ML Guide is a multi-LLM agent system designed to assist users with their machine learning problems. This project was developed during a 17-hour hackathon at the AI National Summit (AINS) event on June 9, 2024.
(Drive Link to video):
- Exploratory Data Analysis (EDA): Automatically performs an initial EDA using Sweetviz to give users insights into their dataset.
- Research Paper Extraction: Extracts relevant research papers from arXiv to provide users with the latest developments in the field.
- Web Scraping for Similar Problems: Uses JiraAI Reader and Serper API to search the web for similar machine learning problems and solutions.
- Model Code Generation: Generates code for the best machine learning model tailored to the user's problem using multi-LLM agents managed by CrewAI.
![]() |
![]() |
![]() |
![]() |
- CrewAI: This platform is used for orchestrating multiple AI agents to work together efficiently, providing the backbone for managing and integrating different AI models to solve complex problems .
- arXiv: A repository of electronic preprints (known as e-prints) approved for publication after moderation, but not peer-reviewed. It provides access to the latest research papers in the field of machine learning and other scientific areas .
- JinaAI: This tool is used for neural search, enabling efficient and effective search capabilities across different data types, which is essential for finding relevant information and solutions related to the user's problem .
- Sweetviz: An open-source Python library that generates beautiful, high-density visualizations of a pandas DataFrame, aiding in performing exploratory data analysis (EDA) to give users insights into their dataset .
To get started with ML Guide, follow these steps:
-
Clone the repository:
git clone https://github.com/achrefbenammar404/AINS-ML.Guide.git cd AINS-ML.Guide
-
Set up a virtual environment (optional but recommended):
python3 -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate`
-
Install the required packages:
pip install -r requirements.txt
-
Set up environment variables: Create a
.env
file in the root directory and add the following variables:GROQ_API_KEY = "your_Groq_api_key_here" JINA_API_KEY = "your_jina_api_key_here"
To run the ML Guide application, execute the following command:
streamlit run src/app.py
This will start the Streamlit web application. Open the provided URL in your web browser to interact with the ML Guide interface.
- Input Problem and Dataset: Upload your dataset and describe your machine learning problem.
- Exploratory Data Analysis: View the automatic EDA report generated by Sweetviz.
- Research Extraction: Review the relevant research papers extracted from arXiv.
- Web Search: Examine similar problems and solutions found on the web.
- Model Generation: Get the code for the best model to solve your problem, generated by the multi-LLM agents.