Update app.py

app.py

@@ -1,11 +1,24 @@
 import streamlit as st
-#from streamlit_datalist import stDatalist
 from utils import convert_to_base64, convert_to_html
 import requests
+import boto3
+import sagemaker
+
+region = os.getenv("region")
+sm_endpoint_name = os.getenv("sm_endpoint_name")
+access_key = os.getenv("access_key")
+secret_key = os.getenv("secret_key")
+hf_token = os.getenv("hf_read_access")
+
+session = boto3.Session(
+    aws_access_key_id=access_key,
+    aws_secret_access_key=secret_key,
+    region_name=region
+)
+sess = sagemaker.Session(boto_session=session)
+
+smr = session.client("sagemaker-runtime")
 
-IP = '127.0.0.1'
-PORT= 8080
-url = f'http://{IP}:{PORT}/predictions/model'
 headers = {'Content-Type': 'application/json'}
 st.set_page_config(page_title="AWS Inferentia2 Demo", layout="wide")
 #st.set_page_config(layout="wide")
@@ -72,9 +85,15 @@ def ask_llm(prompt, byte_image):
             "temperature": 0.2,
         }
     }
-    response = requests.post(url, json=payload, headers=headers)
+    #response = requests.post(url, json=payload, headers=headers)
+    response = smr.invoke_endpoint(
+        EndpointName=sm_endpoint_name,
+        Body=json.dumps(payload),
+        ContentType="application/json",
+    )
 
-    return response.text
+    #return response.text
+    return response
 
 def app():
     st.markdown("---")