Skip to content

AI & ML Overview

Welcome to the AI & ML blocks page! Here you can find a list of all the Flojoy Blocks and examples to produce no-code apps with Python-based AI (Artificial Intelligence) and ML (Machine Learning) models.


SPEECH_2_TEXT Performs speech to text on the selected audio file.


ACCURACY Take two dataframes with the true and predicted labels from a classification task, and indicates whether the prediction was correct or not.
ONE_HOT_ENCODING Create a one-hot encoding from a dataframe containing categorical features.
SUPPORT_VECTOR_MACHINE Train a support vector machine (SVM) model for classification tasks.
TORCHSCRIPT_CLASSIFIER Execute a TorchScript classifier against an input image.
TRAIN_TEST_SPLIT Split an input dataframe into test and training dataframes according to a size parameter.


NLP_CONNECT_VIT_GPT2 The NLP_CONNECT_VIT_GPT2 node captions an input image and produces an output string wrapped in a dataframe.


HUGGING_FACE_PIPELINE The HUGGING_FACE_PIPELINE node uses a classification pipeline to process and classify an image.


ONNX_MODEL Load a serialized ONNX model and uses it to make predictions using ONNX Runtime.


COUNT_VECTORIZER Receive a collection of text documents (as a matrix, vector, or dataframe) and convert it into a matrix of token counts.


OBJECT_DETECTION Detect objects in an input image with YOLOv3, then return an image DataContainer with those objects highlighted.


PROPHET_PREDICT Run a Prophet time series prediction model on an incoming dataframe.


LEAST_SQUARES Perform a least squares regression on the input DataContainer (input can be a Matrix or OrderedPair).


DEEPLAB_V3 Return a segmentation mask from an input image.


BART_LARGE_CNN Take an input dataframe with multiple rows and a single column, then produce a dataframe with a single "summary_text" column.