Upload 3 files

Dockerfile

@@ -0,0 +1,26 @@
+# Gunakan image base Python
+FROM python:3.11
+
+# Set working directory
+WORKDIR /app
+
+# Install build tools dan clean apt cache agar image tetap ringan
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    git \
+    curl \
+ && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements dan install
+COPY requirements.txt .
+RUN pip install --upgrade pip
+RUN pip install --no-cache-dir -r requirements.txt -f https://download.pytorch.org/whl/torch_stable.html
+
+# Copy seluruh kode aplikasi
+COPY . .
+
+# Expose port yang digunakan (sesuaikan dengan port API)
+EXPOSE 8000
+
+# Jalankan aplikasi
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]

app.py

@@ -0,0 +1,36 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import torch
+
+# Inisialisasi FastAPI
+app = FastAPI()
+
+# Deteksi device (GPU jika tersedia)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load model dan tokenizer
+model_name = "hanifahputri/Capstone-Model-SumAI"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name).to(device)
+
+# Schema untuk input menggunakan Pydantic
+class SummarizationRequest(BaseModel):
+    text: str
+
+# Endpoint untuk summarization
+@app.post("/summarize")
+def summarize(request: SummarizationRequest):
+    text = request.text
+    inputs = tokenizer.encode("summarize: " + text, return_tensors="pt", max_length=512, truncation=True).to(device)
+    outputs = model.generate(
+        inputs,
+        max_length=150,
+        min_length=30,
+        length_penalty=2.0,
+        num_beams=4,
+        early_stopping=True
+    )
+    summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"summary": summary}
+

requirements.txt

@@ -0,0 +1,6 @@
+fastapi==0.115.12
+uvicorn==0.34.2
+torch==2.3.0+cpu
+transformers==4.51.3
+sentencepiece==0.2.0
+protobuf==4.25.3