llamaIndex - ✅(Solved) Fix [Feature Request]: iGPT Email Intelligence Tool / Data Loader [1 pull requests, 6 comments, 4 participants]

llamaIndex2026-02-11 13:01:05

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

run-llama/llama_index#20674•Fetched 2026-04-08 00:31:35

View on GitHub

Comments

Participants

Timeline

Reactions

Author

Participants

Timeline (top)

commented ×6mentioned ×4subscribed ×4labeled ×3

Root Cause

Standard RAG approaches break on email because threads are conversational graphs, not flat documents. Chunking individual messages loses the relationships between replies, forwards, and CCs. Metadata (who said what, when, to whom) matters as much as body text, but gets stripped during typical ingestion.

RAW_BUFFERClick to expand / collapse

Feature Description

A tool and/or data loader integration for iGPT, an Email Intelligence API that returns structured, reasoning-ready context from email threads.

Unlike raw email connectors that return unprocessed message data, iGPT handles thread reconstruction, participant role detection, temporal reasoning, and intent extraction. The API returns structured JSON with tasks, owners, decisions, sentiment, deadlines, and citations.

Proposed integration — two possible components:

Tool** (iGPTEmailTool): Wraps recall.ask() and recall.search() endpoints. Agents can query email context and get structured responses in a single call. Data Loader** (iGPTReader): Wraps recall.search() to load email context as LlamaIndex Documents for indexing and retrieval.

API details: Base URL: https://api.igpt.ai/v1 Auth: Bearer token (API key) Key endpoints: recall/ask (reasoning + retrieval), recall/search (retrieval only) Output: Structured JSON with citations Python SDK: pip install igptai — GitHub Docs: https://docs.igpt.ai Github: https://github.com/orgs/igptai/

Reason

There is currently no LlamaIndex integration that handles email context engineering. The existing email-related tools and loaders connect to Gmail or IMAP and return raw message data, which leaves developers to handle thread reconstruction, deduplication, participant tracking, and context assembly themselves.

iGPT solves this preprocessing layer and returns structured, reasoning-ready JSON. A LlamaIndex integration would let developers skip months of email infrastructure work and go straight to building their application.

Value of Feature

Email is the most common business data source (376 billion messages sent daily) but one of the hardest to make useful for AI applications. Developers building RAG apps, AI agents, and workflow automation over email data currently have to build their own parsing, threading, and extraction infrastructure before they can even start on their actual product.

An iGPT integration would give LlamaIndex users a one-call path from raw inbox data to structured outputs (tasks, decisions, owners, sentiment, deadlines) with citations. This is useful for anyone building CRM auto-updates, customer health dashboards, deal risk monitors, support ticket automation, or any application that needs to reason over business communications.

The Python SDK already exists (pip install igptai), so the integration surface is straightforward.

extent analysis

Fix Plan

To integrate iGPT with LlamaIndex, we need to create two components: iGPTEmailTool and iGPTReader. Here are the steps:

iGPTEmailTool

Install the iGPT Python SDK: pip install igptai
Import the SDK and create a client instance with your API key
Implement a function to wrap the recall.ask() and recall.search() endpoints
Use the function to query email context and get structured responses

iGPTReader

Implement a function to wrap the recall.search() endpoint
Use the function to load email context as LlamaIndex Documents for indexing and retrieval

Example Code

import igptai

# Initialize the iGPT client
client = igptai.Client(api_key="YOUR_API_KEY")

# iGPTEmailTool function to query email context
def query_email_context(query):
    response = client.recall.ask(query)
    return response.json()

# iGPTReader function to load email context as LlamaIndex Documents
def load_email_context(query):
    response = client.recall.search(query)
    documents = []
    for result in response.json():
        document = {
            "id": result["id"],
            "text": result["text"],
            "metadata": result["metadata"]
        }
        documents.append(document)
    return documents

Verification

To verify the integration, you can test the query_email_context and load_email_context functions with sample queries. Check that the responses are in the expected format and contain the correct information.

Extra Tips

Make sure to replace YOUR_API_KEY with your actual iGPT API key.
You can customize the query_email_context and load_email_context functions to fit your specific use case.
Consider implementing error handling and logging to ensure that any issues with the integration are properly handled and debugged.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #ssr #installation #tensor shape #autograd error #model compatibility #GPU setup #container setup #orchestration issue

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

llamaIndex - ✅(Solved) Fix [Feature Request]: iGPT Email Intelligence Tool / Data Loader [1 pull requests, 6 comments, 4 participants]

Recommended Tools

GitHub issue graph ai analysis

Root Cause

Fix Action

Fixed

PR fix notes

PR #20727: feat: Add iGPT Email Intelligence tool and reader integrations

Description (problem / solution / changelog)

Description

New Package?

Version Bump?

Type of Change

How Has This Been Tested?

Suggested Checklist

Changed files

Feature Description

Reason

Value of Feature

extent analysis

Fix Plan

Example Code

Verification

Extra Tips

Still need to ship something?

TRENDING

llamaIndex - ✅(Solved) Fix [Feature Request]: iGPT Email Intelligence Tool / Data Loader [1 pull requests, 6 comments, 4 participants]

Recommended Tools

GitHub issue graph ai analysis

Root Cause

Fix Action

Fixed

PR fix notes

PR #20727: feat: Add iGPT Email Intelligence tool and reader integrations

Description (problem / solution / changelog)

Description

New Package?

Version Bump?

Type of Change

How Has This Been Tested?

Suggested Checklist

Changed files

Feature Description

Reason

Value of Feature

extent analysis

Fix Plan

Example Code

Verification

Extra Tips

Still need to ship something?

RELATED_DISCOVERY

TRENDING