File size: 2,136 Bytes
3f6c2a7 a84c0cf 3f6c2a7 cd6d890 a84c0cf 3f6c2a7 a84c0cf cd6d890 a84c0cf 3f6c2a7 384e68d cd6d890 a84c0cf cd6d890 a84c0cf cd6d890 3f6c2a7 3adf7f1 3f6c2a7 cd6d890 a84c0cf cd6d890 a84c0cf cd6d890 a84c0cf cd6d890 a84c0cf cd6d890 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import os
import logging
app = FastAPI()
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Set the cache directory for Hugging Face
os.environ['TRANSFORMERS_CACHE'] = os.getenv('TRANSFORMERS_CACHE', '/app/cache')
# Enable CORS
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# Load model and tokenizer
model_name = "Bijoy09/MObilebert"
try:
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
logger.info("Model and tokenizer loaded successfully")
except Exception as e:
logger.error(f"Failed to load model or tokenizer: {e}")
raise RuntimeError(f"Failed to load model or tokenizer: {e}")
class TextRequest(BaseModel):
text: str
@app.post("/predict/")
@app.post("/predict")
async def predict(request: TextRequest):
try:
logger.info(f"Received text: {request.text}")
model.eval()
inputs = tokenizer.encode_plus(
request.text,
add_special_tokens=True,
max_length=64,
truncation=True,
padding='max_length',
return_attention_mask=True,
return_tensors='pt'
)
logger.info(f"Tokenized inputs: {inputs}")
with torch.no_grad():
logits = model(inputs['input_ids'], attention_mask=inputs['attention_mask']).logits
logger.info(f"Model logits: {logits}")
prediction = torch.argmax(logits, dim=1).item()
return {"prediction": "Spam" if prediction == 1 else "Ham"}
except Exception as e:
logger.error(f"Prediction failed: {e}")
raise HTTPException(status_code=500, detail=f"Prediction failed: {e}")
@app.get("/")
async def root():
return {"message": "Welcome to the MobileBERT API"}
|