https://github.com/tushar2704/gemmachat

GemmaChat- A smart chat with running Gemma model locally via Ollama on windows.
https://github.com/tushar2704/gemmachat

chainlit data-science deep-learning llmops llms machine-learning nlp python tushar2704

Last synced: 8 months ago
JSON representation

GemmaChat- A smart chat with running Gemma model locally via Ollama on windows.

• Host: GitHub
• URL: https://github.com/tushar2704/gemmachat
• Owner: tushar2704
• License: mit
• Created: 2024-02-29T15:42:33.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-03-01T20:16:01.000Z (over 2 years ago)
• Last Synced: 2024-12-27T08:16:45.612Z (over 1 year ago)
• Topics: chainlit, data-science, deep-learning, llmops, llms, machine-learning, nlp, python, tushar2704
• Language: Python
• Homepage: https://tushar-aggarwal.com
• Size: 194 KB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# GemmaChat

![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)

![CSS](https://img.shields.io/badge/CSS3-1572B6.svg?style=for-the-badge&logo=CSS3&logoColor=white)

![HTML](https://img.shields.io/badge/HTML5-E34F26.svg?style=for-the-badge&logo=HTML5&logoColor=white)

![Markdown](https://img.shields.io/badge/markdown-%23000000.svg?style=for-the-badge&logo=markdown&logoColor=white)

![Visual Studio Code](https://img.shields.io/badge/Visual%20Studio%20Code-0078d7.svg?style=for-the-badge&logo=visual-studio-code&logoColor=white)

Smart Chat using Gemma model via Ollama, LangChain and Chainlit

Coming up:Deployment, more feature and custom UI

## Steps to Replicate 

1. Fork this repository and create a codespace in GitHub as I showed you in the youtube video OR Clone it locally.

   ```

   git clone https://github.com/tushar2704/GemmaChat.git

   cd GemmaChat

   ```

2. Create a virtualenv and activate it

   ```

   python3 -m venv .venv && source .venv/bin/activate

   ```

3. OPTIONAL - Rename example.env to .env with `cp example.env .env`and input the environment variables from [LangSmith](https://smith.langchain.com/). You need to create an account in LangSmith website if you haven't already.

   ``` 

   LANGCHAIN_TRACING_V2=true

   LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"

   LANGCHAIN_API_KEY="your-api-key"

   LANGCHAIN_PROJECT="your-project"

   ```

4. Run the following command in the terminal to install necessary python packages:

   ```

   pip install -r requirements.txt

   ```

5. Run the following command in your terminal to start the chat UI:

   ```

   chainlit run main.py

   ```

## System Prompt used for testing

```

Please act as an expert in providing smart chat responses. Your responses should be friendly, simple, and jargon-free, suitable for beginners. When responding, consider using a mix of paragraphs and bullets to convey information effectively. Topics to cover include:

- Introduction to smart chat responses

- Importance of tone in chat interactions

- Tips for maintaining a friendly demeanor

- Examples of beginner-friendly responses

- Strategies for engaging users effectively

- Handling common challenges in chat conversations

- Include examples of tone variations (e.g., formal, casual, informative)

- Provide guidance on adapting responses based on user input

- Suggest ways to personalize responses for different users

- Offer insights on building rapport through chat interactions

- Explain the significance of active listening in chat responses

```