Ändern Sie die Parser-Lambda-Funktion in Amazon Bedrock Agents

import json
import re
import logging
 
 
RATIONALE_REGEX_LIST = [
    "(.*?)(<function_call>)",
    "(.*?)(<answer>)"
]
RATIONALE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_REGEX_LIST]
 
RATIONALE_VALUE_REGEX_LIST = [
    "<scratchpad>(.*?)(</scratchpad>)",
    "(.*?)(</scratchpad>)",
    "(<scratchpad>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_VALUE_REGEX_LIST]
 
ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)
 
ANSWER_TAG = "<answer>"
FUNCTION_CALL_TAG = "<function_call>"
 
ASK_USER_FUNCTION_CALL_REGEX = r"(<function_call>user::askuser)(.*)\)"
ASK_USER_FUNCTION_CALL_PATTERN = re.compile(ASK_USER_FUNCTION_CALL_REGEX, re.DOTALL)
 
ASK_USER_FUNCTION_PARAMETER_REGEX = r"(?<=askuser=\")(.*?)\""  
ASK_USER_FUNCTION_PARAMETER_PATTERN = re.compile(ASK_USER_FUNCTION_PARAMETER_REGEX, re.DOTALL)
 
KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"
 
FUNCTION_CALL_REGEX = r"<function_call>(\w+)::(\w+)::(.+)\((.+)\)"
 
ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"  
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX, re.DOTALL)
 
# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the argument askuser for user::askuser function call. Please try again with the correct argument added"
ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls to the askuser function must be: <function_call>user::askuser(askuser=\"$ASK_USER_INPUT\")</function_call>."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = 'The function call format is incorrect. The format for function calls must be: <function_call>$FUNCTION_NAME($FUNCTION_ARGUMENT_NAME=""$FUNCTION_ARGUMENT_NAME"")</function_call>.'

logger = logging.getLogger()
 
# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
    logger.info("Lambda input: " + str(event))
    
    # Sanitize LLM response
    sanitized_response = sanitize_response(event['invokeModelRawResponse'])
    
    # Parse LLM response for any rationale
    rationale = parse_rationale(sanitized_response)
    
    # Construct response fields common to all invocation types
    parsed_response = {
        'promptType': "ORCHESTRATION",
        'orchestrationParsedResponse': {
            'rationale': rationale
        }
    }
    
    # Check if there is a final answer
    try:
        final_answer, generated_response_parts = parse_answer(sanitized_response)
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
        
    if final_answer:
        parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'FINISH',
            'agentFinalResponse': {
                'responseText': final_answer
            }
        }
        
        if generated_response_parts:
            parsed_response['orchestrationParsedResponse']['responseDetails']['agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
            }
       
        logger.info("Final answer parsed response: " + str(parsed_response))
        return parsed_response
    
    # Check if there is an ask user
    try:
        ask_user = parse_ask_user(sanitized_response)
        if ask_user:
            parsed_response['orchestrationParsedResponse']['responseDetails'] = {
                'invocationType': 'ASK_USER',
                'agentAskUser': {
                    'responseText': ask_user
                }
            }
            
            logger.info("Ask user parsed response: " + str(parsed_response))
            return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
        
    # Check if there is an agent action
    try:
        parsed_response = parse_function_call(sanitized_response, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

    addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
    logger.info(parsed_response)
    return parsed_response
        
    raise Exception("unrecognized prompt type")
 
def sanitize_response(text):
    pattern = r"(\\n*)"
    text = re.sub(pattern, r"\n", text)
    return text
    
def parse_rationale(sanitized_response):
    # Checks for strings that are not required for orchestration
    rationale_matcher = next((pattern.search(sanitized_response) for pattern in RATIONALE_PATTERNS if pattern.search(sanitized_response)), None)
    
    if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()
        
        # Check if there is a formatted rationale that we can parse from the string
        rationale_value_matcher = next((pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if pattern.search(rationale)), None)
        if rationale_value_matcher:
            return rationale_value_matcher.group(1).strip()
        
        return rationale
    
    return None
    
def parse_answer(sanitized_llm_response):
    if has_generated_response(sanitized_llm_response):
        return parse_generated_response(sanitized_llm_response)
 
    answer_match = ANSWER_PATTERN.search(sanitized_llm_response)
    if answer_match and is_answer(sanitized_llm_response):
        return answer_match.group(0).strip(), None
        
    return None, None
  
def is_answer(llm_response):
    return llm_response.rfind(ANSWER_TAG) > llm_response.rfind(FUNCTION_CALL_TAG)
    
def parse_generated_response(sanitized_llm_response):
    results = []
    
    for match in ANSWER_PART_PATTERN.finditer(sanitized_llm_response):
        part = match.group(1).strip()
        
        text_match = ANSWER_TEXT_PART_PATTERN.search(part)
        if not text_match:
            raise ValueError("Could not parse generated response")
        
        text = text_match.group(1).strip()        
        references = parse_references(sanitized_llm_response, part)
        results.append((text, references))
    
    final_response = " ".join([r[0] for r in results])
    
    generated_response_parts = []
    for text, references in results:
        generatedResponsePart = {
            'text': text, 
            'references': references
        }
        generated_response_parts.append(generatedResponsePart)
        
    return final_response, generated_response_parts

    
def has_generated_response(raw_response):
    return ANSWER_PART_PATTERN.search(raw_response) is not None
 
def parse_references(raw_response, answer_part):
    references = []
    for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
        reference = match.group(1).strip()
        references.append({'sourceId': reference})
    return references
    
def parse_ask_user(sanitized_llm_response):
    ask_user_matcher = ASK_USER_FUNCTION_CALL_PATTERN.search(sanitized_llm_response)
    if ask_user_matcher:
        try:
            ask_user = ask_user_matcher.group(2).strip()
            ask_user_question_matcher = ASK_USER_FUNCTION_PARAMETER_PATTERN.search(ask_user)
            if ask_user_question_matcher:
                return ask_user_question_matcher.group(1).strip()
            raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
        except ValueError as ex:
            raise ex
        except Exception as ex:
            raise Exception(ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE)
        
    return None
 
def parse_function_call(sanitized_response, parsed_response):
    match = re.search(FUNCTION_CALL_REGEX, sanitized_response)
    if not match:
        raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)
    
    verb, resource_name, function = match.group(1), match.group(2), match.group(3)
    
    parameters = {}
    for arg in match.group(4).split(","):
        key, value = arg.split("=")
        parameters[key.strip()] = {'value': value.strip('" ')}
        
    parsed_response['orchestrationParsedResponse']['responseDetails'] = {}
        
    # Function calls can either invoke an action group or a knowledge base.
    # Mapping to the correct variable names accordingly
    if resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
        parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'KNOWLEDGE_BASE'
        parsed_response['orchestrationParsedResponse']['responseDetails']['agentKnowledgeBase'] = {
            'searchQuery': parameters['searchQuery'],
            'knowledgeBaseId': resource_name.replace(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, '')
        }
        
        return parsed_response
    
    parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'ACTION_GROUP'
    parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
        "verb": verb, 
        "actionGroupName": resource_name,
        "apiName": function,
        "actionGroupInput": parameters
    }
    
    return parsed_response
    
def addRepromptResponse(parsed_response, error):
    error_message = str(error)
    logger.warn(error_message)
    
    parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
        'repromptResponse': error_message
    }

import logging
import re
import xml.etree.ElementTree as ET

RATIONALE_REGEX_LIST = [
    "(.*?)(<function_calls>)",
    "(.*?)(<answer>)"
]
RATIONALE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_REGEX_LIST]

RATIONALE_VALUE_REGEX_LIST = [
    "<scratchpad>(.*?)(</scratchpad>)",
    "(.*?)(</scratchpad>)",
    "(<scratchpad>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_VALUE_REGEX_LIST]

ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)

ANSWER_TAG = "<answer>"
FUNCTION_CALL_TAG = "<function_calls>"

