DEV Community

Duc Tran
Duc Tran

Posted on • Edited on

19 2 2 1 2

Chat UI for Deepseek in your local

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.

Image description

Full source code in here

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

Pull deepseek-r1 model

ollama pull deepseek-r1 
Enter fullscreen mode Exit fullscreen mode

Clone repo

git clone -b v1 https://github.com/ductnn/chat-deepseek-ui.git
cd chat-deepseek-ui
Enter fullscreen mode Exit fullscreen mode

Install required packages:

pip install streamlit ollama
Enter fullscreen mode Exit fullscreen mode

If you still get build errors in package pyarrow, try installing pyarrow
as a binary:

pip install --only-binary=:all: pyarrow
Enter fullscreen mode Exit fullscreen mode

Run the app:

streamlit run app.py
Enter fullscreen mode Exit fullscreen mode

Heroku

This site is built on Heroku

Join the ranks of developers at Salesforce, Airbase, DEV, and more who deploy their mission critical applications on Heroku. Sign up today and launch your first app!

Get Started

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs