SageMaker Endpoint#

Amazon SageMaker is a system that can build, train, and deploy machine learning (ML) models for any use case with fully managed infrastructure, tools, and workflows.

This notebooks goes over how to use an LLM hosted on a SageMaker endpoint.

!pip3 install langchain boto3

Set up#

You have to set up following required parameters of the SagemakerEndpoint call:

  • endpoint_name: The name of the endpoint from the deployed Sagemaker model. Must be unique within an AWS Region.

  • credentials_profile_name: The name of the profile in the ~/.aws/credentials or ~/.aws/config files, which has either access keys or role information specified. If not specified, the default credential profile or, if on an EC2 instance, credentials from IMDS will be used. See:


from langchain.docstore.document import Document
example_doc_1 = """
Peter and Elizabeth took a taxi to attend the night party in the city. While in the party, Elizabeth collapsed and was rushed to the hospital.
Since she was diagnosed with a brain injury, the doctor told Peter to stay besides her until she gets well.
Therefore, Peter stayed with her at the hospital for 3 days without leaving.

docs = [
from typing import Dict

from langchain import PromptTemplate, SagemakerEndpoint
from langchain.llms.sagemaker_endpoint import LLMContentHandler
from langchain.chains.question_answering import load_qa_chain
import json

query = """How long was Elizabeth hospitalized?

prompt_template = """Use the following pieces of context to answer the question at the end.


Question: {question}
PROMPT = PromptTemplate(
    template=prompt_template, input_variables=["context", "question"]

class ContentHandler(LLMContentHandler):
    content_type = "application/json"
    accepts = "application/json"

    def transform_input(self, prompt: str, model_kwargs: Dict) -> bytes:
        input_str = json.dumps({prompt: prompt, **model_kwargs})
        return input_str.encode('utf-8')
    def transform_output(self, output: bytes) -> str:
        response_json = json.loads("utf-8"))
        return response_json[0]["generated_text"]

content_handler = ContentHandler()

chain = load_qa_chain(

chain({"input_documents": docs, "question": query}, return_only_outputs=True)