Issue Resolution Agent

This agent helps resolve user issues by searching through a knowledge base of past issues (past_issues.csv). It uses Google's Generative AI to understand natural language queries and match them to historical solutions.

Prerequisites

• Python 3.10+
• A Google Cloud API Key (for Gemini)

Setup

1. Configure Environment Variables: Create a .env file in the root directory with the following content:

   # Required: Your Google Cloud API Key
   GOOGLE_API_KEY=your_api_key_here
   
   # Optional: The model to use (e.g., gemini-2.0-flash-exp)
   ISSUE_AGENT_MODEL=gemini-2.0-flash-exp

2. Install Dependencies:

   pip install -r requirements.txt

3. Prepare Data: Ensure past_issues.csv exists in the root directory. You can add more rows to this CSV to expand the agent's knowledge base.

Running the Agent

You can run the agent interactively using the provided Python script:

python run_issue_agent.py

This will start an interactive session where you can type your issues and get responses from the agent.

Project Structure

• issue_resolution_agent/: Contains the agent's source code, tools, and prompts.
• run_issue_agent.py: The entry point script to run the agent.
• past_issues.csv: The simulated knowledge base.
• requirements.txt: Python dependencies.