import os
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings

with open("./data/data.txt", 'r', encoding='utf-8') as file:
    txt_list = [line.strip() for line in file]

embedding_path = "/data/Z_LLM_data/Embed_data/bge-m3"
embeddings = HuggingFaceEmbeddings(model_name=embedding_path)

faiss_archived = "./data/faiss_data/data"
vectorstore_txt_faiss = FAISS.from_texts(txt_list, embeddings)
vectorstore_txt_faiss.save_local(faiss_archived)

retriever_txt_faiss1 = vectorstore_txt_faiss.as_retriever(search_kwargs={"k":3})
retriever_txt_faiss2 = vectorstore_txt_faiss.as_retriever(
    search_type="mmr",
    search_kwargs={"k": 3,  # 检索结果
                   "fetch_k": 1,  # 候选结果数量
                   "lambda_mult": 0.5}  # 平衡指数，1为相关性；0为多样性
)
retriever_txt_faiss3 = vectorstore_txt_faiss.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"score_threshold": 0.5}
)

def intersection_of_three_lists(input_str):
    list1 = retriever_txt_faiss1.invoke(input_str)
    list2 = retriever_txt_faiss2.invoke(input_str)
    list3 = retriever_txt_faiss3.invoke(input_str)
    
    def _intersection_of_three_lists(retrieval_results):
        return [doc.page_content for doc in retrieval_results]
        
    list11 = _intersection_of_three_lists(list1)
    list22 = _intersection_of_three_lists(list2)
    list33 = _intersection_of_three_lists(list3)
        
    return list(set(list11) & set(list22) & set(list33))