Update app.py

app.py

@@ -3,74 +3,42 @@ import sagemaker
 import boto3
 from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
 
+# Get IAM execution role
 try:
-	role = sagemaker.get_execution_role()
+    role = sagemaker.get_execution_role()
 except ValueError:
-	iam = boto3.client('iam')
-	role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
+    iam = boto3.client('iam')
+    role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
 
-# Hub Model configuration. https://huggingface.co/models
+# Hugging Face model configuration
 hub = {
-	'HF_MODEL_ID':'praneethposina/customer_support_bot',
-	'SM_NUM_GPUS': json.dumps(1)
+    'HF_MODEL_ID': 'praneethposina/customer_support_bot',
+    'SM_NUM_GPUS': json.dumps(1),
 }
 
+# Get the correct image URI for Hugging Face LLM
+image_uri = get_huggingface_llm_image_uri(
+    backend="huggingface", 
+    version="3.2.3"
+)
 
-
-# create Hugging Face Model Class
+# Create HuggingFaceModel instance
 huggingface_model = HuggingFaceModel(
-	image_uri=get_huggingface_llm_image_uri("huggingface",version="3.2.3"),
-	env=hub,
-	role=role, 
+    image_uri=image_uri,
+    env=hub,
+    role=role
 )
 
-# deploy model to SageMaker Inference
+# Deploy the model to SageMaker
 predictor = huggingface_model.deploy(
-	initial_instance_count=1,
-	instance_type="ml.g5.2xlarge",
-	container_startup_health_check_timeout=300,
-  )
-  
-# send request
-predictor.predict({
-	"inputs": "Hi, what can you help me with?",
-})
-
-
-import json
-import sagemaker
-import boto3
-from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
-
-try:
-	role = sagemaker.get_execution_role()
-except ValueError:
-	iam = boto3.client('iam')
-	role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
-
-# Hub Model configuration. https://huggingface.co/models
-hub = {
-	'HF_MODEL_ID':'praneethposina/customer_support_bot',
-	'SM_NUM_GPUS': json.dumps(1)
-}
-
-
-
-# create Hugging Face Model Class
-huggingface_model = HuggingFaceModel(
-	image_uri=get_huggingface_llm_image_uri("huggingface",version="3.2.3"),
-	env=hub,
-	role=role, 
+    initial_instance_count=1,
+    instance_type="ml.g5.2xlarge",
+    container_startup_health_check_timeout=300,
 )
 
-# deploy model to SageMaker Inference
-predictor = huggingface_model.deploy(
-	initial_instance_count=1,
-	instance_type="ml.g5.2xlarge",
-	container_startup_health_check_timeout=300,
-  )
-  
-# send request
-predictor.predict({
-	"inputs": "Hi, what can you help me with?",
-})
+# Perform inference
+response = predictor.predict({
+    "inputs": "Hi, what can you help me with?"
+})
+
+print("Model Response:", response)