How to use the pathlib.os.getcwd function in pathlib

def convert_to_tsv(relation_df):
    """Converts the Dataframe to tsv for PBG to read.
    each row is in the triplet format that defines one edge/relationship in the graph
    columns: start,label,end
        - start: id of the 'from' node
        - end: id of the 'to' node
        - label: type of the relationship
    
    Arguments:
        relation_df {[Dataframe]} -- Dataframe in above mentioned format
    """
    try:
        tsv_path = os.path.join(
            os.getcwd(),
            GLOBAL_CONFIG["PROJECT_NAME"],
            GLOBAL_CONFIG["DATA_DIRECTORY"],
            GLOBAL_CONFIG["TSV_FILE_NAME"] + ".tsv",
        )  # default myproject/data/graph.tsv
        logging.info(f"WRITING TSV FILE TO {tsv_path}")
        relation_df[["start", "label", "end"]].to_csv(
            tsv_path, sep="\t", header=False, index=False
        )
    except Exception as e:
        logging.info("error in converting to tsv")
        logging.info(e, exc_info=True)
        sys.exit(e)

for version in versions
        ]  # embedding filenames stored are in format : embeddings_0_0.json for number of partitions
        edge_filenames = [
            f"graph_partitioned/edges{p}_{p1}.h5"
            for p in partitions
            for p1 in partitions
        ]  # edge files are stored are in format : edges_0_0.json for number of partitions
        meta_dict = dict(
            entities=entities,
            partitions=GLOBAL_CONFIG["NUM_PARTITIONS"],
            entity_files=entity_filenames,
            embedding_files=embedding_filenames,
            edge_files=edge_filenames,
        )  # metadata for all these files
        metadata_path = os.path.join(
            os.getcwd(), GLOBAL_CONFIG["PROJECT_NAME"], "metadata.json"
        )  # save to myproject/metadata.json
        with open(metadata_path, "w") as f:
            json.dump(meta_dict, f)
        f.close()
    except Exception as e:
        logging.info("""error in exporting meta data. """)
        logging.info(e, exc_info=True)

def similarity_search(entity_id):
    try:
        from embeoj.utils import load_config

        global GLOBAL_CONFIG, DATA_DIRECTORY, CHECKPOINT_DIRECTORY
        GLOBAL_CONFIG = load_config("GLOBAL_CONFIG")
        DATA_DIRECTORY = os.path.join(
            os.getcwd(), GLOBAL_CONFIG["PROJECT_NAME"], GLOBAL_CONFIG["DATA_DIRECTORY"]
        )
        CHECKPOINT_DIRECTORY = os.path.join(
            os.getcwd(),
            GLOBAL_CONFIG["PROJECT_NAME"],
            GLOBAL_CONFIG["CHECKPOINT_DIRECTORY"],
        )

        create_indexes()  # create indexes if not present
        entity_details = find_entity_data(entity_id)
        entity_type = entity_details["entity_type"]
        partition_number = entity_details["partition_number"]
        # find index of entity id
        query_index = entity_details["entity_index"]
        search_result, entity_file_list, neighbors = search_all(
            entity_type, partition_number, query_index
        )

def initialise_config():
    from embeoj.utils import load_config

    global GLOBAL_CONFIG
    global DATA_DIRECTORY
    global CHECKPOINT_DIRECTORY
    global FILENAMES
    GLOBAL_CONFIG = load_config("GLOBAL_CONFIG")

    FILENAMES = {
        "train": os.path.join(
            os.getcwd(),
            GLOBAL_CONFIG["PROJECT_NAME"],
            GLOBAL_CONFIG["DATA_DIRECTORY"],
            GLOBAL_CONFIG["TSV_FILE_NAME"] + ".tsv",
        )
    }  # path to tsv file with train data
    DATA_DIRECTORY = os.path.join(
        os.getcwd(), GLOBAL_CONFIG["PROJECT_NAME"], GLOBAL_CONFIG["DATA_DIRECTORY"]
    )

    CHECKPOINT_DIRECTORY = os.path.join(
        os.getcwd(),
        GLOBAL_CONFIG["PROJECT_NAME"],
        GLOBAL_CONFIG["CHECKPOINT_DIRECTORY"],
    )

def initialise_config():
    from embeoj.utils import load_config

    global SIMILARITY_SEARCH_CONFIG
    global GLOBAL_CONFIG
    global DATA_DIRECTORY
    global CHECKPOINT_DIRECTORY
    global FAISS_INDEX_NAME
    global EMBEDDING_DIMENSIONS
    global NUM_CLUSTER
    global neighbors

    SIMILARITY_SEARCH_CONFIG = load_config("SIMILARITY_SEARCH_CONFIG")
    GLOBAL_CONFIG = load_config("GLOBAL_CONFIG")
    DATA_DIRECTORY = os.path.join(
        os.getcwd(), GLOBAL_CONFIG["PROJECT_NAME"], GLOBAL_CONFIG["DATA_DIRECTORY"]
    )
    CHECKPOINT_DIRECTORY = os.path.join(
        os.getcwd(),
        GLOBAL_CONFIG["PROJECT_NAME"],
        GLOBAL_CONFIG["CHECKPOINT_DIRECTORY"],
    )
    FAISS_INDEX_NAME = SIMILARITY_SEARCH_CONFIG["FAISS_INDEX_NAME"]
    EMBEDDING_DIMENSIONS = GLOBAL_CONFIG["EMBEDDING_DIMENSIONS"]
    NUM_CLUSTER = SIMILARITY_SEARCH_CONFIG["NUM_CLUSTER"]
    neighbors = SIMILARITY_SEARCH_CONFIG["NEAREST_NEIGHBORS"] + 1

def initialise_config():
    from embeoj.utils import load_config

    global GLOBAL_CONFIG
    global json_path
    GLOBAL_CONFIG = load_config("GLOBAL_CONFIG")
    json_path = os.path.join(
        os.getcwd(),
        GLOBAL_CONFIG["PROJECT_NAME"],
        GLOBAL_CONFIG["DATA_DIRECTORY"],
        GLOBAL_CONFIG["JSON_EXPORT_FILE"] + ".json",
    )  # path to the json dump of the graph db

global GLOBAL_CONFIG
    global DATA_DIRECTORY
    global CHECKPOINT_DIRECTORY
    global FILENAMES
    GLOBAL_CONFIG = load_config("GLOBAL_CONFIG")

    FILENAMES = {
        "train": os.path.join(
            os.getcwd(),
            GLOBAL_CONFIG["PROJECT_NAME"],
            GLOBAL_CONFIG["DATA_DIRECTORY"],
            GLOBAL_CONFIG["TSV_FILE_NAME"] + ".tsv",
        )
    }  # path to tsv file with train data
    DATA_DIRECTORY = os.path.join(
        os.getcwd(), GLOBAL_CONFIG["PROJECT_NAME"], GLOBAL_CONFIG["DATA_DIRECTORY"]
    )

    CHECKPOINT_DIRECTORY = os.path.join(
        os.getcwd(),
        GLOBAL_CONFIG["PROJECT_NAME"],
        GLOBAL_CONFIG["CHECKPOINT_DIRECTORY"],
    )