP HTTP Server

AI/GitHub/Copilot/MCP

Configures an HTTP/SSE MCP server for remote tool integration

3 in1 outSecurity 4/10

MCP Local Server

AI/GitHub/Copilot/MCP

Configures a local/stdio MCP server for tool integration

4 in1 outSecurity 3/10

Create Session

Creates a new Copilot chat session

3 in2 outSecurity 2/10

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 0/10

Tool Config

AI/GitHub/Copilot/Tools

Configures an agent tool with parameters

3 in1 outSecurity 2/10

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

Get Auth Status

Gets the authentication status of the Copilot client

1 in2 outSecurity 2/10

Get Models

Lists available Copilot models

1 in1 outSecurity 2/10

Get Version

Gets the version of the Copilot CLI

Load Model

Load Trained ML Model from Path

2 in2 outSecurity 3/10

Load Model (Binary)

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

2 in2 outSecurity 3/10

Predict

Predict with Machine Learning Model

4 in1 outSecurity 4/10

Prediction Class/Label

Extract class_idx and label from predictions.

1 in2 outSecurity 10/10

Save Model

Save Trained ML Model to Path

3 in1 outSecurity 3/10

Save Model (Binary)

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

3 in1 outSecurity 3/10

Teachable Machine

Image classification using Teachable Machine models.

6 in2 outSecurity 10/10

Train Classifier (Decision Tree)

AI/ML/Classification

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

Train Classifier (Naive Bayes)

AI/ML/Classification

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

2 in2 outSecurity 4/10

Train Classifier (SVM)

AI/ML/Classification

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

2 in2 outSecurity 4/10

Train Clustering (DBSCAN)

AI/ML/Clustering

Fit/Train DBSCAN Density-Based Clustering

4 in3 outSecurity 4/10

Train Clustering (KMeans)

AI/ML/Clustering

Fit/Train KMeans Clustering

3 in2 outSecurity 4/10

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.

6 in4 outSecurity 4/10

Sample Dataset

Random sample N records or a ratio from a dataset

5 in2 outSecurity 4/10

Shuffle Dataset

Shuffle dataset rows randomly

3 in1 outSecurity 4/10

Split Dataset

Split a dataset into training and testing subsets

5 in1 outSecurity 4/10

Stratified Split

Split a dataset into training and testing subsets while maintaining class distribution

6 in1 outSecurity 4/10

Accuracy

AI/ML/Metrics

Calculate classification accuracy by comparing predictions to actual values

4 in2 outSecurity 2/10

Confusion Matrix

AI/ML/Metrics

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

4 in2 outSecurity 2/10

Regression Metrics

AI/ML/Metrics

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

4 in2 outSecurity 2/10

Get Centroids

AI/ML/Model Info

Extract cluster centroids from a trained KMeans model

Get Coefficients

AI/ML/Model Info

Extract coefficients and intercept from a trained Linear Regression model

Model Info

AI/ML/Model Info

Get general information about any ML model

2 in3 outSecurity 10/10

Extract Keypoint

Extract a specific keypoint from a pose by index or name

2 in5 outSecurity 10/10

Feature Extraction

Extract feature vectors from images using ONNX models

4 in3 outSecurity 10/10

Feature Similarity

Compare two feature vectors using cosine similarity or L2 distance

Image Classification

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)

7 in2 outSecurity 10/10

Load ONNX

Load ONNX Model from Path

2 in4 outSecurity 10/10

Model Info

Get ONNX model metadata (inputs, outputs, shapes)

2 in4 outSecurity 10/10

Object Detection

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)

6 in2 outSecurity 10/10

Pose Estimation

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)

5 in2 outSecurity 10/10

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

Get information about a loaded ONNX session

1 in4 outSecurity 10/10

Unload ONNX

Release ONNX model from cache to free memory

Audio to Mel Spectrogram

Convert audio to mel spectrogram for speech models

Load Audio

Load audio file for processing

2 in4 outSecurity 10/10

Resample Audio

Resample audio to target sample rate

Trim Audio

Trim audio to speech segments from VAD

Voice Activity Detection

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

6 in3 outSecurity 10/10

Batch Image Inference

AI/ML/ONNX/Batch

Run ONNX inference on multiple images in batches

6 in3 outSecurity 10/10

Compare Faces

Compare two face embeddings for similarity

4 in4 outSecurity 10/10

Crop Faces

Crop detected faces from image

Face Detection

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)

6 in3 outSecurity 10/10

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)

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). Download tokenizer.json from the same model repository.

8 in4 outSecurity 10/10

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)

Depth to Point Cloud

AI/ML/ONNX/Vision

Convert depth map to 3D point cloud coordinates

4 in3 outSecurity 10/10

PCA Reduction

AI/ML/Reduction

Principal Component Analysis for dimensionality reduction

3 in2 outSecurity 4/10

t-SNE Reduction

AI/ML/Reduction

t-Distributed Stochastic Neighbor Embedding for dimensionality reduction (placeholder - not yet implemented)

3 in1 outSecurity 4/10

Train Regression (Linear)

AI/ML/Regression

Fit/Train Linear Regression Model

2 in2 outSecurity 4/10

Prediction Score

AI/ML/Teachable Machine

Extract score from predictions.

1 in1 outSecurity 10/10

Auto Classifier

AI/ML/Tuning

Automatically finds the best classification model. Tries Naive Bayes, Decision Tree, and SVM with cross-validation.

5 in4 outSecurity 4/10

Grid Search

AI/ML/Tuning

Exhaustive search over parameter combinations with cross-validation. Returns the best parameters found.

4 in3 outSecurity 4/10

Build Memory Context

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

4 in3 outSecurity 1/10

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 3/10

Create Memory Config

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

7 in1 outSecurity 2/10

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 0/10

Search Memory

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

4 in3 outSecurity 3/10

Store Memory

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

4 in2 outSecurity 3/10

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 4/10

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 3/10

KG Summarize

AI/Memory/Graph

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

5 in4 outSecurity 2/10

Character Chunk Text

AI/Preprocessing

Splits raw text locally using simple character-based chunking

5 in2 outSecurity 1/10

Chunk Text

AI/Preprocessing

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

6 in2 outSecurity 1/10

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 6/10

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 3/10

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.