AWS sagemaker documentation change

Service: sagemaker · 2026-06-28 · Documentation low

File: sagemaker/latest/dg/clarify-foundation-model-evaluate-auto-lib.md

Summary

Added SDK v3 implementation for creating foundation model endpoints using ModelBuilder

Security assessment

New code sample shows standard endpoint deployment. The 'accept_eula' parameter is a license agreement, not a security control. No security mechanisms or vulnerabilities addressed.

Diff

diff --git a/sagemaker/latest/dg/clarify-foundation-model-evaluate-auto-lib.md b/sagemaker/latest/dg/clarify-foundation-model-evaluate-auto-lib.md
index de325e438..8a34a56d5 100644
--- a//sagemaker/latest/dg/clarify-foundation-model-evaluate-auto-lib.md
+++ b//sagemaker/latest/dg/clarify-foundation-model-evaluate-auto-lib.md
@@ -152,0 +153,23 @@ The following code example shows how create an endpoint for a [Llama 2 foundatio
+SageMaker Python SDK v3
+    
+    
+        import sagemaker
+    import json
+    from sagemaker.serve import ModelBuilder
+    from sagemaker.core.jumpstart.configs import JumpStartConfig
+    
+    #JumpStart model and version
+    model_id, model_version = "meta-textgeneration-llama-2-7b-f", "*"
+    
+    jumpstart_config = JumpStartConfig(model_id=model_id, accept_eula=True)
+    model_builder = ModelBuilder.from_jumpstart_config(jumpstart_config=jumpstart_config)
+    model = model_builder.build()
+    endpoint = model_builder.deploy()
+    endpoint_name = endpoint.endpoint_name
+    
+    # Test the endpoint to make sure it works.
+    response = endpoint.invoke(body=json.dumps({"inputs": [[{"role":"user", "content": "Hello how are you?"}]]}))
+
+SageMaker Python SDK v2 (Legacy)
+    
+