Skip to main content

Komponenten

Finden Sie wiederverwendbare Bausteine für die Gestaltung Ihrer eigenen KI-Systeme.

Generate Text (Ollama) icon

Generate Text (Ollama)

Ollama-backed chat completion. The worker takes a user-prompt {{type:String}} and a system-prompt {{type:String}}, replays the past {{param:history_messages}} turns, and chats with the Ollama-served model at {{param:model_name}} at {{param:temperature}}; o

Language & Symbolic
Detect Voice Activity (Silero VAD) icon

Detect Voice Activity (Silero VAD)

Frame-level voice activity detection using the Silero VAD model. Each {{type:AudioFrame}} is downmixed to mono, resampled to 16 kHz, and fed through Silero VAD; the worker emits {{type:[{start:Double,end:Double}]}} carrying per-speech-span start and end ti

Audio & Speech
Convert Value icon

Convert Value

Casts a primitive scalar stream from one numeric, character, or boolean type to another, tick-for-tick, following standard C++ conversion rules. Acts as a type bridge between mismatched primitive streams.

Estimate Density Map Peaks icon

Estimate Density Map Peaks

Density-map peak picker. Reads a {{type:DensityMap}} plus a {{type:UInt64}} target count, finds local maxima inside a {{param:window_size}}-by-{{param:window_size}} neighbourhood via morphological dilation + connected components, sorts peaks by density val

Multimodal/Fusion
Collect icon

Collect

Buffered accumulator with a boolean flush gate. Each tick pulls one {{type:Bool}} from the gate stream and one {{type:t}} from the value stream; while the gate is true the value is appended to an internal list; on the FIRST tick where the gate goes `fals

Multimodal/Fusion
Label COCO Body Landmarks icon

Label COCO Body Landmarks

Schema converter: takes a flat list of landmarks and emits a typed COCO Human17 record with named fields (nose, lEye, rEye, ear, shoulders, elbows, wrists, hips, knees, ankles).

Image - 2D Imaging
Unpack Tuple icon

Unpack Tuple

Splits a tuple-typed stream into one output stream per element, preserving positional order. Inverse of {{component:pack_tuple}}.

Estimate Crowd Count icon

Estimate Crowd Count

CLIP-text-conditioned crowd counter. Each {{type:Image}} is converted to RGB, normalised with the per-channel statistics matching the backbone of {{param:model}}, and fed through the density head; the worker emits three outputs per tick — a

Image - 2D Imaging

Bereit zum Entwickeln?

Schließen Sie sich den technischen Teams an, die Pipelogic nutzen, um KI-Systeme schneller auszuliefern.