Update app.py

app.py

@@ -4,19 +4,20 @@ from pydantic import BaseModel
 from prometheus_client import Counter, generate_latest, CONTENT_TYPE_LATEST
 from transformers import pipeline
 import gradio as gr
+import uvicorn
 
-# ✅ Expose FastAPI app at top level
+# ✅ FastAPI app
 app = FastAPI()
 
 # 📊 Prometheus metrics
 triage_requests = Counter("triage_requests_total", "Total triage requests")
 triage_errors = Counter("triage_errors_total", "Total triage errors")
 
-# 🧠 Load lightweight model (CPU only)
+# 🧠 Load ultra-lightweight model
 triage_pipeline = pipeline(
     "text2text-generation",
-    model="google/flan-t5-small",
-    device=-1  # Force CPU
+    model="sshleifer/tiny-t5",  # ~25MB model
+    device=-1
 )
 
 # 📥 Request model
@@ -29,7 +30,7 @@ async def triage(incident: Incident):
     triage_requests.inc()
     try:
         prompt = f"Classify this incident and suggest priority:\n\n{incident.description}"
-        result = triage_pipeline(prompt, max_new_tokens=100)[0]["generated_text"]
+        result = triage_pipeline(prompt, max_new_tokens=50)[0]["generated_text"]
         return {"triage": result.strip()}
     except Exception as e:
         triage_errors.inc()
@@ -50,7 +51,7 @@ def gradio_triage(description):
     try:
         triage_requests.inc()
         prompt = f"Classify this incident and suggest priority:\n\n{description}"
-        result = triage_pipeline(prompt, max_new_tokens=100)[0]["generated_text"]
+        result = triage_pipeline(prompt, max_new_tokens=50)[0]["generated_text"]
         return result.strip()
     except Exception as e:
         triage_errors.inc()
@@ -61,9 +62,9 @@ demo = gr.Interface(
     inputs=gr.Textbox(lines=5, placeholder="Describe the incident..."),
     outputs="text",
     title="Incident Triage Bot",
-    description="Classify incidents and suggest priority using a lightweight Transformers model"
+    description="Classify incidents and suggest priority using a tiny Transformers model"
 )
 
-@app.get("/gradio")
-def gradio_ui():
-    return Response(content=demo.launch(share=False, inline=True), media_type="text/html")
+# ✅ Mount Gradio properly
+from fastapi.middleware.wsgi import WSGIMiddleware
+app.mount("/gradio", gr.mount_gradio_app(app, demo, path="/gradio"))