QueryDecomposition.py

from langchain.prompts import ChatPromptTemplate
from operator import itemgetter
from langchain_core.output_parsers import StrOutputParser
from langchain import hub
from helper import get_llm, get_retriever

def format_qa_pair(question, answer):
    """Format Q and A pair"""
    
    formatted_string = ""
    formatted_string += f"Question: {question}\nAnswer: {answer}\n\n"
    return formatted_string.strip()


def retrieve_and_rag(question,prompt_rag,sub_question_generator_chain, link):
    """RAG on each sub-question"""
    
    # Use our decomposition
    sub_questions = sub_question_generator_chain.invoke({"question":question})
    
    # Initialize a list to hold RAG chain results
    rag_results = []
    retrievar = get_retriever(link)
    llm = get_llm()
    for sub_question in sub_questions:
        
        # Retrieve documents for each sub-question
        retrieved_docs = retrievar.get_relevant_documents(sub_question)
        
        # Use retrieved documents and sub-question in RAG chain
        answer = (prompt_rag | llm | StrOutputParser()).invoke({"context": retrieved_docs, 
                                                                "question": sub_question})
        rag_results.append(answer)
    
    return rag_results,sub_questions

def get_answer_using_query_decomposition(link: str, question: str):

    # Decomposition
    template = """You are a helpful assistant that generates multiple sub-questions related to an input question. \n
    The goal is to break down the input into a set of sub-problems / sub-questions that can be answered in isolation. \n
    Generate multiple search queries related to: {question} \n
    Output (3 queries):"""
    prompt_decomposition = ChatPromptTemplate.from_template(template)
    llm = get_llm()
    generate_queries_decomposition = ( 
        prompt_decomposition |
        llm |
        StrOutputParser() |
        (lambda x: x.split("\n"))
    )
    questions = generate_queries_decomposition.invoke({"question":question})
    template = """Here is the question you need to answer:

    \n --- \n {question} \n --- \n

    Here is any available background question + answer pairs:

    \n --- \n {q_a_pairs} \n --- \n

    Here is additional context relevant to the question: 

    \n --- \n {context} \n --- \n

    Use the above context and any background question + answer pairs to answer the question: \n {question}
    """

    decomposition_prompt = ChatPromptTemplate.from_template(template)

    q_a_pairs = ""
    retrievar = get_retriever(link)
    answer = ""
    prompt_rag = hub.pull("rlm/rag-prompt")
    for q in questions:
        
        rag_chain = (
        {
            "context": itemgetter("question") | retrievar, 
            "question": itemgetter("question"),
            "q_a_pairs": itemgetter("q_a_pairs")
        } 
        | decomposition_prompt
        | llm
        | StrOutputParser()
        )
        
        answer = rag_chain.invoke({"question":q,"q_a_pairs":q_a_pairs})
        q_a_pair = format_qa_pair(q,answer)
        q_a_pairs = q_a_pairs + "\n---\n"+  q_a_pair

    answers, questions = retrieve_and_rag(question, prompt_rag, generate_queries_decomposition, link)

    return answers[0]


# if __name__ == "__main__":
#     link = "https://lilianweng.github.io/posts/2023-06-23-agent/"
#     question = "What is task decomposition for LLM agents?"
#     answer = get_answer(link, question)
#     print(answer)