The Streamlit app for the AI Assistant can be found here. You're welcome to give it a try!
This is a Streamlit-based AI assistant powered by OpenAI. The assistant is designed to answer questions based on its training knowledge and also supports uploading a CSV file to address further questions using Langchain for enhanced data processing.
- OpenAI Integration: Use GPT-4 or GPT-3.5-turbo models from OpenAI for conversational responses.
- SQL Capabilities: Support for SQL queries using an uploaded CSV file.
- Interactive Chat Interface: Real-time interactive chat experience.
- Clear Chat History: Option to clear chat history.
To run the application, follow the steps below:
-
Install Required Packages:
# Install packages python -m pip install -r requirements.txt
This command will install all the necessary dependencies listed in the requirements.txt file.
-
Run the Application:
# Run application streamlit run main.py
This command will start the application and execute the main.py script, allowing you to interact with the application.
- Enter your OpenAI API key in the sidebar.
- Model: Choose between
gpt-4
orgpt-3.5-turbo
. - Temperature: Adjust the temperature slider (disabled for now).
- Click on the "Upload a file" section.
- Upload a CSV file to enable SQL capabilities.
- Click on the "Clear History" button to clear the chat history.
This AI assistant is built using Streamlit and integrates the powerful capabilities of OpenAI's GPT-4 and GPT-3.5-turbo models. It is further enhanced with Langchain for efficient data processing and querying. The assistant is designed to answer questions based on its training knowledge and allows for uploading a CSV file to address questions through SQL queries.
Please note that this is a beta tool, and any feedback is appreciated to enhance its performance.