Davide Gallitelli dgallitelli

## bonito-v1-sagemaker.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              1 star
            
          
                dgallitelli
                / bonito-v1-sagemaker.ipynb
            
            
              Last active
              April 4, 2024 13:46
            
              
                Using Bonito v1 on Amazon SageMaker to generate datasets for LLM fine-tuning
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## kendra_results.py
from langchain.docstore.document import Document
import boto3
import re

def clean_result(res_text):
    res = re.sub("\s+", " ", res_text).replace("...","")
    return res

def get_query_language(query):
    # Use Amazon Comprehend to detect the language of the query

## sagemaker_async_endpoint.py
"""Wrapper around Sagemaker InvokeEndpointAsync API."""
from abc import abstractmethod
from typing import Any, List, Optional
from langchain.callbacks.manager import CallbackManagerForLLMRun
from langchain.llms.utils import enforce_stop_tokens
from langchain.llms.sagemaker_endpoint import SagemakerEndpoint
import boto3, time, os, uuid
from botocore.exceptions import ClientError

def wait_inference_file(output_url, failure_url, s3_client=None):
	from langchain.docstore.document import Document
	import boto3
	import re

	def clean_result(res_text):
	res = re.sub("\s+", " ", res_text).replace("...","")
	return res

	def get_query_language(query):
	# Use Amazon Comprehend to detect the language of the query
	"""Wrapper around Sagemaker InvokeEndpointAsync API."""
	from abc import abstractmethod
	from typing import Any, List, Optional
	from langchain.callbacks.manager import CallbackManagerForLLMRun
	from langchain.llms.utils import enforce_stop_tokens
	from langchain.llms.sagemaker_endpoint import SagemakerEndpoint
	import boto3, time, os, uuid
	from botocore.exceptions import ClientError

	def wait_inference_file(output_url, failure_url, s3_client=None):