https://github.com/wtfdevansh/crediguide
llm agent which can recommend the credit card based on score and usage give respone in structure way you can read readme for setup and can access our model using website and whatsapp
https://github.com/wtfdevansh/crediguide
agent json langchain openai pydantic python
Last synced: 2 months ago
JSON representation
llm agent which can recommend the credit card based on score and usage give respone in structure way you can read readme for setup and can access our model using website and whatsapp
- Host: GitHub
- URL: https://github.com/wtfdevansh/crediguide
- Owner: wtfdevansh
- Created: 2025-06-17T01:54:44.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-18T08:30:26.000Z (about 1 year ago)
- Last Synced: 2025-06-18T08:36:52.086Z (about 1 year ago)
- Topics: agent, json, langchain, openai, pydantic, python
- Language: Python
- Homepage:
- Size: 0 Bytes
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Credi Guide 💳
Credi Guide is a user-friendly chatbot designed to help you find the perfect credit card based on your financial profile and spending habits. Interact with our intelligent assistant to receive personalized recommendations.
## Features
* Interactive chatbot interface powered by Streamlit.
* Personalized credit card recommendations using a Langchain agent.
* Detailed information for each recommended card:
* Card Name and Issuer
* Card Image
* Rewards Summary
* Annual Fee
* Reason for Recommendation
* Clear and structured presentation of recommendations.
## Technologies Used
* Python
* Streamlit (for the web application)
* Langchain (for the AI agent and logic)
* Langchain-OpenAI (for interacting with OpenAI models)
* Pydantic (for data validation and schema)
* Dotenv (for environment variable management)
## Setup and Installation
1. **Clone the repository:**
```bash
git clone # Replace with the actual URL
cd # Replace with the actual directory name
```
2. **Create and activate a virtual environment (recommended):**
```bash
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
```
3. **Install dependencies:**
```bash
pip install -r requirements.txt
```
4. **Set up environment variables:**
Create a file named `.env` in the root directory of the project and add your OpenAI API key:
```env
OPENAI_API_KEY="your_openai_api_key_here"
```
Replace `"your_openai_api_key_here"` with your actual OpenAI API key.
## How to Run
* Ensure your virtual environment is activated and you are in the project's root directory.
* Run the Streamlit application using the following command:
```bash
streamlit run app.py
```
* Open your web browser and navigate to the local URL provided by Streamlit (usually `http://localhost:8501`).
## Access using whatsapp
[qr code](https://drive.google.com/file/d/19gqYk-wESRacfz-aiskbgPJ473pQijSh/view?usp=sharing)
## Access using web
[url](https://wtfdevansh-crediguide-app-dpt10d.streamlit.app/)
## Project Structure
```
.
├── app.py # Main Streamlit application file
├── llm_agent.py # Defines the Langchain agent and its tools
├── card_agent/ # Module for card recommendation logic
│ ├── recommender.py # Core recommendation engine
│ ├── data_loader.py # Loads card data
│ └── ...
├── data/
│ └── sampleData.json # Sample data for credit cards
├── requirements.txt # Project dependencies
├── schema/ # Pydantic schemas for data validation
│ └── schema.py
├── assets/ # Images and static files for the UI
└── README.md # This file
```
## Contributing
* Contributions are welcome! If you have suggestions for improvements or find any issues, please feel free to:
* Open an issue on the project's GitHub page.
* Fork the repository, make your changes, and submit a pull request.
## Demo video
[whatsapp demo](https://drive.google.com/file/d/1GAk_eXgrWctWkaSwj4SX_yDt7jkcmYxx/view?usp=sharing)
[web demo](https://drive.google.com/file/d/1HykOXT5uiu6Jmet2DIzEeSv7nyt3bTKk/view?usp=sharing)