Skip to content

A RAG + ReAct agentic chat and KML Viewer for investigating LEAPP reports.

Notifications You must be signed in to change notification settings

jacobecontreras/leapp-rag

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LEAPP RAG + Custom ReAct Agent

DISCLAIMER: This tool is a proof-of-concept designed strictly for educational purposes and data location assistance. It is not a substitute for manual data verification or forensic conclusions. All outputs must be verified against the original evidence.

Purpose

This project explores the mechanics of AI agents within a forensic context. Its primary utility is to assist in locating evidence within LEAPP reports.

The system utilizes a RAG (Retrieval-Augmented Generation) architecture combined with a custom ReAct (Reasoning + Acting) Agent to parse and interact with report data.

Privacy & Configuration

All data processing, vector storage, and report viewing is fully local.

The only external data transmission is strictly for LLM reasoning. This is handled via Open Router using a "Bring Your Own Key" (BYOK) model, ensuring the user retains control over the API connection.

Features

  • AI Assistance: A ReAct agent for querying report data.
  • Report Viewer: An embedded viewer for browsing the default HTML reports generated by aLEAPP and iLEAPP.
  • KML Viewer: A map interface using Leaflet.js to visualize .kml location data.

Tech Stack

  • Frontend: Electron (HTML, CSS, JavaScript)
  • Backend: Python FastAPI

About

A RAG + ReAct agentic chat and KML Viewer for investigating LEAPP reports.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published