https://github.com/ductnn/chat-deepseek-ui
Chat UI for Deepseek
https://github.com/ductnn/chat-deepseek-ui
chatgpt deepseek
Last synced: 18 days ago
JSON representation
Chat UI for Deepseek
- Host: GitHub
- URL: https://github.com/ductnn/chat-deepseek-ui
- Owner: ductnn
- Created: 2025-02-01T07:28:57.000Z (5 months ago)
- Default Branch: master
- Last Pushed: 2025-02-07T09:35:50.000Z (5 months ago)
- Last Synced: 2025-03-27T18:18:20.886Z (4 months ago)
- Topics: chatgpt, deepseek
- Language: Python
- Homepage:
- Size: 373 KB
- Stars: 11
- Watchers: 1
- Forks: 4
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Chat deepseek UI
A simple web-based chat interface powered by Ollama's deep-seek model.
This tool provides an interactive, real-time chatting experience with the
assistant, using Streamlit for the frontend. The assistant processes and streams
responses back to the user, ensuring a seamless and engaging interaction.
## Features
- **Real-time Chat Interface**: Allows for dynamic interaction with the assistant.
- **Persistent Chat History**: Maintains chat history between sessions.
- **Save & Load Chat History**: Automatically saves chat history to a JSON file for persistent conversations.
### Setup
Install [ollama](https://ollama.com/download)
Pull deepseek-r1 model
```sh
ollama pull deepseek-r1
```
Clone repo
```sh
git clone https://github.com/ductnn/chat-deepseek-ui.git
cd chat-deepseek-ui
```
Build postgres database and redis:
```sh
# Use docker-compose
docker-compose up -d
```
Install required packages:
```sh
pip install streamlit ollama
```
If you still get build errors in package `pyarrow`, try installing `pyarrow`
as a binary:
```sh
pip install --only-binary=:all: pyarrow
```
Create file `.env`, or copy from `.env.example` and fill in your database credentials:
```sh
DB_NAME=mydatabase
DB_USER=myuser
DB_PASSWORD=mypassword
DB_HOST=localhost
DB_PORT=5432
```
Run the app:
```sh
streamlit run app.py
```