SageMakerEndpoint
Amazon SageMaker 是一個系統，能夠使用完全託管的基礎架構、工具和工作流程，為任何用例構建、訓練和部署機器學習 (ML) 模型。
這個筆記本將介紹如何使用託管在 SageMaker endpoint 上的 LLM。
!pip3 install langchain boto3
設定
您必須設定 SagemakerEndpoint 呼叫的以下必要參數
endpoint_name：已部署的 Sagemaker 模型端點的名稱。 在 AWS 區域內必須是唯一的。credentials_profile_name：~/.aws/credentials 或 ~/.aws/config 檔案中配置文件的名稱，其中指定了訪問金鑰或角色資訊。 如果未指定，將使用預設憑證配置文件，或者，如果在 EC2 實例上，將使用來自 IMDS 的憑證。請參閱：https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
範例
from langchain_core.documents import Document
API 參考：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,
)
]
使用外部 boto3 會話初始化的範例
用於跨帳戶情境
import json
from typing import Dict
import boto3
from langchain.chains.question_answering import load_qa_chain
from langchain_community.llms import SagemakerEndpoint
from langchain_community.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.chains.question_answering import load_qa_chain
from langchain_community.llms import SagemakerEndpoint
from langchain_community.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)