init project

.gitignore

@@ -0,0 +1,2 @@
+# files
+*.DS_Store

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Đặt biến môi trường cho cache (sử dụng HF_HOME thay vì TRANSFORMERS_CACHE)
+ENV HF_HOME=/tmp/.cache
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY app.py .
+
+RUN mkdir -p /tmp/hf_home /tmp/transformers_cache
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,27 @@
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+app = FastAPI()
+
+# Load model
+model_name = "AITeamVN/Vietnamese_Embedding_v2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+
+class InputText(BaseModel):
+    text: str
+
+@app.get("/")
+def root():
+    return {"message": "AITeamVN/Vietnamese_Embedding_v2 embedding API is running."}
+
+@app.post("/embed")
+def get_embedding(data: InputText):
+    inputs = tokenizer(data.text, return_tensors="pt", padding=True, truncation=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        # Get CLS token or use pooling method
+        embedding = outputs.last_hidden_state[:, 0, :].squeeze().tolist()
+    return {"embedding": embedding}

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+fastapi
+uvicorn