import gradio as gr from transformers import pipeline # Available models for zero-shot classification AVAILABLE_MODELS = [ "mjwong/multilingual-e5-large-instruct-xnli-anli", "mjwong/multilingual-e5-base-xnli-anli", "mjwong/multilingual-e5-large-xnli-anli", "mjwong/mcontriever-msmarco-xnli", "mjwong/mcontriever-xnli" ] def classify_text(model_name, text, labels): classifier = pipeline("zero-shot-classification", model=model_name) labels_list = [label.strip() for label in labels.split(",")] result = classifier(text, candidate_labels=labels_list) return {label: score for label, score in zip(result["labels"], result["scores"])} # Example Input examples = [["One day I will see the world", "travel, live, die, future"]] # Define the Gradio interface css = """ footer {display:none !important} .output-markdown{display:none !important} .gr-button-primary { z-index: 14; height: 43px; width: 130px; left: 0px; top: 0px; padding: 0px; cursor: pointer !important; background: none rgb(17, 20, 45) !important; border: none !important; text-align: center !important; font-family: Poppins !important; font-size: 14px !important; font-weight: 500 !important; color: rgb(255, 255, 255) !important; line-height: 1 !important; border-radius: 12px !important; transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important; box-shadow: none !important; } .gr-button-primary:hover{ background: none rgb(66, 133, 244) !important; box-shadow: rgb(0 0 0 / 23%) 0px 1px 7px 0px !important; } /* Two-column layout for text and labels */ .gr-blocks-container { display: flex; gap: 20px; } .gr-blocks-container .gr-block:first-child { flex: 1; } .gr-blocks-container .gr-block:last-child { flex: 1; } """ iface = gr.Interface( fn=classify_text, inputs=[ gr.Dropdown(AVAILABLE_MODELS, label="Choose Model"), gr.Row([ gr.Textbox(label="Enter Text", placeholder="Type or paste text here..."), gr.Textbox(label="Enter Labels (comma-separated)", placeholder="e.g., sports, politics, technology") ]) ], outputs=gr.Label(label="Classification Scores"), title="Zero-Shot Text Classifier", description="Select a model, enter text, and a set of labels to classify it using a zero-shot classification model.", examples=examples, css=css ) # Launch the app if __name__ == "__main__": iface.launch()