Add lightweight bge-m3 embedding API (no llama-cpp-python)

app.py

@@ -0,0 +1,30 @@
+"""
+Hiền Concept — bge-m3 Embedding Service
+Lightweight HF Space: gradio + sentence-transformers only (~300MB)
+API: POST /api/predict → 1024-dim float list
+"""
+
+import gradio as gr
+from sentence_transformers import SentenceTransformer
+
+print("📥 Loading BAAI/bge-m3...")
+model = SentenceTransformer("BAAI/bge-m3")
+print("✅ bge-m3 ready!")
+
+
+def embed(text: str) -> list:
+    """Embed text with bge-m3. Called by Vercel chatbot via Gradio API."""
+    if not text or not text.strip():
+        return []
+    vec = model.encode(text.strip(), normalize_embeddings=True)
+    return vec.tolist()
+
+
+with gr.Blocks(title="Hiền Embed") as demo:
+    gr.Markdown("# bge-m3 Embedding API\n1024-dim vectors — used by Hiền Concept chatbot")
+    txt = gr.Textbox(label="Text", placeholder="chi phí là bao nhiêu?")
+    btn = gr.Button("Embed")
+    out = gr.JSON(label="Embedding (1024-dim)")
+    btn.click(fn=embed, inputs=txt, outputs=out, api_name="embed")
+
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio>=4.0.0
+sentence-transformers>=3.0.0