data_connectors

# LlamaIndex 数据连接器指南 通过 LlamaHub 提供 300+ 数据连接器。 ## 内置加载器 ### SimpleDirectoryReader python from llama_index.core import SimpleDirectoryReader # 加载所有文件 documents = SimpleDirectoryReader("./data").load_data() # 按扩展名过滤 documents = SimpleDirectoryReader( "./data", required_exts=[".pdf", ".docx", ".txt"] ).load_data() # 递归加载 documents = SimpleDirectoryReader("./data", recursive=True).load_data() ### 网页 python from llama_index.readers.web import SimpleWebPageReader, BeautifulSoupWebReader # 简单加载器 reader = SimpleWebPageReader() documents = reader.load_data(["https://example.com"]) # 高级加载器 (BeautifulSoup) reader = BeautifulSoupWebReader() documents = reader.load_data(urls=[ "https://docs.python.org", "https://numpy.org" ]) ### PDF python from llama_index.readers.file import PDFReader reader = PDFReader() documents = reader.load_data("paper.pdf") ### GitHub python from llama_index.readers.github import GithubRepositoryReader reader = GithubRepositoryReader( owner="facebook", repo="react", filter_file_extensions=[".js", ".jsx"], verbose=True ) documents = reader.load_data(branch="main") ## LlamaHub 连接器 访问 https://llamahub.ai 获取 300+ 连接器： - Notion, Google Docs, Confluence - Slack, Discord, Twitter - PostgreSQL, MongoDB, MySQL - S3, GCS, Azure Blob - Stripe, Shopify, Salesforce ### 从 LlamaHub 安装 bash pip install llama-index-readers-notion python from llama_index.readers.notion import NotionPageReader reader = NotionPageReader(integration_token="your-token") documents = reader.load_data(page_ids=["page-id"]) ## 自定义加载器 python from llama_index.core.readers.base import BaseReader from llama_index.core import Document class CustomReader(BaseReader): def load_data(self, file_path: str): # 您的自定义加载逻辑 with open(file_path) as f: text = f.read() return [Document(text=text, metadata={"source": file_path})] reader = CustomReader() documents = reader.load_data("data.txt") ## 资源 - **LlamaHub**: https://llamahub.ai - **数据连接器文档**: https://developers.llamaindex.ai/python/framework/modules/data_connectors/