Finding Data Connectors

Data connectors (also called Readers) load data from external sources into LlamaIndex Document objects. Beyond the built-in SimpleDirectoryReader, every connector is published as its own package so you only install what you need.

Finding a connector

• Browse the readers directory of the LlamaIndex repo. Each package has a README with installation and usage instructions.
• Search PyPI for llama-index-readers-. Package names follow the pattern llama-index-readers-<source>, for example llama-index-readers-google or llama-index-readers-database.
• The same layout holds for other integration types: agent tools live under tools, LLMs under llms, embeddings under embeddings, and so on. See the integrations overview for the full picture.

Usage Pattern

Install the package, then import the reader from the matching namespace:

pip install llama-index-readers-google

from llama_index.readers.google import GoogleDocsReader

loader = GoogleDocsReader()
documents = loader.load_data(document_ids=[...])

Built-in connector: SimpleDirectoryReader

SimpleDirectoryReader can parse a wide range of file types including .md, .pdf, .jpg, .png, .docx, as well as audio and video types. It is available directly as part of LlamaIndex:

from llama_index.core import SimpleDirectoryReader

documents = SimpleDirectoryReader("./data").load_data()

Popular connectors

A few of the hundreds available:

• Notion (NotionPageReader, llama-index-readers-notion)
• Google Docs (GoogleDocsReader, llama-index-readers-google)
• Slack (SlackReader, llama-index-readers-slack)
• Discord (DiscordReader, llama-index-readers-discord)
• Apify Actors (ApifyActor, llama-index-readers-apify). Can crawl the web, scrape webpages, extract text content, download files including .pdf, .jpg, .png, .docx, etc.

See the data connectors module guide for more details.