An AI chatbot featuring conversational memory, designed to enable users to discuss their CSV, PDF and TXT data in a more intuitive manner. π
By integrating the strengths of Langchain and OpenAI, AI_Assistant employs large language models to provide users with seamless, context-aware natural language interactions for a better understanding of their data.π§
- enable print tokens utilizations for the conversation
- Use CSV Agent for chat with the entire csv file
- Add lots of files accepted like GitHub repo, Excel etc...
- Run falcon-40b-instruct and falcon-40b on a custom dataset
- Add free models like vicuna and free embeddings
- Replace chain of the chatbot by a custom agent for handling more features | memory + vectorstore + custom prompt
Follow these steps to set up and run the service locally :
- Python 3.8 or higher
- Git
Clone the repository :
git clone https://github.com/AhmedEwis/AI_Assistant.git
Navigate to the project directory :
cd AI_Assistant
Create a virtual environment :
python -m venv .venv
.\.venv\Scripts\activate
Install the required dependencies in the virtual environment :
pip install -r requirements.txt
Launch the chat service locally :
streamlit run src/Home.py
Contributions are always welcome! If you want to contribute to this project, please open an issue, submit a pull request or contact me at [email protected] (: