https://github.com/muzammil-git/converse-ai

Converse is a demo application showcasing conversational AI using DeepSeek R1, Hugging Face embeddings, and LLaMA Index. It features natural dialogue capabilities, Chroma DB vector storage, and a user-friendly Gradio interface for seamless human-AI interaction.
https://github.com/muzammil-git/converse-ai

deepseek-r1 docker fastapi gradio grok huggingface-embeddings llamaindex postgresql vectordb

Last synced: 8 months ago
JSON representation

Converse is a demo application showcasing conversational AI using DeepSeek R1, Hugging Face embeddings, and LLaMA Index. It features natural dialogue capabilities, Chroma DB vector storage, and a user-friendly Gradio interface for seamless human-AI interaction.

• Host: GitHub
• URL: https://github.com/muzammil-git/converse-ai
• Owner: muzammil-git
• Created: 2025-03-05T00:17:32.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-03-05T00:38:44.000Z (8 months ago)
• Last Synced: 2025-03-05T01:25:17.393Z (8 months ago)
• Topics: deepseek-r1, docker, fastapi, gradio, grok, huggingface-embeddings, llamaindex, postgresql, vectordb
• Language: Python
• Homepage:
• Size: 10.7 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
# Converse: A Conversational AI Demo

## Introduction

Converse is a conversational AI demo that showcases the capabilities of the DeepSeek R1 model, Hugging Face embeddings, and the LLaMA Index framework. 

## Client-Side

![image](client.png)

## Server-Side

![image](server.png)

## Features

* **Conversational Interface**: Engage in natural-sounding conversations with the AI model.

* **Response Generation**: The AI model generates responses based on the user's input.

* **DeepSeek R1 Model**: A conversational AI model developed by Groq.

* **Hugging Face Embeddings**: A library of pre-trained embeddings for natural language processing.

* **LLaMA Index Framework**: A framework for building and querying large language models.

* **Chroma DB**: A vector store for efficient storage and retrieval of embeddings.

* **Client-Side Interface**: Built using Gradio, a Python library for building user interfaces.

## Setup and Usage

1. Clone the repository: `git clone https://github.com/your-username/converse.git`

2. Install the required dependencies: `poetry install`

3. Run the server: `poetry run python main.py`

4. Client is up on local URL:  `http://127.0.0.1:7860`

5. Open a web browser and navigate to `http://localhost:8000` to interact with the AI model.

## Example Use Cases

* **Simple Conversation**: Ask the AI model a question, and it will respond accordingly.

* **Multi-Turn Conversation**: Engage in a conversation with the AI model, and it will respond based on the context.

* **Retrieval-Augmented Generation (RAG)**: Use the AI model to generate responses based on a set of documents or knowledge base.

* **Vector Store**: Use Chroma DB to store and retrieve embeddings for efficient querying.

## Future Enhancements

* **Improved Response Generation**: Enhance the AI model's ability to generate more accurate and informative responses.

* **Client Side**: The human interaction part, markdown rendering.

* **Emotional Intelligence**: Integrate emotional intelligence into the AI model to make it more empathetic and understanding.

* **Multimodal Interaction**: Allow users to interact with the AI model using multiple modalities, such as voice or text.