How to beginner · 3 min read

How to use SimpleDirectoryReader in LlamaIndex

Q: How to use SimpleDirectoryReader in LlamaIndex

Use SimpleDirectoryReader from llama_index to load all documents from a directory into a list of Document objects. Instantiate it with the directory path, then call load_data() to read files for indexing or processing.

Quick answer

Use SimpleDirectoryReader from llama_index to load all documents from a directory into a list of Document objects. Instantiate it with the directory path, then call load_data() to read files for indexing or processing.

PREREQUISITES

Python 3.8+
pip install llama-index>=0.6.0
Basic knowledge of Python file paths

Setup

Install the llama-index package via pip and prepare your environment.

bash

pip install llama-index>=0.6.0

Step by step

Use SimpleDirectoryReader to load documents from a directory and print their contents.

python

from llama_index import SimpleDirectoryReader

# Specify the directory containing your text files
directory_path = './data'

# Initialize the reader
reader = SimpleDirectoryReader(directory_path)

# Load documents from the directory
documents = reader.load_data()

# Print the content of each loaded document
for i, doc in enumerate(documents):
    print(f"Document {i+1} content:\n{doc.get_text()}\n---")

output

Document 1 content:
This is the content of the first document.
---
Document 2 content:
This is the content of the second document.
---

Common variations

Use SimpleDirectoryReader with a file_extractor parameter to customize file parsing.
Combine with llama_index indexes like GPTVectorStoreIndex for retrieval.
Use async loading by running load_data() in an async context if supported.

python

from llama_index import SimpleDirectoryReader

# Custom file extractor example (e.g., only .txt files)
reader = SimpleDirectoryReader(
    './data',
    file_extractor=lambda filename: filename.endswith('.txt')
)
documents = reader.load_data()
print(f"Loaded {len(documents)} text files.")

output

Loaded 3 text files.

Troubleshooting

If no documents load, verify the directory path is correct and contains supported files.
Ensure files are readable text formats; binary or unsupported files will be skipped.
Check for permission errors on the directory or files.

✅

Key Takeaways

Use SimpleDirectoryReader to quickly load all documents from a directory for indexing.
Customize file loading with the file_extractor parameter to filter files by extension or name.
Always verify the directory path and file permissions to avoid empty or failed loads.

Verified 2026-04

Verify ↗