QueryExpansion.py

import os
from dotenv import load_dotenv
from bs4.filter import SoupStrainer
from langchain_community.document_loaders import WebBaseLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
from langchain.prompts import ChatPromptTemplate
from langchain.load import dumps, loads
from operator import itemgetter
from langchain_core.output_parsers import StrOutputParser
from langchain_openai import ChatOpenAI
from helper import get_retriever
load_dotenv()


def get_unique_union(documents: list[list]):
    """ Unique union of retrieved docs """
    # Flatten list of lists, and convert each Document to string
    flattened_docs = [dumps(doc) for sublist in documents for doc in sublist]
    # Get unique documents
    unique_docs = list(set(flattened_docs))
    # Return
    return [loads(doc) for doc in unique_docs]


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

    retrievar = get_retriever(link)

    template = """You are an AI language model assistant. Your task is to generate five 
    different versions of the given user question to retrieve relevant documents from a vector 
    database. By generating multiple perspectives on the user question, your goal is to help
    the user overcome some of the limitations of the distance-based similarity search. 
    Provide these alternative questions separated by newlines. Original question: {question}"""

    prompt_perspectives  = ChatPromptTemplate.from_template(template)

   
    llm = ChatOpenAI(temperature=0)
    generate_queries = (
        prompt_perspectives  |
        llm |
        StrOutputParser() |
        (lambda x: x.split("\n"))
    )

    retrieval_chain = generate_queries | retrievar.map() | get_unique_union
    # docs = retrieval_chain.invoke({"question": question})

    template = """Answer the following question based on this context:

    {context}

    Question: {question}
    """

    prompt = ChatPromptTemplate.from_template(template)

    llm = ChatOpenAI(temperature=0)

    final_rag_chain = (
        {
            "context": retrieval_chain,
            "question": itemgetter("question")
        }
        | prompt
        | llm
        | StrOutputParser()
    )

    response = final_rag_chain.invoke({"question": question})
    return response

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