Graphbook is an open source Python framework for building interactive, scalable AI apps faster. With a focus on transparency, efficiency, and interoperability, Graphbook is the ideal AI app builder.
Graphbook is open source with an MIT license making it free and transparent on GitHub. Get started now.
Supported batching and multiprocessing makes it built for AI and Machine Learning.
Software teams are now more-than-ever enabled to deliver high quality automation solutions to the business.
No frontend coding experience required
Build with no-code when you need to
Pause, play, and view ML model outputs in realtime.
Parameters can be configured in code and/or UI
Define your nodes and workflows in Python
Invoke your workflows as regular code
Easily deploy training and inference to your Ray clusters
Use your favorite framework: Pytorch, Tensorflow, or none at all
import grapbook as gb
g = gb.Graph()
@g()
def graph():
numbers = g.step(GenerateNumbers)
mean = g.step(CalcMean)
transformed = g.step(Transform)
running_mean = g.step(CalcRunningMean)
transformed.bind(numbers)
mean.bind(transformed)
running_mean.bind(transformed)
Write nodes in Python
@step("DinoV2")
@batch(8, "images")
@param("model", "transformers/automodel", default="facebook/dinov2-base")
@param("processor", "transformers/autoimageprocessor", default="facebook/dinov2-base")
def process_images(ctx, images, items, notes):
inputs = ctx.processor(images=images, return_tensors='pt')
outputs = ctx.model(**inputs)
last_hidden_states = outputs.last_hidden_state
return last_hidden_states
@step("DinoV2")
@batch(8, "images")
@param(
"model",
"transformers/automodel",
default="facebook/dinov2-base"
)
@param(
"processor",
"transformers/autoimageprocessor",
default="facebook/dinov2-base"
)
def process_images(ctx, images, items, notes):
inputs = ctx.processor(images=images)
outputs = ctx.model(**inputs)
last_hidden_states = outputs.last_hidden_state
return last_hidden_states
With your nodes, assemble a DAG app in the visual editor or in your favorite IDE along with your nodes
Run, monitor, and adjust configurable parameters in your workflow
At its core, Graphbook is a framework for building efficient DAG-structured AI/ML data pipelines, but there are many features that help you build.
No. But you can build no-code ML for your customers and internal teams with this framework.
Yes. Your nodes are written in Python, and pipelines/workflows can be serialized as either .py or .json files.
Yes.
In Graphbook, you can continue to use your workflow as-is or set new variables (directly in the workflow) such as where your production database is.
Yes, Graphbook is abstract enough where you can implement anything that can be written in Python including sending API requests to OpenAI.
The framework uses Ray to scale your application.
We are actively looking for collaborators. You are very welcome to contribute! Visit our repo.