This is the official Python client for interacting with our powerful API. The Clarifai Python SDK offers a comprehensive set of tools to integrate Clarifai's AI platform to leverage computer vision capabilities like classification , detection ,segementation and natural language capabilities like classification , summarisation , generation , Q&A ,etc into your applications. With just a few lines of code, you can leverage cutting-edge artificial intelligence to unlock valuable insights from visual and textual content.
Website | Schedule Demo | Signup for a Free Account | API Docs | Clarifai Community | Python SDK Docs | Examples | Colab Notebooks | Discord
- Installation
- Getting Started
- Compute Orchestration
- Interacting with Datasets
- Interacting with Inputs
- Interacting with Models
- Interacting with Workflows
- Search
- Retrieval Augmented Generation (RAG)
- More Examples
Install from PyPi:
pip install -U clarifaiInstall from Source:
git clone https://github.com/Clarifai/clarifai-python.git
cd clarifai-python
python3 -m venv .venv
source .venv/bin/activate
pip install -e .For developers, use the precommit hook .pre-commit-config.yaml to automate linting.
pip install -r requirements-dev.txt
pre-commit installNow every time you run git commit your code will be automatically linted and won't commit if it fails.
You can also manually trigger linting using:
pre-commit run --all-filesClarifai uses Personal Access Tokens(PATs) to validate requests. You can create and manage PATs under your Clarifai account security settings.
🔗 Create PAT:Log into Portal → Profile Icon → Security Settings → Create Personal Access Token → Set the scopes → Confirm
🔗 Get User ID:Log into Portal → Profile Icon → Account → Profile → User-ID
Export your PAT as an environment variable. Then, import and initialize the API Client.
Set PAT as environment variable through terminal:
export CLARIFAI_PAT={your personal access token}# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.userimportUserclient=User(user_id="user_id")
# Get all appsapps_generator=client.list_apps()
apps=list(apps_generator)OR
PAT can be passed as constructor argument
fromclarifai.client.userimportUserclient=User(user_id="user_id", pat="your personal access token")Clarifai’s Compute Orchestration offers a streamlined solution for managing the infrastructure required for training, deploying, and scaling machine learning models and workflows.
This flexible system supports any compute instance — across various hardware providers and deployment methods — and provides automatic scaling to match workload demands. More Details
fromclarifai.client.userimportUserclient=User(user_id="user_id",base_url="https://api.clarifai.com")
# Create a new compute clustercompute_cluster=client.create_compute_cluster(compute_cluster_id="demo-id",config_filepath="computer_cluster_config.yaml")
# List Clustersall_compute_clusters=list(client.list_compute_clusters())
print(all_compute_clusters)fromclarifai.client.compute_clusterimportComputeCluster# Initialize the ComputeCluster instancecompute_cluster=ComputeCluster(user_id="user_id",compute_cluster_id="demo-id")
# Create a new nodepoolnodepool=compute_cluster.create_nodepool(nodepool_id="demo-nodepool-id",config_filepath="nodepool_config.yaml")
#Get a nodepoolnodepool=compute_cluster.nodepool(nodepool_id="demo-nodepool-id")
print(nodepool)
# List nodepoolsall_nodepools=list(compute_cluster.list_nodepools())
print(all_nodepools)fromclarifai.client.nodepoolimportNodepool# Initialize the Nodepool instancenodepool=Nodepool(user_id="user_id",nodepool_id="demo-nodepool-id")
# Create a new deploymentdeployment=nodepool.create_deployment(deployment_id="demo-deployment-id",config_filepath="deployment_config.yaml")
#Get a deploymentdeployment=nodepool.deployment(nodepool_id="demo-deployment-id")
print(deployment)
# List deploymentsall_deployments=list(nodepool.list_deployments())
print(all_deployments)Refer Here: https://github.com/Clarifai/clarifai-python/tree/master/clarifai/cli
Clarifai datasets help in managing datasets used for model training and evaluation. It provides functionalities like creating datasets,uploading datasets, retrying failed uploads from logs and exporting datasets as .zip files.
