Divar Car Search Agent

This project is an intelligent chatbot that helps users find car listings on Divar.ir, a popular classifieds website in Iran. The agent uses AI to understand natural language queries, scrapes the website for relevant data, and presents it in a user-friendly way. The frontend is built with Streamlit.

Features

• Natural Language Understanding: Ask for cars in plain Persian (e.g., "پراید در شیراز بین 300 تا 500 میلیون").
• Web Scraping: Extracts real-time car listing data from Divar.ir.
• Detailed Information: Can retrieve detailed information about a specific car, including price, mileage, color, and seller's description.
• Interactive Chat: A simple and intuitive chat interface powered by Streamlit.
• AI-Powered: Uses a Large Language Model (via OpenRouter) to process queries and generate responses.

How It Works

1. User Input: The user enters a query in the Streamlit chat interface.
2. AI Agent: The query is sent to a LangChain-based agent.
3. Tool Selection: The agent decides which tool to use:
   • DivarCarSearch: To search for a list of cars based on model, city, and price.
   • DivarCarSearchDetail: To get more details about a specific car from its URL.
4. Scraping: The selected tool scrapes Divar.ir using httpx and BeautifulSoup.
5. Response Generation: The scraped data is sent back to the agent, which then generates a natural language response for the user.
6. Display: The response is displayed in the chat interface.

Installation

1. Clone the repository:

   git clone <your-repository-url>
   cd final_divar

2. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`

3. Install the required packages:

   pip install -r requirements.txt

4. Set up your environment variables: Create a file named .env in the root of the project and add your OpenRouter API key:

   OPENROUTER_API_KEY="your-openrouter-api-key"
   

How to Run

Once you have completed the installation steps, run the following command in your terminal:

streamlit run main.py

This will start the Streamlit application, and you can open it in your web browser at the provided URL (usually http://localhost:8501).