| import gradio as gr | |
| from sentence_transformers import SentenceTransformer | |
| # ✅ Load a model that outputs 1024-dim vectors | |
| model = SentenceTransformer('intfloat/e5-large') | |
| def embed_text(text): | |
| # Optionally prepend "passage: " if using e5 models | |
| processed_text = "passage: " + text.strip() | |
| embedding = model.encode(processed_text).tolist() | |
| return embedding | |
| # Gradio interface | |
| iface = gr.Interface( | |
| fn=embed_text, | |
| inputs=gr.Textbox(lines=5, label="Enter patient text"), | |
| outputs="json", | |
| title="Clinical Text Embedding API (1024-dim)" | |
| ) | |
| iface.launch() | |