Logo Lanfrica

LeroyJoel/naija-rights-explainer-

Domain:

natural language processing

Record type:

software
Creator:
Ler
Host:
# Naija Rights Xplainer (CrewAI) ## Overview An AI-powered multi-agent system that explains Nigerian legal/civic rights in plain English and translates them into Hausa, Yoruba, and Igbo. Built with CrewAI. ## Installation Ensure you have Python >=3.10 <3.14 installed on your system. This project uses UV for dependency management and package handling, offering a seamless setup and execution experience. First, if you haven't already, install uv: ```bash pip install uv ``` Next, navigate to your project directory and install the dependencies: (Optional) Lock the dependencies and install them by using the CLI command: ```bash crewai install ``` ### Customizing Add your API keys into the `.env` file (see Environment below). - Modify `src/naija_rights_xplainer/config/agents.yaml` to define your agents - Modify `src/naija_rights_xplainer/config/tasks.yaml` to define your tasks - Modify `src/naija_rights_xplainer/crew.py` to add your own logic, tools and specific args - Modify `src/naija_rights_xplainer/main.py` to add custom inputs for your agents and tasks ## Running the Project (CLI) To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project: ```bash $ crewai run ``` This command initializes the naija_rights_explainer Crew, assembling the agents and assigning them tasks as defined in your configuration. This will create a `report.md` file in the project root containing the explanation and translations. ## Agents (from `config/agents.yaml`) - Legal Rights Explainer (`legal_rights_explainer`) - Role: Simplify Nigerian legal and civic rights - Model: `gemini/gemini-1.5-flash` - Local Language Translator (Hausa) (`translator_local_languages`) - Goal: Translate legal info into Hausa - Model: `huggingface/Helsinki-NLP/opus-mt-en-ha` - Local Language Translator (Yoruba) (`translator_local_languages_yoruba`) - Goal: Translate legal info into Yoruba - Model: `huggingface/Helsinki-NLP/opus-mt-en-yo` - Local Langua …