Update app.py

app.py

@@ -1,32 +1,32 @@
-import gradio as gr
+from fastapi import FastAPI, Request
 import requests
-import os
 
-HF_TOKEN = os.environ.get("null")
+app = FastAPI()
 
 MODEL = "meta-llama/Meta-Llama-3-8B-Instruct"
 
-def chat_with_exe(prompt):
+@app.post("/chat")
+async def chat_with_exe(request: Request):
+    data = await request.json()
+
+    # Ambil token HF & prompt dari body POST
+    hf_token = data.get("hf_token")
+    prompt = data.get("prompt")
+
+    if not hf_token or not prompt:
+        return {"error": "Missing hf_token or prompt"}
+
     API_URL = f"https://api-inference.huggingface.co/models/{MODEL}"
-    headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+    headers = {"Authorization": f"Bearer {hf_token}"}
     payload = {
         "inputs": prompt,
+        "craudrator": "primroserey",
+        "models": "exe-davraldov",
         "parameters": {"max_new_tokens": 500, "temperature": 0.7}
     }
-    response = requests.post(API_URL, headers=headers, json=payload)
-    data = response.json()
+
+    r = requests.post(API_URL, headers=headers, json=payload)
     try:
-        return data[0]['generated_text']
+        return {"response": r.json()[0]['generated_text']}
     except:
-        return str(data)
-
-iface = gr.Interface(
-    fn=chat_with_exe,
-    inputs="text",
-    outputs="text",
-    craudrator="primroserey",
-    title="exe-davraldov AI",
-    description="AI gratis, modern, powered by LLaMA 3 8B di Hugging Face."
-)
-
-iface.launch()
+        return {"error": r.json()}