pip install llama-index-readers-json

from llama_index.readers.json import JSONReader

from llama_index.core import SimpleDirectoryReader
reader = SimpleDirectoryReader(input_dir="path/to/directory")documents = reader.load_data()

...documents = reader.load_data(num_workers=4)

SimpleDirectoryReader(input_dir="path/to/directory", recursive=True)

reader = SimpleDirectoryReader(input_dir="path/to/directory", recursive=True)all_docs = []for docs in reader.iter_data():# <do something with the documents per file>all_docs.extend(docs)

SimpleDirectoryReader(input_files=["path/to/file1", "path/to/file2"])

SimpleDirectoryReader(input_dir="path/to/directory", exclude=["path/to/file1", "path/to/file2"])

SimpleDirectoryReader(input_dir="path/to/directory", required_exts=[".pdf", ".docx"])

SimpleDirectoryReader(input_dir="path/to/directory", num_files_limit=100)

SimpleDirectoryReader(input_dir="path/to/directory", encoding="latin-1")

def get_meta(file_path):return {"foo": "bar", "file_path": file_path}

SimpleDirectoryReader(input_dir="path/to/directory", file_metadata=get_meta)

from llama_index.core import SimpleDirectoryReaderfrom llama_index.core.readers.base import BaseReaderfrom llama_index.core import Document

class MyFileReader(BaseReader):def load_data(self, file, extra_info=None):with open(file, "r") as f:text = f.read()# load_data returns a list of Document objectsreturn [Document(text=text + "Foobar", extra_info=extra_info or {})]

reader = SimpleDirectoryReader(input_dir="./data", file_extractor={".myfile": MyFileReader()})
documents = reader.load_data()

from s3fs import S3FileSystem
s3_fs = S3FileSystem(key="...", secret="...")bucket_name = "my-document-bucket"
reader = SimpleDirectoryReader(input_dir=bucket_name,fs=s3_fs,recursive=True,# recursively searches all subdirectories)
documents = reader.load_data()