JUMP TOGetting StartedOverviewQuick startInstallationLabelbox API keyFundamental conceptsTask objectsWhat's newAnnotateProjectAI criticMultimodal chat evaluation projectPrompt and response projectsBatchModelExperimentsModel run sliceModel run custom metricsFoundryCatalogDatasetData rowAttachmentsCustom embeddingsMedia attributesGlobal keysCatalog sliceSchemaOntologyOntology examplesMetadataFeaturesimport/exportExport overviewExport glossaryImageImport image dataImport image annotationsExport image annotationsUpload image predictionsVideoImport video dataImport video annotationsExport video annotationsUpload video predictionsTextImport text dataImport text annotationsExport text annotationsUpload text predictionsGeospatial (tiled imagery)Import geospatial dataImport geospatial annotationsExport geospatial annotationsUpload geospatial predictionsDocuments (PDF)Import document dataImport document annotationsExport document annotationsUpload document predictionsAudioImport audio dataImport audio annotationsExport audio annotationsHTMLImport HTML dataImport HTML annotationsExport HTML annotationsUpload HTML predictionsConversational textImport conversational text dataImport conversational text annotationsExport conversational text annotationsUpload conversational text predictionsPrompt and response generationImport prompt and response annotationsExport prompt and response dataLLM response evaluationImport conversation & model response dataImport LLM response evaluations annotationsExport LLM response evaluation annotationsUpload LLM response evaluationMultimodal chatImport multimodal chat dataImport multimodal chat annotationsExport multimodal chat annotationsintegrationsIAM integrationWebhooksmanage teamOrganizationUserLabeling WorkforceExamplesExporting to CSVHugging Face integrationImport a labeled dataset (images)Import a labeled dataset (text)Hugging Face integrationDescribes how to combine the Python SDK and HuggingFace Transformer models to improve similarity search. You can improve similarity search for your data rows by using the Labelbox Python SDK and Hugging Face Transformer models to custom embeddings. This lets you use off-the-shelf models to create search terms that lets you compare custom embedding and model performance.