使用LlamaIndex載入文檔

from llama_index.core import download_loader
# 載入環境變數
from dotenv import load_dotenv 
load_dotenv()

YoutubeTranscriptReader = download_loader("YoutubeTranscriptReader")

loader = YoutubeTranscriptReader()
youtube_documents = loader.load_data(ytlinks=['https://www.youtube.com/watch?v=nHcbHdgVUJg&ab_channel=WintWealth'])

[Document(id_='nHcbHdgVUJg', embedding=None, metadata={'video_id': 'nHcbHdgVUJg'}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text="I'm a Commerce graduate.......", start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n')]

from pathlib import Path
from llama_index.core import download_loader

PDFReader = download_loader("PDFReader")

loader = PDFReader()

pdf_document = loader.load_data(file=Path('./sample.pdf'))

[Document(id_='c63920fc-1f19-4112-ab6a-d18aa193c037', embedding=None, metadata={'page_label': '1', 'file_name': 'sample.pdf'}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text=' \n \n \n \n \n \nLangChain 技术解密： \n构建大模型应用的全景指南 \n \n \n王浩帆 编著 \n \n \n \n \n \n \n \n \n \n \n \n \n', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), ......]

from llama_index.core import download_loader
import os

NotionPageReader = download_loader('NotionPageReader')

integration_token = "your-notion-token"
database_id = "your-database-id"
reader = NotionPageReader(integration_token=integration_token)
notion_documents = reader.load_data(database_id=database_id)

import os
from llama_index.core import VectorStoreIndex

all_documents = youtube_documents + pdf_document
index = VectorStoreIndex.from_documents(all_documents)

query_engine = index.as_query_engine()
response = query_engine.query("介紹LangChain")
print(response)