Ghost Hunting AI - Service
- other
We build an interactive city tour with RAG,LLM,MCP for KdG -The Lab. This is the backend
About
What is Ghost Hunting AI - Service?
Ghost Hunting AI - Service is a backend application that uses LLM, RAG, and MCP to generate a guided tour with puzzles for each location, based on text files you provide. It runs on Python and is separate from its frontend counterpart.
How to use Ghost Hunting AI - Service?
Run the service with python main.py after installing dependencies (pip install -r requirements.txt) and setting up a log directory. You must also create a credentials directory containing a .env file with your GOOGLE_DRIVE_FOLDER_ID and OPENROUTER_API_KEY.
Key features of Ghost Hunting AI - Service
- Generates location-specific guided tours with puzzles
- Uses LLM, RAG, and MCP technologies
- Works with your own text files as input
- Integrates with Google Drive for data storage
- Requires only an OpenRouter API key for LLM access
Use cases of Ghost Hunting AI - Service
- Creating interactive, puzzle-filled tours for any location based on user-supplied text files
- Building custom educational or entertainment experiences from personal documents
FAQ from Ghost Hunting AI - Service
What does Ghost Hunting AI - Service do?
It takes text files you provide and generates a guided tour with puzzles tailored to each location mentioned in those files, using LLM, RAG, and MCP.
What are the system requirements to run this service?
You need Python 3.8 or higher, a log directory, a .env file with a Google Drive folder ID and an OpenRouter API key, and the dependencies listed in requirements.txt.
How do I install the necessary dependencies?
Run pip install -r requirements.txt in the project root after ensuring Python is installed.
Does Ghost Hunting AI - Service include a frontend?
No, the frontend is a separate repository (KAFRMA-Frontend) available on GitHub. This service is the backend component.
What API key is needed, and where do I get it?
You need an OpenRouter API key. The service does not specify how to obtain it, but OpenRouter provides API access to various LLMs.
Details
- Author
- maurostyleman
- Category
- other
- Repository
- maurostyleman/kafrma-backend
Ghost Hunting AI - Service
We have developed a service using LLM, RAG, and MCP that generates a guided tour with puzzles for each location, based on your own text files.
Frontend
Link to the frontend repository: KAFRMA-FrontendTeam
- Kacper Chrolowski - LinkedIn - Frans Dillen - LinkedIn - Mauro Styleman - LinkedInUsage
python main.py
Setup Requirements
Logs
You need to create a log directory in the root of the project.
MCP
Create a new directory named credentials in the root of the project.
Inside this directory, create a .env file containing the following variables:
GOOGLE_DRIVE_FOLDER_ID: Specifies the folder where all data passed to the RAG is stored.
OPENROUTER_API_KEY: Stores your LLM API key.
Additional Requirements
Ensure you have Python installed (recommended version: 3.8 or higher).
Install the required dependencies using:
pip install -r requirements.txt
Make sure your API keys are valid and have the necessary permissions.
Verify that your Google Drive folder contains the correct data before running the service.
Ensure these steps are completed to enable the service to function correctly.
