Tutorial

Learn how to use the Clarifai Python SDK

Each of the following code snippets is a self-contained example of around 10 lines of Python code that can be easily copied and pasted into a Python source code file. By experimenting with these snippets, you'll quickly get started with the Clarifai API.

For detailed information about the API, please refer to the API Reference.

Predict with Models

For more information on any of the public models, visit here

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.model import Model

# Model Predict
model_prediction = Model("https://clarifai.com/anthropic/completion/models/claude-v2").predict_by_bytes(b"Write a tweet on future of AI", "text")

model = Model(user_id="user_id", app_id="app_id", model_id="model_id")
model_prediction = model.predict_by_url(url="url", input_type="image") # Supports image, text, audio, video

# Customizing Model Inference Output
model = Model(user_id="user_id", app_id="app_id", model_id="model_id",
                  output_config={"min_value": 0.98}) # Return predictions having prediction confidence > 0.98
model_prediction = model.predict_by_filepath(filepath="local_filepath", input_type="text") # Supports image, text, audio, video

model = Model(user_id="user_id", app_id="app_id", model_id="model_id",
                  output_config={"sample_ms": 2000}) # Return predictions for specified interval
model_prediction = model.predict_by_url(url="VIDEO_URL", input_type="video")

Predict with Workflow

For more information on any of the public workflows, visit here.

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.workflow import Workflow

# Workflow Predict
workflow = Workflow("workflow_url") # Example: https://clarifai.com/clarifai/main/workflows/Face-Sentiment
workflow_prediction = workflow.predict_by_url(url="url", input_type="image") # Supports image, text, audio, video

# Customizing Workflow Inference Output
workflow = Workflow(user_id="user_id", app_id="app_id", workflow_id="workflow_id",
                  output_config={"min_value": 0.98}) # Return predictions having prediction confidence > 0.98
workflow_prediction = workflow.predict_by_filepath(filepath="local_filepath", input_type="text") # Supports image, text, audio, video

Create App

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.user import User
client = User(user_id="user_id")

# Get all apps
apps = client.list_apps()

# Create app and dataset
app = client.create_app(app_id="demo_app", base_workflow="Universal")

Create Dataset

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.app import App

# Get an app
app = App(user_id="user_id", app_id="app_id")

 # Create a dataset
dataset = app.create_dataset(dataset_id="demo_dataset")

Upload Dataset

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.dataset import Dataset

# Get a dataset
dataset = Dataset(user_id="user_id", app_id="app_id", dataset_id="dataset_id")

# Upload dataset from loaders
dataset.upload_dataset(task='visual_segmentation', split="train", dataset_loader='coco_segmentation')

# Upload a dataset from local folder
dataset.upload_from_folder(folder_path='folder_path', input_type='text', labels=True)

# Upload a text dataset from csv file
dataset.upload_from_csv(csv_path='csv_path', labels=True)

Upload Inputs

from clarifai.client.user import User
app = User(user_id="user_id").app(app_id="app_id")
input_obj = app.inputs()

#input upload from url
input_obj.upload_from_url(input_id = 'demo', image_url='https://samples.clarifai.com/metro-north.jpg')

#input upload from filename
input_obj.upload_from_file(input_id = 'demo', video_file='demo.mp4')

# text upload
input_obj.upload_text(input_id = 'demo', raw_text = 'This is a test')

List Apps

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.user import User
client = User(user_id="user_id")

# Get all apps
apps = client.list_apps()

List Datasets

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.app import App

# Get an app
app = App(user_id="user_id", app_id="app_id")

# Get all datasets
datasets = app.list_datasets()

List Models

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.app import App

# Get an app
app = App(user_id="user_id", app_id="app_id")

# Get all models
models = app.list_models()

# List all models in community filtered by model_type, description
all_llm_community_models = App().list_models(filter_by={"query": "LLM",
                                                     "model_type_id": "text-to-text"}, only_in_app=False)

List Workflows

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.app import App

# Get an app
app = App(user_id="user_id", app_id="app_id")

# List all workflow in an app
workflows = app.list_workflows()

# List all workflow in community filtered by description
all_face_community_workflows = App().list_workflows(filter_by={"query": "face"}, only_in_app=False) # Get all face related workflows

Delete App

# Note: CLARIFAI_PAT must be set as env variable.
from clarifai.client.user import User
client = User(user_id="user_id")

# Delete an app
client.delete_app(app_id="app_id")

Tutorial

Predict with Models​

Predict with Workflow​

Create App​

Create Dataset​

Upload Dataset​

Upload Inputs​

List Apps​

List Datasets​

List Models​

List Workflows​

Delete App​