Create app.py

app.py

@@ -0,0 +1,71 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+print("Loading IndoBERT model...")
+MODEL_NAME = "indobenchmark/indobert-base-p1"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModel.from_pretrained(MODEL_NAME)
+model.eval()
+print("Model loaded!")
+
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0]
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+def generate_embedding(text):
+    encoded_input = tokenizer(text, padding=True, truncation=True, max_length=512, return_tensors='pt')
+    
+    with torch.no_grad():
+        model_output = model(**encoded_input)
+    
+    embedding = mean_pooling(model_output, encoded_input['attention_mask'])
+    embedding = torch.nn.functional.normalize(embedding, p=2, dim=1)
+    
+    return embedding[0].numpy().tolist()
+
+def embed_single(text):
+    """For Gradio interface - single text"""
+    if not text:
+        return {"error": "Text required"}
+    
+    embedding = generate_embedding(text)
+    return {
+        "success": True,
+        "embedding": embedding,
+        "dimension": len(embedding)
+    }
+
+def embed_batch(texts):
+    """For Gradio interface - batch texts"""
+    if not texts:
+        return {"error": "Texts required"}
+    
+    text_list = [t.strip() for t in texts.split('\n') if t.strip()]
+    embeddings = [generate_embedding(text) for text in text_list]
+    
+    return {
+        "success": True,
+        "embeddings": embeddings,
+        "count": len(embeddings),
+        "dimension": len(embeddings[0]) if embeddings else 0
+    }
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# 🇮🇩 IndoBERT Embedding API")
+    
+    with gr.Tab("Single"):
+        input_single = gr.Textbox(label="Text", lines=3)
+        btn_single = gr.Button("Generate")
+        output_single = gr.JSON(label="Result")
+        btn_single.click(embed_single, inputs=input_single, outputs=output_single)
+    
+    with gr.Tab("Batch"):
+        input_batch = gr.Textbox(label="Texts (one per line)", lines=10)
+        btn_batch = gr.Button("Generate Batch")
+        output_batch = gr.JSON(label="Result")
+        btn_batch.click(embed_batch, inputs=input_batch, outputs=output_batch)
+
+demo.launch()