Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/diazdavilajesus16-stack/IA-LUMINA/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks you through everything you need to get Lumina AI running locally — from cloning the repository to opening your first conversation in the browser. Lumina AI is a Streamlit-based educational chatbot backed by a Keras neural network, and it ships with a pre-trained model so you can start chatting immediately after installation.

​
Prerequisites

  • Python 3.8 or higher
  • pip (comes bundled with Python)
  • A terminal or command prompt
1

Clone the repository

Clone the Lumina AI repository to your local machine.
git clone https://github.com/diazdavilajesus16/IA-LUMINA.git
cd IA-LUMINA
2

Install dependencies

Install all required Python packages from requirements.txt.
pip install -r requirements.txt
The file installs the following packages:
requirements.txt
streamlit>=1.28.0
PyPDF2>=3.0.0
gTTS>=2.3.0
SpeechRecognition>=3.10.0
pydub>=0.25.0
3

Verify model files

Lumina AI ships with a pre-trained model. Before launching, confirm the following files are present in the project root:
FileDescription
chatbot_model.h5Trained Keras neural network
words.pklVocabulary used during training
classes.pklIntent class labels
respuestas.jsonIntent definitions and responses
These files are included in the repository and do not need to be generated for a standard setup.
If any of the model files (chatbot_model.h5, words.pkl, or classes.pkl) are missing, you must train the model before launching. Run:
python training_chatbot.py
Training reads respuestas.json and writes all three model files to the project root. It typically takes one to three minutes.
4

Launch the app

Start the Streamlit server from the project root.
streamlit run Main.py
Streamlit prints a local URL (typically http://localhost:8501) in your terminal.
5

Open your browser and start chatting

Navigate to http://localhost:8501 in your browser. Lumina AI greets you and is ready to help with subjects including mathematics, physics, chemistry, history, literature, and study techniques.Use the sidebar to explore quick actions, load a PDF for context-aware answers, or open the subject panel to dive into a specific topic.
Voice input and text-to-speech features require ffmpeg installed on your system. Without it, the app displays a warning and falls back to text-only mode. See the installation guide for platform-specific ffmpeg instructions.

Build docs developers (and LLMs) love

Get started for freeTalk to us