Extract and index email messages from mbox mailbox files
LlamaIndex reader that extracts emails from mbox mailbox files into documents.
Why it matters
Parse and load email messages stored in mbox format mailbox files into a searchable document index for retrieval-augmented generation, knowledge management, or email analysis workflows.
Outcomes
What it gets done
Read mbox mailbox files from a specified input directory
Extract individual email messages from the mbox format
Convert emails into structured documents for indexing
Load parsed email data into LlamaIndex or LangChain pipelines
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-mbox | bash Overview
LlamaIndex Readers Integration: Mbox
Mbox Reader extracts email messages from mbox (mailbox) format files into LlamaIndex documents, given a directory containing the mbox files. Use it when you need an mbox email archive loaded into LlamaIndex documents. It reads existing mbox files, not a live email account.
What it does
Mbox Reader reads mbox (mailbox) files -- a common format for storing email messages -- and extracts the emails into documents. You point it at a directory of mbox files with load_data(input_dir=...).
When to use - and when NOT to
Use it when you need to load email messages stored in mbox format into LlamaIndex documents, for example indexing an email archive for search or analysis. It reads existing mbox files rather than connecting live to an email account, so it is not a fit if your email lives only in a live inbox with no mbox export.
Inputs and outputs
Install with:
pip install llama-index-readers-mbox
Point it at a directory containing mbox files:
from llama_index.readers.mbox import MboxReader
reader = MboxReader()
documents = reader.load_data(input_dir="<Input Directory>")
load_data takes an input_dir and returns each email in the mbox files found there as a document.
Who it's for
Developers building LlamaIndex or LangChain pipelines that need email archives exported in mbox format loaded as documents.
Source README
LlamaIndex Readers Integration: Mbox
Overview
Mbox Reader is a simple reader for mbox (mailbox) files, commonly used for storing email messages. It reads a set of emails saved in the mbox format and extracts them into documents.
Installation
You can install Mbox Reader via pip:
pip install llama-index-readers-mbox
Usage
from llama_index.readers.mbox import MboxReader
### Initialize MboxReader
reader = MboxReader()
### Load data from mbox files in the input directory
documents = reader.load_data(input_dir="<Input Directory>")
This loader is designed to be used as a way to load data into
LlamaIndex and/or subsequently
used as a Tool in a LangChain Agent.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.