ASK_USER_FUNCTION_CALL_REGEX = r"<tool_name>user::askuser</tool_name>"
ASK_USER_FUNCTION_CALL_PATTERN = re.compile(ASK_USER_FUNCTION_CALL_REGEX, re.DOTALL)

ASK_USER_TOOL_NAME_REGEX = r"<tool_name>((.|\n)*?)</tool_name>"
ASK_USER_TOOL_NAME_PATTERN = re.compile(ASK_USER_TOOL_NAME_REGEX, re.DOTALL)

TOOL_PARAMETERS_REGEX = r"<parameters>((.|\n)*?)</parameters>"
TOOL_PARAMETERS_PATTERN = re.compile(TOOL_PARAMETERS_REGEX, re.DOTALL)

ASK_USER_TOOL_PARAMETER_REGEX = r"<question>((.|\n)*?)</question>"
ASK_USER_TOOL_PARAMETER_PATTERN = re.compile(ASK_USER_TOOL_PARAMETER_REGEX, re.DOTALL)


KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"

FUNCTION_CALL_REGEX = r"(?<=<function_calls>)(.*)"

ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX, re.DOTALL)

# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the parameter 'question' for user::askuser function call. Please try again with the correct argument added."
ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls to the askuser function must be: <invoke> <tool_name>user::askuser</tool_name><parameters><question>$QUESTION</question></parameters></invoke>."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls must be: <invoke> <tool_name>$TOOL_NAME</tool_name> <parameters> <$PARAMETER_NAME>$PARAMETER_VALUE</$PARAMETER_NAME>...</parameters></invoke>."

logger = logging.getLogger()


# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
    logger.info("Lambda input: " + str(event))

    # Sanitize LLM response
    sanitized_response = sanitize_response(event['invokeModelRawResponse'])

    # Parse LLM response for any rationale
    rationale = parse_rationale(sanitized_response)

    # Construct response fields common to all invocation types
    parsed_response = {
        'promptType': "ORCHESTRATION",
        'orchestrationParsedResponse': {
            'rationale': rationale
        }
    }

    # Check if there is a final answer
    try:
        final_answer, generated_response_parts = parse_answer(sanitized_response)
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

    if final_answer:
        parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'FINISH',
            'agentFinalResponse': {
                'responseText': final_answer
            }
        }

        if generated_response_parts:
            parsed_response['orchestrationParsedResponse']['responseDetails']['agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
            }

        logger.info("Final answer parsed response: " + str(parsed_response))
        return parsed_response

    # Check if there is an ask user
    try:
        ask_user = parse_ask_user(sanitized_response)
        if ask_user:
            parsed_response['orchestrationParsedResponse']['responseDetails'] = {
                'invocationType': 'ASK_USER',
                'agentAskUser': {
                    'responseText': ask_user
                }
            }

            logger.info("Ask user parsed response: " + str(parsed_response))
            return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

    # Check if there is an agent action
    try:
        parsed_response = parse_function_call(sanitized_response, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

    addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
    logger.info(parsed_response)
    return parsed_response

    raise Exception("unrecognized prompt type")


def sanitize_response(text):
    pattern = r"(\\n*)"
    text = re.sub(pattern, r"\n", text)
    return text


def parse_rationale(sanitized_response):
    # Checks for strings that are not required for orchestration
    rationale_matcher = next(
        (pattern.search(sanitized_response) for pattern in RATIONALE_PATTERNS if pattern.search(sanitized_response)),
        None)

    if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()

        # Check if there is a formatted rationale that we can parse from the string
        rationale_value_matcher = next(
            (pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if pattern.search(rationale)), None)
        if rationale_value_matcher:
            return rationale_value_matcher.group(1).strip()

        return rationale

    return None


def parse_answer(sanitized_llm_response):
    if has_generated_response(sanitized_llm_response):
        return parse_generated_response(sanitized_llm_response)

    answer_match = ANSWER_PATTERN.search(sanitized_llm_response)
    if answer_match and is_answer(sanitized_llm_response):
        return answer_match.group(0).strip(), None

    return None, None


def is_answer(llm_response):
    return llm_response.rfind(ANSWER_TAG) > llm_response.rfind(FUNCTION_CALL_TAG)


def parse_generated_response(sanitized_llm_response):
    results = []

    for match in ANSWER_PART_PATTERN.finditer(sanitized_llm_response):
        part = match.group(1).strip()

        text_match = ANSWER_TEXT_PART_PATTERN.search(part)
        if not text_match:
            raise ValueError("Could not parse generated response")

        text = text_match.group(1).strip()
        references = parse_references(sanitized_llm_response, part)
        results.append((text, references))

    final_response = " ".join([r[0] for r in results])

    generated_response_parts = []
    for text, references in results:
        generatedResponsePart = {
            'text': text,
            'references': references
        }
        generated_response_parts.append(generatedResponsePart)

    return final_response, generated_response_parts


def has_generated_response(raw_response):
    return ANSWER_PART_PATTERN.search(raw_response) is not None


def parse_references(raw_response, answer_part):
    references = []
    for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
        reference = match.group(1).strip()
        references.append({'sourceId': reference})
    return references


def parse_ask_user(sanitized_llm_response):
    ask_user_matcher = ASK_USER_FUNCTION_CALL_PATTERN.search(sanitized_llm_response)
    if ask_user_matcher:
        try:
            parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_llm_response)
            params = parameters_matches.group(1).strip()
            ask_user_question_matcher = ASK_USER_TOOL_PARAMETER_PATTERN.search(params)
            if ask_user_question_matcher:
                ask_user_question = ask_user_question_matcher.group(1)
                return ask_user_question
            raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
        except ValueError as ex:
            raise ex
        except Exception as ex:
            raise Exception(ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE)

    return None


def parse_function_call(sanitized_response, parsed_response):
    match = re.search(FUNCTION_CALL_REGEX, sanitized_response)
    if not match:
        raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)

    tool_name_matches = ASK_USER_TOOL_NAME_PATTERN.search(sanitized_response)
    tool_name = tool_name_matches.group(1)
    parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_response)
    params = parameters_matches.group(1).strip()

    action_split = tool_name.split('::')
    verb = action_split[0].strip()
    resource_name = action_split[1].strip()
    function = action_split[2].strip()

    xml_tree = ET.ElementTree(ET.fromstring("<parameters>{}</parameters>".format(params)))
    parameters = {}
    for elem in xml_tree.iter():
        if elem.text:
            parameters[elem.tag] = {'value': elem.text.strip('" ')}

    parsed_response['orchestrationParsedResponse']['responseDetails'] = {}

    # Function calls can either invoke an action group or a knowledge base.
    # Mapping to the correct variable names accordingly
    if resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
        parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'KNOWLEDGE_BASE'
        parsed_response['orchestrationParsedResponse']['responseDetails']['agentKnowledgeBase'] = {
            'searchQuery': parameters['searchQuery'],
            'knowledgeBaseId': resource_name.replace(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, '')
        }

        return parsed_response

    parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'ACTION_GROUP'
    parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
        "verb": verb,
        "actionGroupName": resource_name,
        "apiName": function,
        "actionGroupInput": parameters
    }

    return parsed_response


def addRepromptResponse(parsed_response, error):
    error_message = str(error)
    logger.warn(error_message)

    parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
        'repromptResponse': error_message
    }

import logging
import re
import xml.etree.ElementTree as ET
 
RATIONALE_REGEX_LIST = [
    "(.*?)(<function_calls>)",
    "(.*?)(<answer>)"
]
RATIONALE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_REGEX_LIST]
 
RATIONALE_VALUE_REGEX_LIST = [
    "<thinking>(.*?)(</thinking>)",
    "(.*?)(</thinking>)",
    "(<thinking>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_VALUE_REGEX_LIST]
 
ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)
 
ANSWER_TAG = "<answer>"
FUNCTION_CALL_TAG = "<function_calls>"
 
