This project leverages the capabilities of Llama 3 in conjunction with CrewAI to build an automated data analysis pipeline. The pipeline is designed to efficiently analyze data stored in a SQL database, utilizing a team of specialized AI agents, each assigned a specific role in the workflow.
The process begins with loading any dataset (ds-salaries.csv) into a SQLite database. The data is subsequently accessed and queried as part of the automated analysis pipeline.
Three AI agents are employed, each with a distinct role:
- SQL Developer Agent: Responsible for constructing and executing optimized SQL queries to extract relevant data from the database.
- Data Analyst Agent: Analyzes the extracted data, providing detailed insights and interpretations.
- Report Writer Agent: Summarizes the analysis into an executive report, focusing on clarity and conciseness.
Llama 3 is integrated into the project to handle natural language processing and decision-making tasks. Callback mechanisms are implemented to log and monitor the model's activities for transparency and accuracy.
The entire process, from data extraction to report generation, is automated using CrewAI. Tasks are executed sequentially, ensuring coherence and precision in the final output.
This project demonstrates the potential of integrating AI-driven agents with database systems for automated, intelligent data analysis. It is particularly useful in scenarios where rapid, high-quality insights are required with minimal human intervention.
To set up the project locally:
-
Clone the Repository: git clone https://github.com/riddhihalade/sql_agent.git cd sql_agent
-
Install Dependencies: poetry install
-
Set Up the Environment: Add necessary environment variables and API keys in a .env file located in the project’s root directory.
-
Prepare the Database: Load the dataset of choice into the SQLite database.