https://github.com/afauzulh/simple-ecommerce-chatbot
Simple ecommerce product catalogue chatbot using Ollama, LangChain, Streamlit and DummyJSON Product API
https://github.com/afauzulh/simple-ecommerce-chatbot
agent-tools chatbot docker dummyjson-api langchain large-language-models ollama prompt-engineering
Last synced: 3 months ago
JSON representation
Simple ecommerce product catalogue chatbot using Ollama, LangChain, Streamlit and DummyJSON Product API
- Host: GitHub
- URL: https://github.com/afauzulh/simple-ecommerce-chatbot
- Owner: AFauzulh
- Created: 2024-11-26T02:48:57.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-26T04:39:36.000Z (over 1 year ago)
- Last Synced: 2025-03-21T20:47:25.092Z (over 1 year ago)
- Topics: agent-tools, chatbot, docker, dummyjson-api, langchain, large-language-models, ollama, prompt-engineering
- Language: Python
- Homepage:
- Size: 178 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.MD
Awesome Lists containing this project
README
# Set up environment
**Pre-requisites :**
1. Create virtual environment (I'm using [venv](https://docs.python.org/3/library/venv.html))
2. Run `pip install -r requirements.txt`
3. Download and install [Ollama](https://ollama.com/)
**Ollama**
After installing, open Ollama and run command `ollama run llama3.2` on your terminal to download the pretrained LLM model. In this project, I'm using `llama3.2-3B` because it's lightweight and has good performance.
## Deployment
I'm using Streamlit and Docker to deploy the chatbot.
### Step 1 : Build Docker Image
```bash
docker build -t ecommerce-chatbot-app .
```
### Step 2 : Run Docker Container
```bash
docker run -d --restart always --gpus all --name ecommerce-chatbot-app -p 8501:8501 ecommerce-chatbot-app
```
To stop and delete the container run
```bash
docker stop ecommerce-chatbot-app && docker rm ecommerce-chatbot-app
```
## Chatbot Overview
**Example of Questions**


**Retrieved data from API**