ASK_USER_FUNCTION_CALL_REGEX = r"<tool_name>user::askuser</tool_name>"
ASK_USER_FUNCTION_CALL_PATTERN = re.compile(ASK_USER_FUNCTION_CALL_REGEX, re.DOTALL)
 
ASK_USER_TOOL_NAME_REGEX = r"<tool_name>((.|\n)*?)</tool_name>"
ASK_USER_TOOL_NAME_PATTERN = re.compile(ASK_USER_TOOL_NAME_REGEX, re.DOTALL)
 
TOOL_PARAMETERS_REGEX = r"<parameters>((.|\n)*?)</parameters>"
TOOL_PARAMETERS_PATTERN = re.compile(TOOL_PARAMETERS_REGEX, re.DOTALL)
 
ASK_USER_TOOL_PARAMETER_REGEX = r"<question>((.|\n)*?)</question>"
ASK_USER_TOOL_PARAMETER_PATTERN = re.compile(ASK_USER_TOOL_PARAMETER_REGEX, re.DOTALL)
 
 
KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"
 
FUNCTION_CALL_REGEX = r"(?<=<function_calls>)(.*)"
 
ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX, re.DOTALL)
 
# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the parameter 'question' for user::askuser function call. Please try again with the correct argument added."
ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls to the askuser function must be: <invoke> <tool_name>user::askuser</tool_name><parameters><question>$QUESTION</question></parameters></invoke>."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls must be: <invoke> <tool_name>$TOOL_NAME</tool_name> <parameters> <$PARAMETER_NAME>$PARAMETER_VALUE</$PARAMETER_NAME>...</parameters></invoke>."
 
logger = logging.getLogger()
 
 
# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
    logger.info("Lambda input: " + str(event))
 
    # Sanitize LLM response
    sanitized_response = sanitize_response(event['invokeModelRawResponse'])
 
    # Parse LLM response for any rationale
    rationale = parse_rationale(sanitized_response)
 
    # Construct response fields common to all invocation types
    parsed_response = {
        'promptType': "ORCHESTRATION",
        'orchestrationParsedResponse': {
            'rationale': rationale
        }
    }
 
    # Check if there is a final answer
    try:
        final_answer, generated_response_parts = parse_answer(sanitized_response)
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    if final_answer:
        parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'FINISH',
            'agentFinalResponse': {
                'responseText': final_answer
            }
        }
 
        if generated_response_parts:
            parsed_response['orchestrationParsedResponse']['responseDetails']['agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
            }
 
        logger.info("Final answer parsed response: " + str(parsed_response))
        return parsed_response
 
    # Check if there is an ask user
    try:
        ask_user = parse_ask_user(sanitized_response)
        if ask_user:
            parsed_response['orchestrationParsedResponse']['responseDetails'] = {
                'invocationType': 'ASK_USER',
                'agentAskUser': {
                    'responseText': ask_user
                }
            }
 
            logger.info("Ask user parsed response: " + str(parsed_response))
            return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    # Check if there is an agent action
    try:
        parsed_response = parse_function_call(sanitized_response, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
    logger.info(parsed_response)
    return parsed_response
 
    raise Exception("unrecognized prompt type")
 
 
def sanitize_response(text):
    pattern = r"(\\n*)"
    text = re.sub(pattern, r"\n", text)
    return text
 
 
def parse_rationale(sanitized_response):
    # Checks for strings that are not required for orchestration
    rationale_matcher = next(
        (pattern.search(sanitized_response) for pattern in RATIONALE_PATTERNS if pattern.search(sanitized_response)),
        None)
 
    if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()
 
        # Check if there is a formatted rationale that we can parse from the string
        rationale_value_matcher = next(
            (pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if pattern.search(rationale)), None)
        if rationale_value_matcher:
            return rationale_value_matcher.group(1).strip()
 
        return rationale
 
    return None
 
 
def parse_answer(sanitized_llm_response):
    if has_generated_response(sanitized_llm_response):
        return parse_generated_response(sanitized_llm_response)
 
    answer_match = ANSWER_PATTERN.search(sanitized_llm_response)
    if answer_match and is_answer(sanitized_llm_response):
        return answer_match.group(0).strip(), None
 
    return None, None
 
 
def is_answer(llm_response):
    return llm_response.rfind(ANSWER_TAG) > llm_response.rfind(FUNCTION_CALL_TAG)
 
 
def parse_generated_response(sanitized_llm_response):
    results = []
 
    for match in ANSWER_PART_PATTERN.finditer(sanitized_llm_response):
        part = match.group(1).strip()
 
        text_match = ANSWER_TEXT_PART_PATTERN.search(part)
        if not text_match:
            raise ValueError("Could not parse generated response")
 
        text = text_match.group(1).strip()
        references = parse_references(sanitized_llm_response, part)
        results.append((text, references))
 
    final_response = " ".join([r[0] for r in results])
 
    generated_response_parts = []
    for text, references in results:
        generatedResponsePart = {
            'text': text,
            'references': references
        }
        generated_response_parts.append(generatedResponsePart)
 
    return final_response, generated_response_parts
 
 
def has_generated_response(raw_response):
    return ANSWER_PART_PATTERN.search(raw_response) is not None
 
 
def parse_references(raw_response, answer_part):
    references = []
    for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
        reference = match.group(1).strip()
        references.append({'sourceId': reference})
    return references
 
 
def parse_ask_user(sanitized_llm_response):
    ask_user_matcher = ASK_USER_FUNCTION_CALL_PATTERN.search(sanitized_llm_response)
    if ask_user_matcher:
        try:
            parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_llm_response)
            params = parameters_matches.group(1).strip()
            ask_user_question_matcher = ASK_USER_TOOL_PARAMETER_PATTERN.search(params)
            if ask_user_question_matcher:
                ask_user_question = ask_user_question_matcher.group(1)
                return ask_user_question
            raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
        except ValueError as ex:
            raise ex
        except Exception as ex:
            raise Exception(ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE)
 
    return None
 
 
def parse_function_call(sanitized_response, parsed_response):
    match = re.search(FUNCTION_CALL_REGEX, sanitized_response)
    if not match:
        raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)
 
    tool_name_matches = ASK_USER_TOOL_NAME_PATTERN.search(sanitized_response)
    tool_name = tool_name_matches.group(1)
    parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_response)
    params = parameters_matches.group(1).strip()
 
    action_split = tool_name.split('::')
    verb = action_split[0].strip()
    resource_name = action_split[1].strip()
    function = action_split[2].strip()
 
    xml_tree = ET.ElementTree(ET.fromstring("<parameters>{}</parameters>".format(params)))
    parameters = {}
    for elem in xml_tree.iter():
        if elem.text:
            parameters[elem.tag] = {'value': elem.text.strip('" ')}
 
    parsed_response['orchestrationParsedResponse']['responseDetails'] = {}
 
    # Function calls can either invoke an action group or a knowledge base.
    # Mapping to the correct variable names accordingly
    if resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
        parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'KNOWLEDGE_BASE'
        parsed_response['orchestrationParsedResponse']['responseDetails']['agentKnowledgeBase'] = {
            'searchQuery': parameters['searchQuery'],
            'knowledgeBaseId': resource_name.replace(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, '')
        }
 
        return parsed_response
 
    parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'ACTION_GROUP'
    parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
        "verb": verb,
        "actionGroupName": resource_name,
        "apiName": function,
        "actionGroupInput": parameters
    }
 
    return parsed_response
 
 
def addRepromptResponse(parsed_response, error):
    error_message = str(error)
    logger.warn(error_message)
 
    parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
        'repromptResponse': error_message
    }

import json
import logging
import re
from collections import defaultdict

RATIONALE_VALUE_REGEX_LIST = [
  "<thinking>(.*?)(</thinking>)",
  "(.*?)(</thinking>)",
  "(<thinking>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in
                            RATIONALE_VALUE_REGEX_LIST]

ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)

ANSWER_TAG = "<answer>"
ASK_USER = "user__askuser"

KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"

ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX,
                                           re.DOTALL)

# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the parameter 'question' for user__askuser function call. Please try again with the correct argument added."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = "The tool name format is incorrect. The format for the tool name must be: 'httpVerb__actionGroupName__apiName."
logger = logging.getLogger()


# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
  logger.setLevel("INFO")
  logger.info("Lambda input: " + str(event))

  # Sanitize LLM response
  response = load_response(event['invokeModelRawResponse'])

  stop_reason = response["stop_reason"]
  content = response["content"]
  content_by_type = get_content_by_type(content)

  # Parse LLM response for any rationale
  rationale = parse_rationale(content_by_type)

  # Construct response fields common to all invocation types
  parsed_response = {
    'promptType': "ORCHESTRATION",
    'orchestrationParsedResponse': {
      'rationale': rationale
    }
  }

  match stop_reason:
    case 'tool_use':
      # Check if there is an ask user
      try:
        ask_user = parse_ask_user(content_by_type)
        if ask_user:
          parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'ASK_USER',
            'agentAskUser': {
              'responseText': ask_user,
              'id': content_by_type['tool_use'][0]['id']
            },

          }

          logger.info("Ask user parsed response: " + str(parsed_response))
          return parsed_response
      except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

      # Check if there is an agent action
      try:
        parsed_response = parse_function_call(content_by_type, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
      except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

    case 'end_turn' | 'stop_sequence':
      # Check if there is a final answer
      try:
        if content_by_type["text"]:
          text_contents = content_by_type["text"]
          for text_content in text_contents:
            final_answer, generated_response_parts = parse_answer(text_content)
            if final_answer:
              parsed_response['orchestrationParsedResponse'][
                'responseDetails'] = {
                'invocationType': 'FINISH',
                'agentFinalResponse': {
                  'responseText': final_answer
                }
              }

            if generated_response_parts:
              parsed_response['orchestrationParsedResponse']['responseDetails'][
                'agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
              }

            logger.info("Final answer parsed response: " + str(parsed_response))
            return parsed_response
      except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
    case _:
      addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
      logger.info(parsed_response)
      return parsed_response


def load_response(text):
  raw_text = r'{}'.format(text)
  json_text = json.loads(raw_text)
  return json_text


def get_content_by_type(content):
  content_by_type = defaultdict(list)
  for content_value in content:
    content_by_type[content_value["type"]].append(content_value)
  return content_by_type


def parse_rationale(content_by_type):
  if "text" in content_by_type:
    rationale = content_by_type["text"][0]["text"]
    if rationale is not None:
      rationale_matcher = next(
          (pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if
           pattern.search(rationale)),
          None)
      if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()
    return rationale
  return None


def parse_answer(response):
  if has_generated_response(response["text"].strip()):
    return parse_generated_response(response)

  answer_match = ANSWER_PATTERN.search(response["text"].strip())
  if answer_match:
    return answer_match.group(0).strip(), None

  return None, None


def parse_generated_response(response):
  results = []

  for match in ANSWER_PART_PATTERN.finditer(response):
    part = match.group(1).strip()

    text_match = ANSWER_TEXT_PART_PATTERN.search(part)
    if not text_match:
      raise ValueError("Could not parse generated response")

    text = text_match.group(1).strip()
    references = parse_references(part)
    results.append((text, references))

  final_response = " ".join([r[0] for r in results])

  generated_response_parts = []
  for text, references in results:
    generatedResponsePart = {
      'text': text,
      'references': references
    }
    generated_response_parts.append(generatedResponsePart)

  return final_response, generated_response_parts


def has_generated_response(raw_response):
  return ANSWER_PART_PATTERN.search(raw_response) is not None


def parse_references(answer_part):
  references = []
  for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
    reference = match.group(1).strip()
    references.append({'sourceId': reference})
  return references


def parse_ask_user(content_by_type):
  try:
    if content_by_type["tool_use"][0]["name"] == ASK_USER:
      ask_user_question = content_by_type["tool_use"][0]["input"]["question"]
      if not ask_user_question:
        raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
      return ask_user_question
  except ValueError as ex:
    raise ex
  return None


def parse_function_call(content_by_type, parsed_response):
  try:
    content = content_by_type["tool_use"][0]
    tool_name = content["name"]

    action_split = tool_name.split('__')
    verb = action_split[0].strip()
    resource_name = action_split[1].strip()
    function = action_split[2].strip()
  except ValueError as ex:
    raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)

  parameters = {}
  for param, value in content["input"].items():
    parameters[param] = {'value': value}

  parsed_response['orchestrationParsedResponse']['responseDetails'] = {}

  # Function calls can either invoke an action group or a knowledge base.
  # Mapping to the correct variable names accordingly
  if resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
    parsed_response['orchestrationParsedResponse']['responseDetails'][
      'invocationType'] = 'KNOWLEDGE_BASE'
    parsed_response['orchestrationParsedResponse']['responseDetails'][
      'agentKnowledgeBase'] = {
      'searchQuery': parameters['searchQuery'],
      'knowledgeBaseId': resource_name.replace(
          KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, ''),
      'id': content["id"]
    }
    return parsed_response
  parsed_response['orchestrationParsedResponse']['responseDetails'][
    'invocationType'] = 'ACTION_GROUP'
  parsed_response['orchestrationParsedResponse']['responseDetails'][
    'actionGroupInvocation'] = {
    "verb": verb,
    "actionGroupName": resource_name,
    "apiName": function,
    "actionGroupInput": parameters,
    "id": content["id"]
  }
  return parsed_response


def addRepromptResponse(parsed_response, error):
  error_message = str(error)
  logger.warn(error_message)

  parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
    'repromptResponse': error_message
  }

import json
import re
import logging
 
 
RATIONALE_REGEX_LIST = [
    "(.*?)(<function_call>)",
    "(.*?)(<answer>)"
]
RATIONALE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_REGEX_LIST]
 
RATIONALE_VALUE_REGEX_LIST = [
    "<scratchpad>(.*?)(</scratchpad>)",
    "(.*?)(</scratchpad>)",
    "(<scratchpad>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_VALUE_REGEX_LIST]
 
ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)
 
ANSWER_TAG = "<answer>"
FUNCTION_CALL_TAG = "<function_call>"
 
ASK_USER_FUNCTION_CALL_REGEX = r"(<function_call>user::askuser)(.*)\)"
ASK_USER_FUNCTION_CALL_PATTERN = re.compile(ASK_USER_FUNCTION_CALL_REGEX, re.DOTALL)
 
ASK_USER_FUNCTION_PARAMETER_REGEX = r"(?<=askuser=\")(.*?)\""  
ASK_USER_FUNCTION_PARAMETER_PATTERN = re.compile(ASK_USER_FUNCTION_PARAMETER_REGEX, re.DOTALL)
 
KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"
 
FUNCTION_CALL_REGEX_API_SCHEMA = r"<function_call>(\w+)::(\w+)::(.+)\((.+)\)"
FUNCTION_CALL_REGEX_FUNCTION_SCHEMA = r"<function_call>(\w+)::(.+)\((.+)\)"
 
ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"  
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX, re.DOTALL)
 
# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the argument askuser for user::askuser function call. Please try again with the correct argument added"
ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls to the askuser function must be: <function_call>user::askuser(askuser=\"$ASK_USER_INPUT\")</function_call>."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = 'The function call format is incorrect. The format for function calls must be: <function_call>$FUNCTION_NAME($FUNCTION_ARGUMENT_NAME=""$FUNCTION_ARGUMENT_NAME"")</function_call>.'
 
logger = logging.getLogger()
logger.setLevel("INFO")
 
# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
    logger.info("Lambda input: " + str(event))
    
    # Sanitize LLM response
    sanitized_response = sanitize_response(event['invokeModelRawResponse'])
    
    # Parse LLM response for any rationale
    rationale = parse_rationale(sanitized_response)
    
    # Construct response fields common to all invocation types
    parsed_response = {
        'promptType': "ORCHESTRATION",
        'orchestrationParsedResponse': {
            'rationale': rationale
        }
    }
    
