i want to build a chatbot trained on custom knowledge base. In the examples there's one us

from llama_index import download_loader, GPTVectorStoreIndex, ServiceContext, StorageContext, load_index_from_storage
from pathlib import Path

years = [2022, 2021, 2020, 2019]
UnstructuredReader = download_loader("UnstructuredReader", refresh_cache=True)

loader = UnstructuredReader()
doc_set = {}
all_docs = []
for year in years:
    year_docs = loader.load_data(file=Path(f'./data/UBER/UBER_{year}.html'), split_documents=False)
    # insert year metadata into each year
    for d in year_docs:
        d.extra_info = {"year": year}
    doc_set[year] = year_docs
    all_docs.extend(year_docs)

from llama_index import download_loader, GPTVectorStoreIndex, ServiceContext, StorageContext, load_index_from_storage
from pathlib import Path

# Replace the UnstructuredReader with SimpleDirectoryReader
from llama_index import SimpleDirectoryReader

# Replace the loader with SimpleDirectoryReader and specify the folder containing your files
loader = SimpleDirectoryReader('./data/your_folder')

# Load the documents
all_docs = loader.load_data()

# Continue with the rest of the example

import nest_asyncio
nest_asyncio.apply()

from llama_index import SimpleDirectoryReader, LLMPredictor, ServiceContext, GPTVectorStoreIndex
from llama_index.response.pprint_utils import pprint_response
from langchain import OpenAI

from llama_index.tools import QueryEngineTool, ToolMetadata
from llama_index.query_engine import SubQuestionQueryEngine

# Configure LLM service
llm_predictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="text-davinci-003", max_tokens=-1, streaming=True))
service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor)

# Load data using SimpleDirectoryReader
lyft_docs = SimpleDirectoryReader(input_files=["../data/10k/lyft_2021.pdf"]).load_data()
uber_docs = SimpleDirectoryReader(input_files=["../data/10k/uber_2021.pdf"]).load_data()

# Build indices
lyft_index = GPTVectorStoreIndex.from_documents(lyft_docs)
uber_index = GPTVectorStoreIndex.from_documents(uber_docs)

# Continue with the rest of the example

from llama_index import download_loader, GPTVectorStoreIndex, ServiceContext, StorageContext, load_index_from_storage
from pathlib import Path

year = 2021  # Choose the year you want to load
UnstructuredReader = download_loader("UnstructuredReader", refresh_cache=True)

loader = UnstructuredReader()
year_docs = loader.load_data(file=Path(f'./data/UBER/UBER_{year}.html'), split_documents=False)

# Insert year metadata into each document
for d in year_docs:
    d.extra_info = {"year": year}

all_docs = year_docs