Add LLM Wars demo

Unify/LLM-Wars/.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+.streamlit
+.python-version

Unify/LLM-Wars/README.md

@@ -0,0 +1,60 @@
+# LLM-Wars
+
+## Introduction
+### Overview
+**LLM Wars** is a web application built with Streamlit that sets up a dynamic competition between two Large Language Models (LLMs). The LLMs engage in a structured debate where they challenge each other by generating complex prompts, responding to those prompts, and evaluating the responses. This application demonstrates the natural language capabilities of modern AI models in an interactive competitive environment with visualizations.
+
+### Objective
+The main goal of LLM Wars is to provide a creative and educational platform for testing AI models against each other following predefined rules. It highlights the strengths and limitations of language models while presenting AI capabilities engagingly to users.
+
+### Tech Stack
+- **Streamlit**: Used for creating the web application interface that is intuitive and interactive.
+- **Unify AI**: Provides the backend LLMs that power the interactions within the application. Unify's API is utilized to send prompts to the LLMs and receive their responses in real-time.
+
+### Application Flow
+1. **Initialization**: Users start by selecting two competing LLMs and one judge LLM from a predefined list of available models.
+2. **Competition Cycle**:
+   - **Prompt Suggestion**: LLM1 generates a challenging prompt.
+   - **Response Generation**: LLM2 attempts to respond accurately to the prompt.
+   - **Verification**: LLM1 verifies the correctness of LLM2's response.
+   - **Judgment**: The judge LLM evaluates the interaction. If LLM2's response is deemed incorrect, LLM1 is declared the winner, and the cycle ends. Otherwise, roles are reversed, and the cycle repeats with LLM2 generating the next prompt.
+3. **Visualization**: The application provides a visual representation of the ongoing interaction, scores, and decisions made by the judge LLM.
+
+### Motivation
+LLM Wars demonstrates novel LLM applications beyond common use cases by creating a competitive AI environment. This pushes the boundaries of what language models can creatively and adaptively achieve. It also serves an educational purpose demystifying AI for audiences like students and professionals.
+
+### Key Concepts
+- **Natural Language Understanding and Generation**: At the core of LLM Wars is the ability of LLMs to understand and generate human-like text, showcasing advancements in AI language models.
+- **API Integration**: Demonstrates how to effectively integrate and utilize third-party APIs (Unify AI) within a Python-based application.
+
+## Quick Demo
+https://github.com/leebissessar5/Unify-LLM-Wars/assets/120032434/0a6f60c0-e679-4577-b409-9d5d6df11c9c
+
+## Repository and Deployment
+### Access the Source Code
+The source code for **LLM Wars** is part of a larger collection of demos. You can access the original source code for this specific project [here](https://github.com/leebissessar5/Unify-LLM-Wars).
+
+### Live Application
+A live version of the application is hosted on Streamlit, allowing you to interact with it immediately without the need to set up a local environment. Visit the application at: [LLM Wars on Streamlit](https://unify-llm-wars-tftznesvztdt2bwsqgub3r.streamlit.app/).
+
+### Running Locally
+To run **LLM Wars** locally, clone the repository, then open up a terminal window from this directory (where this README is located) and follow these steps:
+
+1. **Install Dependencies**: Install the required Python libraries using pip:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+2. **Launch the Application**: Finally, start the application by running:
+   ```bash
+   streamlit run main.py
+   ```
+
+This command initiates the Streamlit server, and you should see a URL displayed in your terminal where you can access the app locally, typically at `http://localhost:8501`.
+
+## Contributors
+| Name | GitHub Profile |
+|------|----------------|
+| Lee Bissessar | [leebissessar](https://github.com/leebissessar5) |
+| Glorry Sibomana | [WHITELOTUS0](https://github.com/WHITELOTUS0) |
+| Kato Steven Mubiru | [KatoStevenMubiru](https://github.com/KatoStevenMubiru) |