    # Check if there is a final answer
    try:
        final_answer, generated_response_parts = parse_answer(sanitized_response)
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
        
    if final_answer:
        parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'FINISH',
            'agentFinalResponse': {
                'responseText': final_answer
            }
        }
        
        if generated_response_parts:
            parsed_response['orchestrationParsedResponse']['responseDetails']['agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
            }
       
        logger.info("Final answer parsed response: " + str(parsed_response))
        return parsed_response
    
    # Check if there is an ask user
    try:
        ask_user = parse_ask_user(sanitized_response)
        if ask_user:
            parsed_response['orchestrationParsedResponse']['responseDetails'] = {
                'invocationType': 'ASK_USER',
                'agentAskUser': {
                    'responseText': ask_user
                }
            }
            
            logger.info("Ask user parsed response: " + str(parsed_response))
            return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
        
    # Check if there is an agent action
    try:
        parsed_response = parse_function_call(sanitized_response, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
    logger.info(parsed_response)
    return parsed_response
        
    raise Exception("unrecognized prompt type")
 
def sanitize_response(text):
    pattern = r"(\\n*)"
    text = re.sub(pattern, r"\n", text)
    return text
    
def parse_rationale(sanitized_response):
    # Checks for strings that are not required for orchestration
    rationale_matcher = next((pattern.search(sanitized_response) for pattern in RATIONALE_PATTERNS if pattern.search(sanitized_response)), None)
    
    if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()
        
        # Check if there is a formatted rationale that we can parse from the string
        rationale_value_matcher = next((pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if pattern.search(rationale)), None)
        if rationale_value_matcher:
            return rationale_value_matcher.group(1).strip()
        
        return rationale
    
    return None
    
def parse_answer(sanitized_llm_response):
    if has_generated_response(sanitized_llm_response):
        return parse_generated_response(sanitized_llm_response)
 
    answer_match = ANSWER_PATTERN.search(sanitized_llm_response)
    if answer_match and is_answer(sanitized_llm_response):
        return answer_match.group(0).strip(), None
        
    return None, None
  
def is_answer(llm_response):
    return llm_response.rfind(ANSWER_TAG) > llm_response.rfind(FUNCTION_CALL_TAG)
    
def parse_generated_response(sanitized_llm_response):
    results = []
    
    for match in ANSWER_PART_PATTERN.finditer(sanitized_llm_response):
        part = match.group(1).strip()
        
        text_match = ANSWER_TEXT_PART_PATTERN.search(part)
        if not text_match:
            raise ValueError("Could not parse generated response")
        
        text = text_match.group(1).strip()        
        references = parse_references(sanitized_llm_response, part)
        results.append((text, references))
    
    final_response = " ".join([r[0] for r in results])
    
    generated_response_parts = []
    for text, references in results:
        generatedResponsePart = {
            'text': text, 
            'references': references
        }
        generated_response_parts.append(generatedResponsePart)
        
    return final_response, generated_response_parts
 
    
def has_generated_response(raw_response):
    return ANSWER_PART_PATTERN.search(raw_response) is not None
 
def parse_references(raw_response, answer_part):
    references = []
    for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
        reference = match.group(1).strip()
        references.append({'sourceId': reference})
    return references
    
def parse_ask_user(sanitized_llm_response):
    ask_user_matcher = ASK_USER_FUNCTION_CALL_PATTERN.search(sanitized_llm_response)
    if ask_user_matcher:
        try:
            ask_user = ask_user_matcher.group(2).strip()
            ask_user_question_matcher = ASK_USER_FUNCTION_PARAMETER_PATTERN.search(ask_user)
            if ask_user_question_matcher:
                return ask_user_question_matcher.group(1).strip()
            raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
        except ValueError as ex:
            raise ex
        except Exception as ex:
            raise Exception(ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE)
        
    return None
 
def parse_function_call(sanitized_response, parsed_response):
    match = re.search(FUNCTION_CALL_REGEX_API_SCHEMA, sanitized_response)
    match_function_schema = re.search(FUNCTION_CALL_REGEX_FUNCTION_SCHEMA, sanitized_response)
    if not match and not match_function_schema:
        raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)
 
    if match:
        schema_type = 'API'
        verb, resource_name, function, param_arg = match.group(1), match.group(2), match.group(3), match.group(4)
    else:
        schema_type = 'FUNCTION'
        resource_name, function, param_arg = match_function_schema.group(1), match_function_schema.group(2), match_function_schema.group(3)
    
    parameters = {}
    for arg in param_arg.split(","):
        key, value = arg.split("=")
        parameters[key.strip()] = {'value': value.strip('" ')}
        
    parsed_response['orchestrationParsedResponse']['responseDetails'] = {}
        
    # Function calls can either invoke an action group or a knowledge base.
    # Mapping to the correct variable names accordingly
    if schema_type == 'API' and resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
        parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'KNOWLEDGE_BASE'
        parsed_response['orchestrationParsedResponse']['responseDetails']['agentKnowledgeBase'] = {
            'searchQuery': parameters['searchQuery'],
            'knowledgeBaseId': resource_name.replace(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, '')
        }
        
        return parsed_response
    
    parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'ACTION_GROUP'
    
    if schema_type == 'API':
        parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
            "verb": verb, 
            "actionGroupName": resource_name,
            "apiName": function,
            "actionGroupInput": parameters
        }
    else:
        parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
            "actionGroupName": resource_name,
            "functionName": function,
            "actionGroupInput": parameters
        }
    
    return parsed_response
    
def addRepromptResponse(parsed_response, error):
    error_message = str(error)
    logger.warn(error_message)
    
    parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
        'repromptResponse': error_message
    }

import logging
import re
import xml.etree.ElementTree as ET
 
RATIONALE_REGEX_LIST = [
    "(.*?)(<function_calls>)",
    "(.*?)(<answer>)"
]
RATIONALE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_REGEX_LIST]
 
RATIONALE_VALUE_REGEX_LIST = [
    "<scratchpad>(.*?)(</scratchpad>)",
    "(.*?)(</scratchpad>)",
    "(<scratchpad>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_VALUE_REGEX_LIST]
 
ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)
 
ANSWER_TAG = "<answer>"
FUNCTION_CALL_TAG = "<function_calls>"
 
ASK_USER_FUNCTION_CALL_REGEX = r"<tool_name>user::askuser</tool_name>"
ASK_USER_FUNCTION_CALL_PATTERN = re.compile(ASK_USER_FUNCTION_CALL_REGEX, re.DOTALL)
 
ASK_USER_TOOL_NAME_REGEX = r"<tool_name>((.|\n)*?)</tool_name>"
ASK_USER_TOOL_NAME_PATTERN = re.compile(ASK_USER_TOOL_NAME_REGEX, re.DOTALL)
 
TOOL_PARAMETERS_REGEX = r"<parameters>((.|\n)*?)</parameters>"
TOOL_PARAMETERS_PATTERN = re.compile(TOOL_PARAMETERS_REGEX, re.DOTALL)
 
ASK_USER_TOOL_PARAMETER_REGEX = r"<question>((.|\n)*?)</question>"
ASK_USER_TOOL_PARAMETER_PATTERN = re.compile(ASK_USER_TOOL_PARAMETER_REGEX, re.DOTALL)
 
 
KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"
 
FUNCTION_CALL_REGEX = r"(?<=<function_calls>)(.*)"
 
ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX, re.DOTALL)
 
# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the parameter 'question' for user::askuser function call. Please try again with the correct argument added."
ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls to the askuser function must be: <invoke> <tool_name>user::askuser</tool_name><parameters><question>$QUESTION</question></parameters></invoke>."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls must be: <invoke> <tool_name>$TOOL_NAME</tool_name> <parameters> <$PARAMETER_NAME>$PARAMETER_VALUE</$PARAMETER_NAME>...</parameters></invoke>."
 
logger = logging.getLogger()
logger.setLevel("INFO")
 
# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
    logger.info("Lambda input: " + str(event))
 
    # Sanitize LLM response
    sanitized_response = sanitize_response(event['invokeModelRawResponse'])
 
    # Parse LLM response for any rationale
    rationale = parse_rationale(sanitized_response)
 
    # Construct response fields common to all invocation types
    parsed_response = {
        'promptType': "ORCHESTRATION",
        'orchestrationParsedResponse': {
            'rationale': rationale
        }
    }
 
    # Check if there is a final answer
    try:
        final_answer, generated_response_parts = parse_answer(sanitized_response)
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    if final_answer:
        parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'FINISH',
            'agentFinalResponse': {
                'responseText': final_answer
            }
        }
 
        if generated_response_parts:
            parsed_response['orchestrationParsedResponse']['responseDetails']['agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
            }
 
        logger.info("Final answer parsed response: " + str(parsed_response))
        return parsed_response
 
    # Check if there is an ask user
    try:
        ask_user = parse_ask_user(sanitized_response)
        if ask_user:
            parsed_response['orchestrationParsedResponse']['responseDetails'] = {
                'invocationType': 'ASK_USER',
                'agentAskUser': {
                    'responseText': ask_user
                }
            }
 
            logger.info("Ask user parsed response: " + str(parsed_response))
            return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    # Check if there is an agent action
    try:
        parsed_response = parse_function_call(sanitized_response, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
    logger.info(parsed_response)
    return parsed_response
 
    raise Exception("unrecognized prompt type")
 
 
def sanitize_response(text):
    pattern = r"(\\n*)"
    text = re.sub(pattern, r"\n", text)
    return text
 
 
def parse_rationale(sanitized_response):
    # Checks for strings that are not required for orchestration
    rationale_matcher = next(
        (pattern.search(sanitized_response) for pattern in RATIONALE_PATTERNS if pattern.search(sanitized_response)),
        None)
 
    if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()
 
        # Check if there is a formatted rationale that we can parse from the string
        rationale_value_matcher = next(
            (pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if pattern.search(rationale)), None)
        if rationale_value_matcher:
            return rationale_value_matcher.group(1).strip()
 
        return rationale
 
    return None
 
 
def parse_answer(sanitized_llm_response):
    if has_generated_response(sanitized_llm_response):
        return parse_generated_response(sanitized_llm_response)
 
    answer_match = ANSWER_PATTERN.search(sanitized_llm_response)
    if answer_match and is_answer(sanitized_llm_response):
        return answer_match.group(0).strip(), None
 
    return None, None
 
 
def is_answer(llm_response):
    return llm_response.rfind(ANSWER_TAG) > llm_response.rfind(FUNCTION_CALL_TAG)
 
 
def parse_generated_response(sanitized_llm_response):
    results = []
 
    for match in ANSWER_PART_PATTERN.finditer(sanitized_llm_response):
        part = match.group(1).strip()
 
        text_match = ANSWER_TEXT_PART_PATTERN.search(part)
        if not text_match:
            raise ValueError("Could not parse generated response")
 
        text = text_match.group(1).strip()
        references = parse_references(sanitized_llm_response, part)
        results.append((text, references))
 
    final_response = " ".join([r[0] for r in results])
 
    generated_response_parts = []
    for text, references in results:
        generatedResponsePart = {
            'text': text,
            'references': references
        }
        generated_response_parts.append(generatedResponsePart)
 
    return final_response, generated_response_parts
 
 
def has_generated_response(raw_response):
    return ANSWER_PART_PATTERN.search(raw_response) is not None
 
 
def parse_references(raw_response, answer_part):
    references = []
    for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
        reference = match.group(1).strip()
        references.append({'sourceId': reference})
    return references
 
 
def parse_ask_user(sanitized_llm_response):
    ask_user_matcher = ASK_USER_FUNCTION_CALL_PATTERN.search(sanitized_llm_response)
    if ask_user_matcher:
        try:
            parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_llm_response)
            params = parameters_matches.group(1).strip()
            ask_user_question_matcher = ASK_USER_TOOL_PARAMETER_PATTERN.search(params)
            if ask_user_question_matcher:
                ask_user_question = ask_user_question_matcher.group(1)
                return ask_user_question
            raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
        except ValueError as ex:
            raise ex
        except Exception as ex:
            raise Exception(ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE)
 
    return None
 
 
def parse_function_call(sanitized_response, parsed_response):
    match = re.search(FUNCTION_CALL_REGEX, sanitized_response)
    if not match:
        raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)
 
    tool_name_matches = ASK_USER_TOOL_NAME_PATTERN.search(sanitized_response)
    tool_name = tool_name_matches.group(1)
    parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_response)
    params = parameters_matches.group(1).strip()
 
    action_split = tool_name.split('::')
    schema_type = 'FUNCTION' if len(action_split) == 2 else 'API'
 
    if schema_type == 'API':
        verb = action_split[0].strip()
        resource_name = action_split[1].strip()
        function = action_split[2].strip()
    else:
        resource_name = action_split[0].strip()
        function = action_split[1].strip()
 
    xml_tree = ET.ElementTree(ET.fromstring("<parameters>{}</parameters>".format(params)))
    parameters = {}
    for elem in xml_tree.iter():
        if elem.text:
            parameters[elem.tag] = {'value': elem.text.strip('" ')}
 
    parsed_response['orchestrationParsedResponse']['responseDetails'] = {}
 
    # Function calls can either invoke an action group or a knowledge base.
    # Mapping to the correct variable names accordingly
    if schema_type == 'API' and resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
        parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'KNOWLEDGE_BASE'
        parsed_response['orchestrationParsedResponse']['responseDetails']['agentKnowledgeBase'] = {
            'searchQuery': parameters['searchQuery'],
            'knowledgeBaseId': resource_name.replace(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, '')
        }
 
        return parsed_response
 
    parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'ACTION_GROUP'
    if schema_type == 'API':
        parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
            "verb": verb,
            "actionGroupName": resource_name,
            "apiName": function,
            "actionGroupInput": parameters
        }
    else:
        parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
            "actionGroupName": resource_name,
            "functionName": function,
            "actionGroupInput": parameters
        }
 
    return parsed_response
 
 
def addRepromptResponse(parsed_response, error):
    error_message = str(error)
    logger.warn(error_message)
 
    parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
        'repromptResponse': error_message
    }

import logging
import re
import xml.etree.ElementTree as ET
 
RATIONALE_REGEX_LIST = [
    "(.*?)(<function_calls>)",
    "(.*?)(<answer>)"
]
RATIONALE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_REGEX_LIST]
 
RATIONALE_VALUE_REGEX_LIST = [
    "<thinking>(.*?)(</thinking>)",
    "(.*?)(</thinking>)",
    "(<thinking>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in RATIONALE_VALUE_REGEX_LIST]
 
ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)
 
ANSWER_TAG = "<answer>"
FUNCTION_CALL_TAG = "<function_calls>"
 
ASK_USER_FUNCTION_CALL_REGEX = r"<tool_name>user::askuser</tool_name>"
ASK_USER_FUNCTION_CALL_PATTERN = re.compile(ASK_USER_FUNCTION_CALL_REGEX, re.DOTALL)
 
ASK_USER_TOOL_NAME_REGEX = r"<tool_name>((.|\n)*?)</tool_name>"
ASK_USER_TOOL_NAME_PATTERN = re.compile(ASK_USER_TOOL_NAME_REGEX, re.DOTALL)
 
TOOL_PARAMETERS_REGEX = r"<parameters>((.|\n)*?)</parameters>"
TOOL_PARAMETERS_PATTERN = re.compile(TOOL_PARAMETERS_REGEX, re.DOTALL)
 
ASK_USER_TOOL_PARAMETER_REGEX = r"<question>((.|\n)*?)</question>"
ASK_USER_TOOL_PARAMETER_PATTERN = re.compile(ASK_USER_TOOL_PARAMETER_REGEX, re.DOTALL)
 
 
KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"
 
