SageMakerEndpoint integration

Integrate with the SageMakerEndpoint LLM using LangChain Python.

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: boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html

Example

from langchain_core.documents 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 = [
    Document(
        page_content=example_doc_1,
    )
]

Example to initialize with external boto3 session

for cross account scenarios

import json
from typing import Dict

import boto3
from langchain_classic.chains.question_answering import load_qa_chain
from langchain_aws.llms import SagemakerEndpoint
from langchain_aws.llms.sagemaker_endpoint import LLMContentHandler
from langchain_core.prompts import PromptTemplate

query = """How long was Elizabeth hospitalized?
"""

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

{context}

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

roleARN = "arn:aws:iam::123456789:role/cross-account-role"
sts_client = boto3.client("sts")
response = sts_client.assume_role(
    RoleArn=roleARN, RoleSessionName="CrossAccountSession"
)

client = boto3.client(
    "sagemaker-runtime",
    region_name="us-west-2",
    aws_access_key_id=response["Credentials"]["AccessKeyId"],
    aws_secret_access_key=response["Credentials"]["SecretAccessKey"],
    aws_session_token=response["Credentials"]["SessionToken"],
)


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

    def transform_input(self, prompt: str, model_kwargs: Dict) -> bytes:
        input_str = json.dumps({"inputs": prompt, "parameters": model_kwargs})
        return input_str.encode("utf-8")

    def transform_output(self, output: bytes) -> str:
        response_json = json.loads(output.read().decode("utf-8"))
        return response_json[0]["generated_text"]


content_handler = ContentHandler()

chain = load_qa_chain(
    llm=SagemakerEndpoint(
        endpoint_name="endpoint-name",
        client=client,
        model_kwargs={"temperature": 1e-10},
        content_handler=content_handler,
    ),
    prompt=PROMPT,
)

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

import json
from typing import Dict

from langchain_classic.chains.question_answering import load_qa_chain
from langchain_aws.llms import SagemakerEndpoint
from langchain_aws.llms.sagemaker_endpoint import LLMContentHandler
from langchain_core.prompts import PromptTemplate

query = """How long was Elizabeth hospitalized?
"""

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

{context}

Question: {question}
Answer:"""
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({"inputs": prompt, "parameters": model_kwargs})
        return input_str.encode("utf-8")

    def transform_output(self, output: bytes) -> str:
        response_json = json.loads(output.read().decode("utf-8"))
        return response_json[0]["generated_text"]


content_handler = ContentHandler()

chain = load_qa_chain(
    llm=SagemakerEndpoint(
        endpoint_name="endpoint-name",
        credentials_profile_name="credentials-profile-name",
        region_name="us-west-2",
        model_kwargs={"temperature": 1e-10},
        content_handler=content_handler,
    ),
    prompt=PROMPT,
)

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

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.