amazon personalize langchain extensions Descargar - amazon personalize langchain extensions Descarga del código fuente

Amazon personaliza las extensiones Langchain

Este repositorio proporciona un conjunto de clases de utilidad para trabajar con Langchain. Actualmente tiene una clase de utilidad AmazonPersonalize para trabajar con una campaña/recomendador de Amazon Personalize y una compilación de cadena personalizada AmazonPersonalizeChain para recuperar recomendaciones de Amazon Personalize y ejecutar un mensaje predeterminado (que el usuario puede anular).

Instalación

Clonar el repositorio

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

Mover al directorio del repositorio

 cd amazon-personalize-langchain-extensions

instalar las clases

pip install .

Uso

[Caso de uso-1] Configure Amazon Personalize Client e invoque Personalize Chain para resumir los 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 Amazon Personalize Client e invoque Personalize Chain para resumir los 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 )

[Caso de uso-3] Invocar Amazon Personalize Chain usando su propio mensaje

 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 Amazon Personalize en una cadena secuencial

 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 Amazon Personalize usando metadatos de la respuesta

 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 )