AIxplora is an open-source personal AI assistant designed to query and interact with any file type, regardless of length or format. It targets users who need to extract information from diverse data sources, offering a flexible and transparent alternative to proprietary solutions. The project aims to provide a powerful, customizable, and privacy-conscious way to leverage AI for file exploration and knowledge management.

How It Works

AIxplora utilizes AI and Large Language Models (LLMs) to process and understand various file formats, including PDFs, audio, and video. It employs a unique summarization approach and interactive file indexing, allowing users to converse directly with their data. Users can opt for official OpenAI/ChatGPT models or integrate open-source models for enhanced privacy, with the flexibility to run everything locally.

Quick Start & Requirements

• Local Setup: Clone the repository, install backend dependencies (pip install -r backend/requirements.txt), install frontend dependencies (npm install in frontend), and launch with python backend/main.py and npm start in frontend.
• Docker Setup: Clone the repository and run docker compose up --build.
• Prerequisites: Python, Node.js, npm.
• Resources: Initial Docker build may be prolonged due to dependency installation.
• Demo: https://github.com/grumpyp/aixplora/assets/75830792/7302684f-2c1f-4849-9f10-c6254be1009d

Highlighted Details

• Universal file integration supporting any format and length.
• Flexible privacy options with support for both proprietary and open-source LLMs.
• Interactive file indexing and conversational data interaction.
• AIxplora-Cloud for seamless knowledge sharing and AIxplora Widget for website integration are planned features.

Maintenance & Community

The project is actively seeking contributions in code, documentation, testing, and feature suggestions. Community engagement is encouraged through GitHub.

Licensing & Compatibility

The repository does not explicitly state a license in the provided README. This requires clarification for commercial use or closed-source linking.

Limitations & Caveats

A Windows version is available, but a Mac version is listed as "coming soon." A known issue with Docker builds may result in an "app exited with code null" message, which is being addressed. The project is presented as a Proof of Concept (PoC), indicating potential for ongoing development and changes.