Amazon Bedrock 集成

# install requirements
%pip install boto3 langfuse awscli --quiet

AWS_ACCESS_KEY_ID="***"
AWS_SECRET_ACCESS_KEY="***"
AWS_SESSION_TOKEN="***"
 
import boto3
 
# used to access Bedrock configuration
bedrock = boto3.client(
    service_name="bedrock",
    region_name="eu-west-1",
    aws_access_key_id=AWS_ACCESS_KEY_ID,
    aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
    aws_session_token=AWS_SESSION_TOKEN
)
 
# used to invoke the Bedrock Converse API
bedrock_runtime = boto3.client(
    service_name="bedrock-runtime",
    region_name="eu-west-1",
    aws_access_key_id=AWS_ACCESS_KEY_ID,
    aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
    aws_session_token=AWS_SESSION_TOKEN
)

# Check which models are available in your account
models = bedrock.list_inference_profiles()
for model in models["inferenceProfileSummaries"]:
  print(model["inferenceProfileName"] + " - " + model["inferenceProfileId"])

EU Anthropic Claude 3 Sonnet - eu.anthropic.claude-3-sonnet-20240229-v1:0
EU Anthropic Claude 3 Haiku - eu.anthropic.claude-3-haiku-20240307-v1:0
EU Anthropic Claude 3.5 Sonnet - eu.anthropic.claude-3-5-sonnet-20240620-v1:0
EU Meta Llama 3.2 3B Instruct - eu.meta.llama3-2-3b-instruct-v1:0
EU Meta Llama 3.2 1B Instruct - eu.meta.llama3-2-1b-instruct-v1:0

import os
 
# Get keys for your project from the project settings page
# https://litefuse.cloud
os.environ["LANGFUSE_PUBLIC_KEY"] = ""
os.environ["LANGFUSE_SECRET_KEY"] = ""
os.environ["LANGFUSE_BASE_URL"] = "https://litefuse.cloud"
 
# Your openai key
os.environ["OPENAI_API_KEY"] = ""

from langfuse import get_client
 
langfuse = get_client()
 
# Verify connection
if langfuse.auth_check():
    print("Langfuse client is authenticated and ready!")
else:
    print("Authentication failed. Please check your credentials and host.")

from langfuse import observe
from botocore.exceptions import ClientError
 
@observe(as_type="generation", name="Bedrock Converse")
def wrapped_bedrock_converse(**kwargs):
  # 1. extract model metadata
  kwargs_clone = kwargs.copy()
  input = kwargs_clone.pop('messages', None)
  modelId = kwargs_clone.pop('modelId', None)
  model_parameters = {
      **kwargs_clone.pop('inferenceConfig', {}),
      **kwargs_clone.pop('additionalModelRequestFields', {})
  }
  langfuse.update_current_generation(
    input=input,
    model=modelId,
    model_parameters=model_parameters,
    metadata=kwargs_clone
  )
 
  # 2. model call with error handling
  try:
    response = bedrock_runtime.converse(**kwargs)
  except (ClientError, Exception) as e:
    error_message = f"ERROR: Can't invoke '{modelId}'. Reason: {e}"
    langfuse.update_current_generation(level="ERROR", status_message=error_message)
    print(error_message)
    return
 
  # 3. extract response metadata
  response_text = response["output"]["message"]["content"][0]["text"]
  langfuse.update_current_generation(
    output=response_text,
    usage_details={
        "input": response["usage"]["inputTokens"],
        "output": response["usage"]["outputTokens"],
        "total": response["usage"]["totalTokens"]
    },
    metadata={
        "ResponseMetadata": response["ResponseMetadata"],
    }
  )
 
  return response_text

# Converesation according to AWS spec including prompting + history
user_message = """You will be acting as an AI personal finance advisor named Alex, created by the company SmartFinance Advisors. Your goal is to provide financial advice and guidance to users. You will be replying to users who are on the SmartFinance Advisors site and who will be confused if you don't respond in the character of Alex.
 
Here is the conversational history (between the user and you) prior to the question. It could be empty if there is no history:
<history>
User: Hi Alex, I'm really looking forward to your advice!
Alex: Hello! I'm Alex, your AI personal finance advisor from SmartFinance Advisors. How can I assist you with your financial goals today?
</history>
 
Here are some important rules for the interaction:
-  Always stay in character, as Alex, an AI from SmartFinance Advisors.
-  If you are unsure how to respond, say "I'm sorry, I didn't quite catch that. Could you please rephrase your question?"
"""
 
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]
 
@observe()
def examples_bedrock_converse_api():
  responses = {}
 
  responses["anthropic"] = wrapped_bedrock_converse(
    modelId="eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
    messages=conversation,
    inferenceConfig={"maxTokens":500,"temperature":1},
    additionalModelRequestFields={"top_k":250}
  )
 
  responses["llama3-2"] = wrapped_bedrock_converse(
    modelId="eu.meta.llama3-2-3b-instruct-v1:0",
    messages=conversation,
    inferenceConfig={"maxTokens":500,"temperature":1},
  )
 
  return responses
 
res = examples_bedrock_converse_api()
 
for key, value in res.items():
    print(f"{key.title()}\n{value}\n")

Anthropic
Understood. I'll continue to act as Alex, the AI personal finance advisor from SmartFinance Advisors, maintaining that character throughout our interaction. I'll provide financial advice and guidance based on the user's questions and needs. If I'm unsure about something, I'll ask for clarification as instructed. How may I assist you with your financial matters today?

Llama3-2
Hello again! I'm glad you're excited about receiving my advice. How can I assist you with your financial goals today? Are you looking to create a budget, paying off debt, saving for a specific goal, or something else entirely?