Generative Node Catalog
Generative category
Generated from 106 catalog nodes in AI/Generative.
Nodes in this category
Showing 48 of 106 matching nodes.
AI Extractor
AI/GenerativeUses an LLM plus a JSON schema to extract structured data from free-form text
AI Extractor from History
AI/GenerativeExtracts structured data by replaying an entire chat history through an LLM
AI Extractor with Struct Schema
AI/GenerativeUses an LLM and a reference struct's schema to extract structured data from free-form text
Add Model Headers
AI/GenerativeAdds custom HTTP headers to a model for use with custom API endpoints
Find Model
AI/GenerativeFinds the best model based on certain selection criteria
Invoke Model
AI/GenerativeInvokes the configured model with the provided chat history. Set history streaming off to preserve and replay structured media responses.
Invoke Simple
AI/GenerativeInvokes an LLM with a system prompt and user prompt, returning text and the full structured response.
Invoke with Tools
AI/GenerativeInvokes an LLM that can call Flow tools/functions and routes each call to execution pins.
LLM Branch
AI/GenerativeRoutes execution based on an LLM-evaluated yes/no decision
Summarize
AI/GenerativeSummarizes 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.
Local Speech to Text
AI/Generative/AudioTranscribes 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).
Local Text to Speech
AI/Generative/AudioGenerates WAV speech locally with an installed any-tts model bit.
Speech to Text
AI/Generative/AudioTranscribes or translates audio with an existing provider Bit.
Text to Speech
AI/Generative/AudioGenerates speech audio with an existing provider Bit and writes it to FlowPath.
Google STT Options
AI/Generative/Audio/OptionsCreates typed speech-to-text options for Gemini and Vertex audio transcription.
Google TTS Options
AI/Generative/Audio/OptionsCreates typed text-to-speech options for Gemini and Vertex speech models.
Hugging Face TTS Options
AI/Generative/Audio/OptionsCreates typed text-to-speech options for Hugging Face speech models.
Mistral TTS Options
AI/Generative/Audio/OptionsCreates typed text-to-speech options for Mistral speech models.
OpenAI-Compatible STT Options
AI/Generative/Audio/OptionsCreates typed speech-to-text options for OpenAI-compatible providers.
OpenAI-Compatible TTS Options
AI/Generative/Audio/OptionsCreates typed text-to-speech options for OpenAI-compatible providers.
xAI STT Options
AI/Generative/Audio/OptionsCreates typed speech-to-text options for xAI transcription models.
xAI TTS Options
AI/Generative/Audio/OptionsCreates typed text-to-speech options for xAI speech models.
Clear History
AI/Generative/HistoryClears all messages from a ChatHistory
From Messages
AI/Generative/HistoryCreates a Chat History from Messages
Get System Prompt
AI/Generative/HistoryExtracts the first system-level message from a chat history for downstream use
History From String
AI/Generative/HistoryCreates a ChatHistory Struct from String (as User Message)
Make History
AI/Generative/HistoryCreates a ChatHistory struct
Pop Message from History
AI/Generative/HistoryRemoves and returns the last message in a chat history
Push Message
AI/Generative/HistoryAppends a chat message to the end of a history
Set History Frequency Penalty
AI/Generative/HistoryStores the frequency penalty parameter used by LLM sampling
Set History N
AI/Generative/HistoryStores how many completions to request in downstream LLM calls
Set History Presence Penalty
AI/Generative/HistoryStores the presence penalty parameter used for discouraging repetition
Set History Temperature
AI/Generative/HistoryStores the sampling temperature used for later LLM invocations
Set History Thinking
AI/Generative/HistoryStores the thinking level that downstream model invocations should use
Set History Top P
AI/Generative/HistoryStores the nucleus sampling (top-p) parameter alongside the chat history
Set History User
AI/Generative/HistoryUpdates the user identifier stored alongside the chat history
Set Max Tokens
AI/Generative/HistoryStores the maximum completion tokens allowed for future calls
Set Response Format
AI/Generative/HistoryConfigures the structured response format expected from later LLM calls
Set Seed
AI/Generative/HistoryStores an optional randomness seed alongside the chat history
Set Stop Words
AI/Generative/HistoryStores one or more stop sequences to truncate future completions
Set Stream
AI/Generative/HistoryStores whether downstream LLM invocations should stream tokens
Set System Message
AI/Generative/HistoryCreates or replaces the system prompt within a chat history before invoking an LLM
Extract Content
AI/Generative/History/MessageExtracts text content from a chat message, flattening multi-part payloads
Make Message
AI/Generative/History/MessageCreates a chat message with text, image, audio, video, or document content and optional tool metadata
Push Content
AI/Generative/History/MessageAppends text, image, audio, video, or document parts onto a chat message
Generate Image
AI/Generative/ImageGenerates one image with an existing provider Bit and writes it to FlowPath.
AWS Bedrock Image Options
AI/Generative/Image/OptionsCreates typed image options for AWS Bedrock image models.
Google Imagen Options
AI/Generative/Image/OptionsCreates typed image options for Google AI Studio and Vertex Imagen models.