app.py

from fastapi import FastAPI
from transformers import AutoTokenizer, AutoModel
import torch

# โหลดโมเดล Sentence-Transformer
MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModel.from_pretrained(MODEL_NAME)

# สร้าง API
app = FastAPI()

# ฟังก์ชันแปลงข้อความเป็นเวกเตอร์
def get_embedding(text):
    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
    with torch.no_grad():
        outputs = model(**inputs)
    embedding = outputs.last_hidden_state.mean(dim=1)  # ใช้ค่าเฉลี่ยของ hidden states
    return embedding.squeeze().tolist()

# API Endpoint
@app.post("/embed")
async def embed_text(data: dict):
    text = data.get("text", "")
    if not text:
        return {"error": "No text provided"}
    vector = get_embedding(text)
    return {"text": text, "embedding": vector}