https://github.com/samitugal/warehousemanagerai
This repository contains a ChatBot application designed to assist with warehouse management tasks. Leveraging advanced LLM models like OpenAI and Amazon LLM, combined with PostgreSQL and Pinecone for data handling, this project aims to streamline and enhance warehouse operations.
https://github.com/samitugal/warehousemanagerai
chatbot generative-ai inventory-management question-answering
Last synced: 21 days ago
JSON representation
This repository contains a ChatBot application designed to assist with warehouse management tasks. Leveraging advanced LLM models like OpenAI and Amazon LLM, combined with PostgreSQL and Pinecone for data handling, this project aims to streamline and enhance warehouse operations.
- Host: GitHub
- URL: https://github.com/samitugal/warehousemanagerai
- Owner: samitugal
- License: apache-2.0
- Created: 2024-07-26T06:12:27.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-07-31T17:32:07.000Z (almost 2 years ago)
- Last Synced: 2025-01-06T01:43:20.227Z (over 1 year ago)
- Topics: chatbot, generative-ai, inventory-management, question-answering
- Language: Python
- Homepage:
- Size: 85 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Warehouse Management ChatBot Project
This project is designed to assist with warehouse management through a ChatBot application. It leverages support from OpenAI and Amazon LLM models to respond to various user queries related to warehouse management.
## Features
- **LLM Models:** Supports both OpenAI and Amazon LLM models.
- **Database:** Utilizes PostgreSQL for relational database management.
- **Embeddings:** Pinecone is used for embedding operations.
- **Langchain Agents and Tools:** Creates an agent to query both relational and unstructured datasets based on user queries.
- **Frontend:** A Streamlit application provides the user interface.
- **History Mechanism:** Keeps track of user interactions and query history.
## Installation
1. **Clone the repository:**
```bash
git clone https://github.com/samitugal/WarehouseManagerAI.git
cd warehouse-management-chatbot
```
2. **Set up the Python environment:**
```bash
python -m venv .venv
source .venv/bin/activate # On Windows use `venv\Scripts\activate`
```
3. **Install the required packages:**
```bash
pip install -r requirements.txt
```
4. **Set up PostgreSQL using Docker:**
- Ensure Docker is installed and running on your system.
- Use the provided `docker-compose.yaml` file to set up the PostgreSQL database with a sample Northwind database.
- Run the following command to start the services:
```bash
docker-compose up -d
```
- The database connection settings in the project configuration file should be updated to match those specified in the `docker-compose.yaml` file.
5. **Set up Pinecone:**
- Sign up for Pinecone and obtain the API key.
- Update the Pinecone API settings in the project configuration file.
## Usage
1. **Run the Streamlit application:**
```bash
streamlit run ui/streamlit_ui.py
```
2. **Interacting with the ChatBot:**
- Open the Streamlit application in your browser.
- Use the ChatBot interface to query the warehouse management system.
- The ChatBot will respond based on the combined power of OpenAI and Amazon LLM models, querying the PostgreSQL database and Pinecone embeddings as needed.
## Project Structure
- `ui/streamlit_ui.py`: The main Streamlit application file.
- `requirements.txt`: List of required Python packages.
- `configs/`: Directory for configuration definitions.
- `Database/`: Directory for database configration definitons.
- `Embeddings/`: Directory for embeddings configration definitons.
- `LLM/`: Directory for large language model configration definitons.
- `data/`: Directory for data-related files.
- `src/`: Source code directory.
- `agents/`: Agents used for querying data.
- `database/`: Database-related modules.
- `embedding_providers/`: Modules for embedding operations.
- `llm/`: Large Language Model-related modules.
- `prompts/`: Directory for prompt templates.
- `tools/`: Tools used by the agents.
- `utils/`: Utility functions and modules.
- `ui/`: Streamlit UI components.
## Contributing
We welcome contributions to improve the project. Please follow these steps to contribute:
1. Fork the repository.
2. Create a new branch (`git checkout -b feature/your-feature`).
3. Make your changes.
4. Commit your changes (`git commit -m 'Add some feature'`).
5. Push to the branch (`git push origin feature/your-feature`).
6. Open a pull request.
## Screenshots
## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
## Acknowledgements
- [OpenAI](https://www.openai.com/)
- [Amazon LLM](https://aws.amazon.com/machine-learning/large-language-models/)
- [Langchain](https://langchain.com/)
- [Pinecone](https://www.pinecone.io/)
- [Streamlit](https://streamlit.io/)