This project is a multi-agent AI workflow built with CrewAI and Python. It reads an Request for Proposal (RFP) document (PDF) and uses sequential AI agents to extract key information, generate a summary, and perform risk analysis.
- Python 3.x
- CrewAI Framework
- Ollama (Local LLM -
mistralmodel) - PyMuPDF (for document extraction)
-
Install Ollama & Download Model: Ensure Ollama is installed on your system. Open a terminal and pull the Mistral model:
ollama run mistral -
Set up the Python Environment: Create a virtual environment (optional but recommended) and install the dependencies:
pip install -r requirements.txt -
Add the Input File: Ensure the
sample_rfp.pdffile is placed in the root directory of this project.
To execute the multi-agent workflow, simply run the main script:
python main.py
The system will sequentially trigger the Research Agent, Summary Agent, and Risk Analysis Agent. The final structured report will be printed in the terminal.