amazon personalize langchain extensions Download - amazon personalize langchain extensions Download do código-fonte

Amazon personaliza extensões Langchain

Este repositório fornece um conjunto de classes utilitárias para trabalhar com Langchain. Atualmente, ele tem uma classe de utilitário AmazonPersonalize para trabalhar com uma campanha/recomendador do Amazon Personalize e uma construção de cadeia personalizada AmazonPersonalizeChain para recuperar recomendações do Amazon Personalize e executar um prompt padrão (que pode ser substituído pelo usuário).

Instalando

Clonar o repositório

git clone https://github.com/aws-samples/amazon-personalize-langchain-extensions.git

Vá para o diretório do repositório

 cd amazon-personalize-langchain-extensions

Instale as classes

pip install .

Uso

[Caso de uso-1] Configure o Amazon Personalize Client e invoque Personalize Chain para resumir os resultados

 from aws_langchain import AmazonPersonalize

recommender_arn = "<insert_arn>"

client = AmazonPersonalize ( credentials_profile_name = "default" , region_name = "us-west-2" , recommender_arn = recommender_arn )
client . get_recommendations ( user_id = "1" )

[Caso de uso-2] Configure o Amazon Personalize Client e invoque Personalize Chain para resumir os resultados

 from aws_langchain import AmazonPersonalize
from aws_langchain import AmazonPersonalizeChain
from langchain . llms . bedrock import Bedrock

recommender_arn = "<insert_arn>"

bedrock_llm = Bedrock ( model_id = "anthropic.claude-v2" , region_name = "us-west-2" )
client = AmazonPersonalize ( credentials_profile_name = "default" , region_name = "us-west-2" , recommender_arn = recommender_arn )
# Create personalize chain
# Use return_direct=True if you do not want summary
chain = AmazonPersonalizeChain . from_llm (
    llm = bedrock_llm , 
    client = client ,
    return_direct = False 
)
response = chain ({ 'user_id' : '1' })
print ( response )

[Use-Case-3] Invoque o Amazon Personalize Chain usando seu próprio prompt

 from langchain . prompts . prompt import PromptTemplate
from aws_langchain import AmazonPersonalize
from aws_langchain import AmazonPersonalizeChain
from langchain . llms . bedrock import Bedrock

RANDOM_PROMPT_QUERY = """
You are a skilled publicist. Write a high-converting marketing email advertising several movies available in a video-on-demand streaming platform next week, 
    given the movie and user information below. Your email will leverage the power of storytelling and persuasive language. 
    The movies to recommend and their information is contained in the <movie> tag. 
    All movies in the <movie> tag must be recommended. Give a summary of the movies and why the human should watch them. 
    Put the email between <email> tags.

    <movie>
    {result} 
    </movie>

    Assistant:
    """

RANDOM_PROMPT = PromptTemplate ( input_variables = [ "result" ], template = RANDOM_PROMPT_QUERY )


recommender_arn = "<insert_arn>"

bedrock_llm = Bedrock ( model_id = "anthropic.claude-v2" , region_name = "us-west-2" )
client = AmazonPersonalize ( credentials_profile_name = "default" , region_name = "us-west-2" , recommender_arn = recommender_arn )

chain = AmazonPersonalizeChain . from_llm ( llm = bedrock_llm , client = client , return_direct = False , prompt_template = RANDOM_PROMPT )
chain . run ({ 'user_id' : '1' , 'item_id' : '234' })

[Caso de uso-4] Invocar o Amazon Personalize em uma cadeia sequencial

 from langchain . chains import SequentialChain
from langchain . chains import LLMChain
from aws_langchain import AmazonPersonalize
from aws_langchain import AmazonPersonalizeChain
from langchain . llms . bedrock import Bedrock
from langchain . prompts . prompt import PromptTemplate

RANDOM_PROMPT_QUERY_2 = """
You are a skilled publicist. Write a high-converting marketing email advertising several movies available in a video-on-demand streaming platform next week, 
    given the movie and user information below. Your email will leverage the power of storytelling and persuasive language. 
    You want the email to impress the user, so make it appealing to them.
    The movies to recommend and their information is contained in the <movie> tag. 
    All movies in the <movie> tag must be recommended. Give a summary of the movies and why the human should watch them. 
    Put the email between <email> tags.

    <movie>
    {result}
    </movie>

    Assistant:
    """

recommender_arn = "<insert_arn>"

bedrock_llm = Bedrock ( model_id = "anthropic.claude-v2" , region_name = "us-west-2" )
client = AmazonPersonalize ( credentials_profile_name = "default" , region_name = "us-west-2" , recommender_arn = recommender_arn )

RANDOM_PROMPT_2 = PromptTemplate ( input_variables = [ "result" ], template = RANDOM_PROMPT_QUERY_2 )
personalize_chain_instance = AmazonPersonalizeChain . from_llm ( llm = bedrock_llm , client = client , return_direct = True )
random_chain_instance = LLMChain ( llm = bedrock_llm , prompt = RANDOM_PROMPT_2 )
overall_chain = SequentialChain ( chains = [ personalize_chain_instance , random_chain_instance ], input_variables = [ "user_id" ], verbose = True )
overall_chain . run ({ 'user_id' : '1' , 'item_id' : '234' })

[Caso de uso-5] Invocar o Amazon Personalize usando metadados da resposta

 from aws_langchain import AmazonPersonalize
from aws_langchain import AmazonPersonalizeChain
from langchain . llms . bedrock import Bedrock

recommender_arn = "<insert_arn>"
metadata_column_list = [ "METADATA_COL1" ]
metadataMap = { "ITEMS" : metadata_column_list }

bedrock_llm = Bedrock ( model_id = "anthropic.claude-v2" , region_name = "us-west-2" )
client = AmazonPersonalize ( credentials_profile_name = "default" , region_name = "us-west-2" , recommender_arn = recommender_arn )
# Create personalize chain
# Use return_direct=True if you do not want summary
chain = AmazonPersonalizeChain . from_llm (
    llm = bedrock_llm , 
    client = client ,
    return_direct = False 
)
response = chain ({ 'user_id' : '1' , 'metadata_columns' : metadataMap })
print ( response )