delete cache dir

Dockerfile

@@ -1,25 +1,14 @@
-# Use the existing base image
-FROM python:3.9
+# Use the official Python 3.10.9 image
+FROM python:3.10.9
 
-# Set the working directory
-WORKDIR /app
-
-# Copy requirements file and install dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Set the HF_HOME environment variable to a writable directory
-ENV HF_HOME=/app/.cache
-ENV TRANSFORMERS_CACHE=/app/.cache
-
-# Create the huggingface directory and set the correct permissions
-RUN mkdir -p /app/.cache && chmod -R 777 /app/.cache
-
-# Copy the application files
+# Copy the current directory contents into the container at .
 COPY . .
 
-# Expose the port (if needed)
-EXPOSE 8000
+# Set the working directory to /
+WORKDIR /
+
+# Install requirements.txt 
+RUN pip install --no-cache-dir --upgrade -r /requirements.txt
 
-# Command to run the application
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000", "--log-level", "debug"]
+# Start the FastAPI app on port 7860, the default port expected by Spaces
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]

app.py

@@ -1,13 +1,10 @@
 from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 import os
 
-# Set the cache directory to a writable location
-os.environ['TRANSFORMERS_CACHE'] = '/app/.cache'
-os.environ['HF_HOME'] = '/app/.cache'
-
 # Inisialisasi model dan tokenizer
 model_name = "w11wo/indonesian-roberta-base-sentiment-classifier"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -16,6 +13,14 @@ model = AutoModelForSequenceClassification.from_pretrained(model_name)
 # Inisialisasi FastAPI
 app = FastAPI()
 
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Bisa disesuaikan dengan daftar asal yang diizinkan
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
 # Model request body
 class TextInput(BaseModel):
     text: str