Welcome to the RAG Chatbot on Streamlit with Speech Functionality! This project leverages Retrieval-Augmented Generation (RAG) models to create an interactive chatbot with text-to-speech capabilities, using Huggingface, OpenAI, and Streamlit.
The RAG Chatbot on Streamlit with Speech Functionality is an application that allows users to interact with a chatbot using their own data, supported by zero-to-few shot prompts and chat history. The chatbot uses a combination of Huggingface embeddings, OpenAI language models, and Streamlit for the UI, incorporating text-to-speech functionality for an enhanced user experience.
Read more about the project in the Medium article.
- RAG Model Integration: Utilize Retrieval-Augmented Generation for intelligent responses.
- Text-to-Speech: Convert chatbot responses to speech for an interactive experience.
- User-Friendly Interface: Built with Streamlit for ease of use.
- Chat History: Maintain and access previous chat interactions.
- Custom Data: Chat with data specific to your requirements.
To get started with the RAG Chatbot, follow these steps:
- Clone the Repository:
bash
Copy code
git clone https://github.com/hanantabak2/RAG_chatbot_on_Streamlit_with_Speech_Functionality.git
cd RAG_chatbot_on_Streamlit_with_Speech_Functionality
- Install Dependencies:
bash
Copy code
pip install -r requirements.txt
- Run the Application:
bash
Copy code
streamlit run app.py
- Start the Application: Run the following command:
bash
Copy code
streamlit run app.py
- Access the UI: Open your web browser and go to http://localhost:8501.
- Chat with the Bot: Enter your queries in the chat interface and interact with the bot using your data.
- Use Text-to-Speech: Enable the text-to-speech functionality to hear the chatbot's responses.
- Huggingface for the RAG model.
- OpenAI for language model support.
- Streamlit for the UI framework.
Feel free to replace placeholders and add any additional sections or information specific to your project.