# Note: CLARIFAI_PAT must be set as env variable.# Create app and datasetapp=client.create_app(app_id="demo_app", base_workflow="Universal")
dataset=app.create_dataset(dataset_id="demo_dataset")
# execute data upload to Clarifai app datasetfromclarifai.datasets.upload.loaders.coco_detectionimportCOCODetectionDataLoadercoco_dataloader=COCODetectionDataLoader("images_dir", "coco_annotation_filepath")
dataset.upload_dataset(dataloader=coco_dataloader, get_upload_status=True)
#Try upload and record the failed outputs in log file.fromclarifai.datasets.upload.utilsimportload_module_dataloadercifar_dataloader=load_module_dataloader('./image_classification/cifar10')
dataset.upload_dataset(dataloader=cifar_dataloader,
get_upload_status=True,
log_warnings=True)
#Retry upload from logs for `upload_dataset`# Set retry_duplicates to True if you want to ingest failed inputs due to duplication issues. by default it is set to 'False'.dataset.retry_upload_from_logs(dataloader=cifar_dataloader, log_file_path='log_file.log',
retry_duplicates=True,
log_warnings=True)
#upload text from csvdataset.upload_from_csv(csv_path='csv_path', input_type='text', csv_type='raw', labels=True)
#upload data from folderdataset.upload_from_folder(folder_path='folder_path', input_type='text', labels=True)
# Export Datasetdataset.export(save_path='output.zip')You can use inputs() for adding and interacting with input data. Inputs can be uploaded directly from a URL or a file. You can also view input annotations and concepts.
# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.userimportUserapp=User(user_id="user_id").app(app_id="app_id")
input_obj=app.inputs()
#input upload from urlinput_obj.upload_from_url(input_id='demo', image_url='https://samples.clarifai.com/metro-north.jpg')
#input upload from filenameinput_obj.upload_from_file(input_id='demo', video_file='demo.mp4')
# text uploadinput_obj.upload_text(input_id='demo', raw_text='This is a test')#listing inputsinput_generator=input_obj.list_inputs(page_no=1,per_page=10,input_type='image')
inputs_list=list(input_generator)
#listing annotationsannotation_generator=input_obj.list_annotations(batch_input=inputs_list)
annotations_list=list(annotation_generator)
#listing conceptsall_concepts=list(app.list_concepts())#listing inputsinput_generator=input_obj.list_inputs(page_no=1,per_page=1,input_type='image')
inputs_list=list(input_generator)
#downloading_inputsinput_bytes=input_obj.download_inputs(inputs_list)
withopen('demo.jpg','wb') asf:
f.write(input_bytes[0])The Model Class allows you to perform predictions using Clarifai models. You can specify which model to use by providing the model URL or ID. This gives you flexibility in choosing models. The App Class also allows listing of all available Clarifai models for discovery.
For greater control over model predictions, you can pass in an output_config to modify the model output as demonstrated below.
# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.modelimportModel"""Get Model information on details of model(description, usecases..etc) and info on training or# other inference parameters(eg: temperature, top_k, max_tokens..etc for LLMs)"""gpt_4_model=Model("https://clarifai.com/openai/chat-completion/models/GPT-4")
print(gpt_4_model)
# Model Predictmodel_prediction=Model("https://clarifai.com/anthropic/completion/models/claude-v2").predict_by_bytes(b"Write a tweet on future of AI")
# Customizing Model Inference Outputmodel_prediction=gpt_4_model.predict_by_bytes(b"Write a tweet on future of AI", inference_params=dict(temperature=str(0.7), max_tokens=30))
# Return predictions having prediction confidence > 0.98model_prediction=model.predict_by_filepath(filepath="local_filepath", output_config={"min_value": 0.98}) # Supports image, text, audio, video# Supports prediction by urlmodel_prediction=model.predict_by_url(url="url") # Supports image, text, audio, video# Return predictions for specified interval of videovideo_input_proto= [input_obj.get_input_from_url("Input_id", video_url=BEER_VIDEO_URL)]
model_prediction=model.predict(video_input_proto, output_config={"sample_ms": 2000})# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.appimportAppfromclarifai.client.modelimportModel"""Create model with trainable model_type"""app=App(user_id="user_id", app_id="app_id")
model=app.create_model(model_id="model_id", model_type_id="visual-classifier")
(or)
model=Model('url')
"""List training templates for the model_type"""templates=model.list_training_templates()
print(templates)
"""Get parameters for the model."""params=model.get_params(template='classification_basemodel_v1', save_to='model_params.yaml')
"""Update the model params yaml and pass it to model.train()"""model_version_id=model.train('model_params.yaml')
"""Training status and saving logs"""status=model.training_status(version_id=model_version_id,training_logs=True)
print(status)Model Export feature enables you to package your trained model into a model.tar file. This file enables deploying your model within a Triton Inference Server deployment.
fromclarifai.client.modelimportModelmodel=Model('url')
model.export('output/folder/')When your model is trained and ready, you can evaluate by the following code
fromclarifai.client.modelimportModelmodel=Model('url')
model.evaluate(dataset_id='your-dataset-id')Compare the evaluation results of your models.
fromclarifai.client.modelimportModelfromclarifai.client.datasetimportDatasetfromclarifai.utils.evaluationimportEvalResultComparemodels= ['model url1', 'model url2'] # or [Model(url1), Model(url2)]dataset='dataset url'# or Dataset(dataset_url)compare=EvalResultCompare(
models=models,
datasets=dataset,
attempt_evaluate=True# attempt evaluate when the model is not evaluated with the dataset
)
compare.all('output/folder/')# Note: CLARIFAI_PAT must be set as env variable.# List all model versionsall_model_versions=list(model.list_versions())
# Go to specific model versionmodel_v1=client.app("app_id").model(model_id="model_id", model_version_id="model_version_id")
# List all models in an appall_models=list(app.list_models())
# List all models in community filtered by model_type, descriptionall_llm_community_models=App().list_models(filter_by={"query": "LLM",
"model_type_id": "text-to-text"}, only_in_app=False)
all_llm_community_models=list(all_llm_community_models)Workflows offer a versatile framework for constructing the inference pipeline, simplifying the integration of diverse models. You can use the Workflow class to create and manage workflows using YAML configuration. For starting or making quick adjustments to existing Clarifai community workflows using an initial YAML configuration, the SDK provides an export feature.
# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.workflowimportWorkflow# Workflow Predictworkflow=Workflow("workflow_url") # Example: https://clarifai.com/clarifai/main/workflows/Face-Sentimentworkflow_prediction=workflow.predict_by_url(url="url") # Supports image, text, audio, video# Customizing Workflow Inference Outputworkflow=Workflow(user_id="user_id", app_id="app_id", workflow_id="workflow_id",
output_config={"min_value": 0.98}) # Return predictions having prediction confidence > 0.98workflow_prediction=workflow.predict_by_filepath(filepath="local_filepath") # Supports image, text, audio, video# Note: CLARIFAI_PAT must be set as env variable.# List all workflow versionsall_workflow_versions=list(workflow.list_versions())
# Go to specific workflow versionworkflow_v1=Workflow(workflow_id="workflow_id", workflow_version=dict(id="workflow_version_id"), app_id="app_id", user_id="user_id")
# List all workflow in an appall_workflow=list(app.list_workflow())
# List all workflow in community filtered by descriptionall_face_community_workflows=App().list_workflows(filter_by={"query": "face"}, only_in_app=False) # Get all face related workflowsall_face_community_workflows=list(all_face_community_workflows)Create a new workflow specified by a yaml config file.
# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.appimportAppapp=App(app_id="app_id", user_id="user_id")
workflow=app.create_workflow(config_filepath="config.yml")Export an existing workflow from Clarifai as a local yaml file.
# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.workflowimportWorkflowworkflow=Workflow("https://clarifai.com/clarifai/main/workflows/Demographics")
workflow.export('demographics_workflow.yml')Clarifai's Smart Search feature leverages vector search capabilities to power the search experience. Vector search is a type of search engine that uses vectors to search and retrieve text, images, and videos.
Instead of traditional keyword-based search, where exact matches are sought, vector search allows for searching based on visual and/or semantic similarity by calculating distances between vector embedding representations of the data.
Here is an example of how to use vector search to find similar images:
# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.searchimportSearchsearch=Search(user_id="user_id", app_id="app_id", top_k=1, metric="cosine")
# Search by image urlresults=search.query(ranks=[{"image_url": "https://samples.clarifai.com/metro-north.jpg"}])
fordatainresults:
print(data.hits[0].input.data.image.url)Smart Text Search is our proprietary feature that uses deep learning techniques to sort, rank, and retrieve text data based on their content and semantic similarity.
Here is an example of how to use Smart Text Search to find similar text:
# Note: CLARIFAI_PAT must be set as env variable.# Search by textresults=search.query(ranks=[{"text_raw": "I love my dog"}])You can use filters to narrow down your search results. Filters can be used to filter by concepts, metadata, and Geo Point.
It is possible to add together multiple search parameters to expand your search. You can even combine negated search terms for more advanced tasks.
For example, you can combine two concepts as below.
# query for images that contain concept "deer" or "dog"results=search.query(ranks=[{"image_url": "https://samples.clarifai.com/metro-north.jpg"}],
filters=[{"concepts": [{"name": "deer", "value":1},
{"name": "dog", "value":1}]}])
# query for images that contain concepts "deer" and "dog"results=search.query(ranks=[{"image_url": "https://samples.clarifai.com/metro-north.jpg"}],
filters=[{"concepts": [{"name": "deer", "value":1}],
"concepts": [{"name": "dog", "value":1}]}])Input filters allows to filter by input_type, status of inputs and by inputs_dataset_id
results=search.query(filters=[{'input_types': ['image', 'text']}])Below is an example of using Search with Pagination.
# Note: CLARIFAI_PAT must be set as env variable.fromclarifai.client.searchimportSearchsearch=Search(user_id="user_id", app_id="app_id", metric="cosine", pagination=True)
# Search by image urlresults=search.query(ranks=[{"image_url": "https://samples.clarifai.com/metro-north.jpg"}],page_no=2,per_page=5)
fordatainresults:
print(data.hits[0].input.data.image.url)You can setup and start your RAG pipeline in 4 lines of code. The setup method automatically creates a new app and the necessary components under the hood. By default it uses the mistral-7B-Instruct model.
fromclarifai.ragimportRAGrag_agent=RAG.setup(user_id="USER_ID")
rag_agent.upload(folder_path="~/docs")
rag_agent.chat(messages=[{"role":"human", "content":"What is Clarifai"}])If you have previously run the setup method, you can instantiate the RAG class with the prompter workflow URL:
fromclarifai.ragimportRAGrag_agent=RAG(workflow_url="WORKFLOW_URL")See many more code examples in this repo. Also see the official Python SDK docs
Examples for uploading models and runners have been moved to this repo. Find our official documentation at docs.clarifai.com/compute/models/upload.
This project uses CalVer with the format YY.MM.PATCH:
- YY — Clarifai year, counting from the company's founding (e.g.
12for the 12th year) - MM — month number, not zero-padded (e.g.
1for January,12for December) - PATCH — incremental release within that month, starting at
0
Git tags use the same format without a v prefix (e.g. 12.2.0). The version is defined in clarifai/__init__.py.