FUNCTION_CALL_REGEX = r"(?<=<function_calls>)(.*)"
 
ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX, re.DOTALL)
 
# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the parameter 'question' for user::askuser function call. Please try again with the correct argument added."
ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls to the askuser function must be: <invoke> <tool_name>user::askuser</tool_name><parameters><question>$QUESTION</question></parameters></invoke>."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = "The function call format is incorrect. The format for function calls must be: <invoke> <tool_name>$TOOL_NAME</tool_name> <parameters> <$PARAMETER_NAME>$PARAMETER_VALUE</$PARAMETER_NAME>...</parameters></invoke>."
 
logger = logging.getLogger()
 
 
# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
    logger.info("Lambda input: " + str(event))
 
    # Sanitize LLM response
    sanitized_response = sanitize_response(event['invokeModelRawResponse'])
 
    # Parse LLM response for any rationale
    rationale = parse_rationale(sanitized_response)
 
    # Construct response fields common to all invocation types
    parsed_response = {
        'promptType': "ORCHESTRATION",
        'orchestrationParsedResponse': {
            'rationale': rationale
        }
    }
 
    # Check if there is a final answer
    try:
        final_answer, generated_response_parts = parse_answer(sanitized_response)
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    if final_answer:
        parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'FINISH',
            'agentFinalResponse': {
                'responseText': final_answer
            }
        }
 
        if generated_response_parts:
            parsed_response['orchestrationParsedResponse']['responseDetails']['agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
            }
 
        logger.info("Final answer parsed response: " + str(parsed_response))
        return parsed_response
 
    # Check if there is an ask user
    try:
        ask_user = parse_ask_user(sanitized_response)
        if ask_user:
            parsed_response['orchestrationParsedResponse']['responseDetails'] = {
                'invocationType': 'ASK_USER',
                'agentAskUser': {
                    'responseText': ask_user
                }
            }
 
            logger.info("Ask user parsed response: " + str(parsed_response))
            return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    # Check if there is an agent action
    try:
        parsed_response = parse_function_call(sanitized_response, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
    except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
 
    addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
    logger.info(parsed_response)
    return parsed_response
 
    raise Exception("unrecognized prompt type")
 
 
def sanitize_response(text):
    pattern = r"(\\n*)"
    text = re.sub(pattern, r"\n", text)
    return text
 
 
def parse_rationale(sanitized_response):
    # Checks for strings that are not required for orchestration
    rationale_matcher = next(
        (pattern.search(sanitized_response) for pattern in RATIONALE_PATTERNS if pattern.search(sanitized_response)),
        None)
 
    if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()
 
        # Check if there is a formatted rationale that we can parse from the string
        rationale_value_matcher = next(
            (pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if pattern.search(rationale)), None)
        if rationale_value_matcher:
            return rationale_value_matcher.group(1).strip()
 
        return rationale
 
    return None
 
 
def parse_answer(sanitized_llm_response):
    if has_generated_response(sanitized_llm_response):
        return parse_generated_response(sanitized_llm_response)
 
    answer_match = ANSWER_PATTERN.search(sanitized_llm_response)
    if answer_match and is_answer(sanitized_llm_response):
        return answer_match.group(0).strip(), None
 
    return None, None
 
 
def is_answer(llm_response):
    return llm_response.rfind(ANSWER_TAG) > llm_response.rfind(FUNCTION_CALL_TAG)
 
 
def parse_generated_response(sanitized_llm_response):
    results = []
 
    for match in ANSWER_PART_PATTERN.finditer(sanitized_llm_response):
        part = match.group(1).strip()
 
        text_match = ANSWER_TEXT_PART_PATTERN.search(part)
        if not text_match:
            raise ValueError("Could not parse generated response")
 
        text = text_match.group(1).strip()
        references = parse_references(sanitized_llm_response, part)
        results.append((text, references))
 
    final_response = " ".join([r[0] for r in results])
 
    generated_response_parts = []
    for text, references in results:
        generatedResponsePart = {
            'text': text,
            'references': references
        }
        generated_response_parts.append(generatedResponsePart)
 
    return final_response, generated_response_parts
 
 
def has_generated_response(raw_response):
    return ANSWER_PART_PATTERN.search(raw_response) is not None
 
 
def parse_references(raw_response, answer_part):
    references = []
    for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
        reference = match.group(1).strip()
        references.append({'sourceId': reference})
    return references
 
 
def parse_ask_user(sanitized_llm_response):
    ask_user_matcher = ASK_USER_FUNCTION_CALL_PATTERN.search(sanitized_llm_response)
    if ask_user_matcher:
        try:
            parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_llm_response)
            params = parameters_matches.group(1).strip()
            ask_user_question_matcher = ASK_USER_TOOL_PARAMETER_PATTERN.search(params)
            if ask_user_question_matcher:
                ask_user_question = ask_user_question_matcher.group(1)
                return ask_user_question
            raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
        except ValueError as ex:
            raise ex
        except Exception as ex:
            raise Exception(ASK_USER_FUNCTION_CALL_STRUCTURE_REMPROMPT_MESSAGE)
 
    return None
 
 
def parse_function_call(sanitized_response, parsed_response):
    match = re.search(FUNCTION_CALL_REGEX, sanitized_response)
    if not match:
        raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)
 
    tool_name_matches = ASK_USER_TOOL_NAME_PATTERN.search(sanitized_response)
    tool_name = tool_name_matches.group(1)
    parameters_matches = TOOL_PARAMETERS_PATTERN.search(sanitized_response)
    params = parameters_matches.group(1).strip()
 
    action_split = tool_name.split('::')
    schema_type = 'FUNCTION' if len(action_split) == 2 else 'API'
 
    if schema_type == 'API':
        verb = action_split[0].strip()
        resource_name = action_split[1].strip()
        function = action_split[2].strip()
    else:
        resource_name = action_split[0].strip()
        function = action_split[1].strip()
 
    xml_tree = ET.ElementTree(ET.fromstring("<parameters>{}</parameters>".format(params)))
    parameters = {}
    for elem in xml_tree.iter():
        if elem.text:
            parameters[elem.tag] = {'value': elem.text.strip('" ')}
 
    parsed_response['orchestrationParsedResponse']['responseDetails'] = {}
 
    # Function calls can either invoke an action group or a knowledge base.
    # Mapping to the correct variable names accordingly
    if schema_type == 'API' and resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
        parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'KNOWLEDGE_BASE'
        parsed_response['orchestrationParsedResponse']['responseDetails']['agentKnowledgeBase'] = {
            'searchQuery': parameters['searchQuery'],
            'knowledgeBaseId': resource_name.replace(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, '')
        }
 
        return parsed_response
 
    parsed_response['orchestrationParsedResponse']['responseDetails']['invocationType'] = 'ACTION_GROUP'
    if schema_type == 'API':
        parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
            "verb": verb,
            "actionGroupName": resource_name,
            "apiName": function,
            "actionGroupInput": parameters
        }
    else:
        parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
            "actionGroupName": resource_name,
            "functionName": function,
            "actionGroupInput": parameters
        }
 
    return parsed_response
 
 
def addRepromptResponse(parsed_response, error):
    error_message = str(error)
    logger.warn(error_message)
 
    parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
        'repromptResponse': error_message
    }

import json
import logging
import re
from collections import defaultdict

RATIONALE_VALUE_REGEX_LIST = [
  "<thinking>(.*?)(</thinking>)",
  "(.*?)(</thinking>)",
  "(<thinking>)(.*?)"
]
RATIONALE_VALUE_PATTERNS = [re.compile(regex, re.DOTALL) for regex in
                            RATIONALE_VALUE_REGEX_LIST]

ANSWER_REGEX = r"(?<=<answer>)(.*)"
ANSWER_PATTERN = re.compile(ANSWER_REGEX, re.DOTALL)

ANSWER_TAG = "<answer>"
ASK_USER = "user__askuser"

KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX = "x_amz_knowledgebase_"

