Overview

P.I.T.O. - Multimodal Product Intelligence & Troubleshooting Orchestrator

🖥 Interface Preview

🎯 Project Purpose

P.I.T.O. (Product Intelligence & Troubleshooting Orchestrator) is a next-generation Enterprise RAG (Retrieval-Augmented Generation) system. Its primary purpose is to bridge the gap between complex technical documentation and real-world troubleshooting.

Instead of searching through 100+ page manuals, users can simply upload a photo of a broken part or error code, and the system will perform high-precision "Cross-Modal Retrieval"—finding the exact page, diagram, or text description needed to fix the issue.

🚀 Key Features

1. Multimodal Core (Text + Vision)

• VLM Descriptions: Automatically generates detailed technical descriptions for every diagram, chart, and photo found in your PDF manuals using Gemini 3 Flash.
• Visual Similarity: Compare user-uploaded photos against indexed engineering blueprints side-by-side.

2. Hybrid Reasoning Engine (Cloud & Local)

• Cloud Precision: Integrates Gemini 3 Pro and OpenAI GPT-5.2 for complex reasoning across vast datasets.
• Local Privacy: Support for Gemma 3 (4B/27B) via Ollama for private, on-device technical support.

3. Linguistics Orchestration

• Global Support: Instantly troubleshoot in Arabic, French, Spanish, Russian, Chinese, and more. The AI automatically translates technical manuals into your preferred language in real-time.

4. Self-Healing Intelligence

• Zero-Config Deployment: Built-in logic that detects and installs missing enterprise requirements automatically. No manual pip commands required for the end-user.

📖 How to Use (Client Guide)

Step 1: Initial Setup & Launch

1. One-Click Launch: Double-click the run_pito.bat file.
2. Auto-Configuration: On the first run, P.I.T.O. will automatically detect and synchronize its environment. It may take a few moments to initialize the mission-critical modules.
3. Credentials: Once the GUI appears, open the sidebar and enter your Gemini or OpenAI API Keys. Click "Update All Credentials".

Step 2: Indexing Knowledge

1. Place your product PDF manuals and images inside the Product_Manuals folder.
2. Click the "Index Knowledge Base" button.
   • Backend Logic: The system will scan every page, extract images, describe them using AI, and store them in the ChromaDB vector database.

Step 3: Troubleshooting

1. Text Query: Type a question like "How do I fix the blinking red light?"
2. Visual Query: Click "📷 UPLOAD PHOTO" to select a picture of the issue.
3. Analyze: Press "ANALYZE".
   • The system will search the manual for matching diagrams.
   • The "MULTIMODAL EVIDENCE" panel will show you the exact reference diagram from the manual side-by-side with your photo.

🛠 Advanced Controls (System Menu)

• File: Export your troubleshooting session as JSON or PDF Intel for corporate reporting.
• Aesthetics: Switch between Cyber-Dark and Arctic-Light themes; customize accent colors.
• Linguistics: Change the AI's output language on the fly.
• Typography: Scale the interface for high-resolution displays or accessibility needs.

👤 Developer & Architect

HSINI MOHAMED
Enterprise Systems Architect

For system integration, custom RAG deployments, or technical support: * WhatsApp: +212 658 029 773 * Email: [email protected] * GitHub: @hsinimoahmed * LinkedIn: Moahmed Hsini

Generated by P.I.T.O. v3.0 - Unrestricted Enterprise Intelligence

🚀 Quick Installation & Setup Guide

To run this project locally, follow these simple steps designed for both developers and users with no prior programming experience.

1. Download Python: Make sure you have Python 3.10+ installed on your computer. Download it from the official Python Website. During installation, make sure to check the box "Add Python to PATH".
2. Extract / Setup Code: Open the terminal (Command Prompt on Windows) and navigate to the project directory, or download/extract the project files.
3. Install Dependencies (pip): In Command Prompt, run the following command to install all necessary packages automatically:

   pip install -r requirements.txt

4. Setup API Keys / Environment: Open the .env file in a text editor (like Notepad) and paste your API keys:

   GEMINI_API_KEY=your_gemini_api_key_here

5. Launch the Application: Double-click the run_project.bat or run_pito.bat file, or run the following command:

   python app.py

   (or app_gui.py)