Add application file

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.9
+
+# Tambahkan user non-root
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+# Bekerja di folder app
+WORKDIR /app
+
+# Install dependensi
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir --upgrade pip \
+ && pip install --no-cache-dir -r requirements.txt
+
+# Salin seluruh project
+COPY --chown=user . .
+
+# Port default Gradio (7860) atau bisa ganti jadi 8000 kalau pakai FastAPI
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"] 

app.py

@@ -0,0 +1,35 @@
+import torch
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+app = FastAPI()
+
+model_id = "mistralai/Mistral-7B-Instruct-v0.1"  # example model
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32)
+
+class ChatRequest(BaseModel):
+    messages: list
+
+@app.post("/chat")
+async def chat(req: ChatRequest):
+    prompt = ""
+    for msg in req.messages:
+        role = msg['role']
+        content = msg['content']
+        prompt += f"[{role.capitalize()}]: {content}\n"
+    prompt += "[Assistant]:"
+
+    # Encode the prompt
+    inputs = tokenizer(prompt, return_tensors="pt")
+    inputs = {key: value.to(model.device) for key, value in inputs.items()}
+
+    # Generate a response
+    output = model.generate(inputs['input_ids'], max_new_tokens=100)
+    
+    # Decode the output
+    result = tokenizer.decode(output[0], skip_special_tokens=True)
+    
+    # Return the response, removing the prompt part
+    return {"response": result.replace(prompt, "").strip()}

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn[standard]
+transformers
+torch