ANSWER_PART_REGEX = "<answer_part\\s?>(.+?)</answer_part\\s?>"
ANSWER_TEXT_PART_REGEX = "<text\\s?>(.+?)</text\\s?>"
ANSWER_REFERENCE_PART_REGEX = "<source\\s?>(.+?)</source\\s?>"
ANSWER_PART_PATTERN = re.compile(ANSWER_PART_REGEX, re.DOTALL)
ANSWER_TEXT_PART_PATTERN = re.compile(ANSWER_TEXT_PART_REGEX, re.DOTALL)
ANSWER_REFERENCE_PART_PATTERN = re.compile(ANSWER_REFERENCE_PART_REGEX,
                                           re.DOTALL)

# You can provide messages to reprompt the LLM in case the LLM output is not in the expected format
MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE = "Missing the parameter 'question' for user__askuser function call. Please try again with the correct argument added."
FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE = "The tool name format is incorrect. The format for the tool name must be: 'httpVerb__actionGroupName__apiName."
logger = logging.getLogger()


# This parser lambda is an example of how to parse the LLM output for the default orchestration prompt
def lambda_handler(event, context):
  logger.setLevel("INFO")
  logger.info("Lambda input: " + str(event))

  # Sanitize LLM response
  response = load_response(event['invokeModelRawResponse'])

  stop_reason = response["stop_reason"]
  content = response["content"]
  content_by_type = get_content_by_type(content)

  # Parse LLM response for any rationale
  rationale = parse_rationale(content_by_type)

  # Construct response fields common to all invocation types
  parsed_response = {
    'promptType': "ORCHESTRATION",
    'orchestrationParsedResponse': {
      'rationale': rationale
    }
  }

  match stop_reason:
    case 'tool_use':
      # Check if there is an ask user
      try:
        ask_user = parse_ask_user(content_by_type)
        if ask_user:
          parsed_response['orchestrationParsedResponse']['responseDetails'] = {
            'invocationType': 'ASK_USER',
            'agentAskUser': {
              'responseText': ask_user,
              'id': content_by_type['tool_use'][0]['id']
            },

          }

          logger.info("Ask user parsed response: " + str(parsed_response))
          return parsed_response
      except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

      # Check if there is an agent action
      try:
        parsed_response = parse_function_call(content_by_type, parsed_response)
        logger.info("Function call parsed response: " + str(parsed_response))
        return parsed_response
      except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response

    case 'end_turn' | 'stop_sequence':
      # Check if there is a final answer
      try:
        if content_by_type["text"]:
          text_contents = content_by_type["text"]
          for text_content in text_contents:
            final_answer, generated_response_parts = parse_answer(text_content)
            if final_answer:
              parsed_response['orchestrationParsedResponse'][
                'responseDetails'] = {
                'invocationType': 'FINISH',
                'agentFinalResponse': {
                  'responseText': final_answer
                }
              }

            if generated_response_parts:
              parsed_response['orchestrationParsedResponse']['responseDetails'][
                'agentFinalResponse']['citations'] = {
                'generatedResponseParts': generated_response_parts
              }

            logger.info("Final answer parsed response: " + str(parsed_response))
            return parsed_response
      except ValueError as e:
        addRepromptResponse(parsed_response, e)
        return parsed_response
    case _:
      addRepromptResponse(parsed_response, 'Failed to parse the LLM output')
      logger.info(parsed_response)
      return parsed_response


def load_response(text):
  raw_text = r'{}'.format(text)
  json_text = json.loads(raw_text)
  return json_text


def get_content_by_type(content):
  content_by_type = defaultdict(list)
  for content_value in content:
    content_by_type[content_value["type"]].append(content_value)
  return content_by_type


def parse_rationale(content_by_type):
  if "text" in content_by_type:
    rationale = content_by_type["text"][0]["text"]
    if rationale is not None:
      rationale_matcher = next(
          (pattern.search(rationale) for pattern in RATIONALE_VALUE_PATTERNS if
           pattern.search(rationale)),
          None)
      if rationale_matcher:
        rationale = rationale_matcher.group(1).strip()
    return rationale
  return None


def parse_answer(response):
  if has_generated_response(response["text"].strip()):
    return parse_generated_response(response)

  answer_match = ANSWER_PATTERN.search(response["text"].strip())
  if answer_match:
    return answer_match.group(0).strip(), None

  return None, None


def parse_generated_response(response):
  results = []

  for match in ANSWER_PART_PATTERN.finditer(response):
    part = match.group(1).strip()

    text_match = ANSWER_TEXT_PART_PATTERN.search(part)
    if not text_match:
      raise ValueError("Could not parse generated response")

    text = text_match.group(1).strip()
    references = parse_references(part)
    results.append((text, references))

  final_response = " ".join([r[0] for r in results])

  generated_response_parts = []
  for text, references in results:
    generatedResponsePart = {
      'text': text,
      'references': references
    }
    generated_response_parts.append(generatedResponsePart)

  return final_response, generated_response_parts


def has_generated_response(raw_response):
  return ANSWER_PART_PATTERN.search(raw_response) is not None


def parse_references(answer_part):
  references = []
  for match in ANSWER_REFERENCE_PART_PATTERN.finditer(answer_part):
    reference = match.group(1).strip()
    references.append({'sourceId': reference})
  return references


def parse_ask_user(content_by_type):
  try:
    if content_by_type["tool_use"][0]["name"] == ASK_USER:
      ask_user_question = content_by_type["tool_use"][0]["input"]["question"]
      if not ask_user_question:
        raise ValueError(MISSING_API_INPUT_FOR_USER_REPROMPT_MESSAGE)
      return ask_user_question
  except ValueError as ex:
    raise ex
  return None


def parse_function_call(content_by_type, parsed_response):
  try:
    content = content_by_type["tool_use"][0]
    tool_name = content["name"]

    action_split = tool_name.split('__')

    schema_type = 'FUNCTION' if len(action_split) == 2 else 'API'
    if schema_type == 'API':
      verb = action_split[0].strip()
      resource_name = action_split[1].strip()
      function = action_split[2].strip()
    else:
      resource_name = action_split[1].strip()
      function = action_split[2].strip()

  except ValueError as ex:
    raise ValueError(FUNCTION_CALL_STRUCTURE_REPROMPT_MESSAGE)

  parameters = {}
  for param, value in content["input"].items():
    parameters[param] = {'value': value}

  parsed_response['orchestrationParsedResponse']['responseDetails'] = {}

  # Function calls can either invoke an action group or a knowledge base.
  # Mapping to the correct variable names accordingly
  if schema_type == 'API' and resource_name.lower().startswith(KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX):
    parsed_response['orchestrationParsedResponse']['responseDetails'][
      'invocationType'] = 'KNOWLEDGE_BASE'
    parsed_response['orchestrationParsedResponse']['responseDetails'][
      'agentKnowledgeBase'] = {
      'searchQuery': parameters['searchQuery'],
      'knowledgeBaseId': resource_name.replace(
          KNOWLEDGE_STORE_SEARCH_ACTION_PREFIX, ''),
      'id': content["id"]
    }
    return parsed_response
  parsed_response['orchestrationParsedResponse']['responseDetails'][
    'invocationType'] = 'ACTION_GROUP'
  if schema_type == 'API':
    parsed_response['orchestrationParsedResponse']['responseDetails'][
      'actionGroupInvocation'] = {
      "verb": verb,
      "actionGroupName": resource_name,
      "apiName": function,
      "actionGroupInput": parameters,
      "id": content["id"]
    }
  else:
    parsed_response['orchestrationParsedResponse']['responseDetails']['actionGroupInvocation'] = {
      "actionGroupName": resource_name,
      "functionName": function,
      "actionGroupInput": parameters
     }
  return parsed_response


def addRepromptResponse(parsed_response, error):
  error_message = str(error)
  logger.warn(error_message)

  parsed_response['orchestrationParsedResponse']['parsingErrorDetails'] = {
    'repromptResponse': error_message
  }