hatespeech-rag

Final submission of the code for the master's thesis

This release marks the final submission of the code associated with my master's thesis, titled
Künstliche Intelligenz - Bedrohung für liberal demokratische Gesellschaften?.
It includes all the source code, scripts, and necessary documentation required to reproduce the results presented in the thesis.

Key Features:

• Completed Codebase: All functionalities and modules referenced in the thesis are now fully implemented and tested.
• Comprehensive Documentation: Detailed instructions and comments are provided within the code to facilitate understanding and replication of the experiments.
• Final Adjustments: Minor bug fixes and optimizations have been applied to ensure stability and accuracy.
• Data and Results: The release includes sample data sets and the results obtained from running the final code, aligned with the findings discussed in the thesis.

Notes:

• A code freeze is now in effect until the thesis colloquium. No further changes or updates will be made unless specifically requested by the reviewing committee.
• This is the definitive version of the code as submitted for academic evaluation.
• For any queries or additional information, please refer to the documentation or contact me directly.

In this Release there is a new WebApp. I worked on this for a couple of weeks and managed to add this before the deadline.

To use the WebApp you have to do following steps:

1. Running the run.py Script

Navigate to the webapp folder where run.py is located and run the script by executing:

python run.py

This command will start the web application, and you should keep this terminal window open and running while you interact with the web interface.

2. Using the Web Interface

Once the run.py script is running, you can access the web application by opening a web browser and navigating to the appropriate URL, typically http://localhost:5000.

[!NOTE]
To make the WebApp suitable for production (available online), you have to meet all the requirements for a production environment, such as handling large traffic, managing sessions securely, and logging errors appropriately. Please think about a Reverse Proxy, too!

Added a BSD 3-Clause License for the Repository, so you can use this code for free!
See more about the License here

Meta AI released Llama 3.1. In this release I changed everything to Llama 3.1 uncensored (mannix/llama3.1-8b-abliterated) to use the lighter and faster version of the pre-trained llm.