Integrate iGPT Email Intelligence with LlamaIndex
Load reasoning-ready email context from the iGPT API into LlamaIndex documents.
Why it matters
Streamline your email data processing by integrating iGPT's advanced email intelligence with LlamaIndex. This asset transforms raw email threads into structured, reasoning-ready documents for efficient RAG pipelines.
Outcomes
What it gets done
Connect to the iGPT API for email data extraction.
Reconstruct email threads and detect participant roles.
Extract intent and clean email content for RAG.
Load processed email data as LlamaIndex Documents.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-igpt-email | bash Overview
LlamaIndex Readers Integration: iGPT Email Intelligence
A LlamaIndex reader that loads structured email context from the iGPT API, with thread reconstruction and intent extraction already done. Use for RAG over email data when you want reasoning-ready structured context rather than raw messages.
What it does
The iGPT Email Intelligence Reader loads structured, reasoning-ready email context from the iGPT API as LlamaIndex Documents, for indexing and retrieval. Unlike raw email connectors that hand back unprocessed message data, iGPT does thread reconstruction, participant role detection, and intent extraction before returning results, so each Document already contains clean, structured content ready for a RAG pipeline instead of raw message dumps the developer would have to parse themselves.
IGPTEmailReader is initialized with an API key and a user identifier, and load_data accepts a natural-language query plus a date_from filter to scope which email context is fetched and turned into documents.
When to use - and when NOT to
Use it when you want to build retrieval or question-answering over a user's email history without writing your own thread-reconstruction and intent-extraction logic on top of a raw email API - the iGPT API does that preprocessing for you. Do not use it expecting raw, unprocessed message bodies; the whole point of this reader is that it hands back already-structured, reasoning-ready content rather than a literal mailbox dump.
Capabilities
load_data fetches structured email context for a query and date range from the iGPT API and returns it as LlamaIndex Document objects, with thread reconstruction, participant roles, and intent already extracted.
How to install
pip install llama-index-readers-igpt-email
Requires an iGPT API key obtained from docs.igpt.ai.
Who it's for
Developers building RAG pipelines over email data who want pre-structured, reasoning-ready context instead of raw messages to parse themselves.
Source README
LlamaIndex Readers Integration: iGPT Email Intelligence
pip install llama-index-readers-igpt-email
The iGPT Email Intelligence Reader loads structured, reasoning-ready email
context from the iGPT API as LlamaIndex Documents for indexing and retrieval.
Unlike raw email connectors that return unprocessed message data, iGPT handles
thread reconstruction, participant role detection, and intent extraction before
returning results - so each Document contains clean, structured content ready
for a RAG pipeline.
To begin, you need to obtain an API key at docs.igpt.ai.
Usage
Here's an example usage of the IGPTEmailReader.
from llama_index.readers.igpt_email import IGPTEmailReader
from llama_index.core import VectorStoreIndex
reader = IGPTEmailReader(api_key="your-key", user="user-id")
documents = reader.load_data(query="project Alpha", date_from="2025-01-01")
index = VectorStoreIndex.from_documents(documents)
This loader is designed to be used as a way to load data into LlamaIndex.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.