CMIP6 GPT

CMIP6 GPT is an AI-powered assistant designed to help users access CMIP6 climate data through natural language conversations. Built using OpenAI's GPT models, LangChain, and Streamlit.

Features

• Natural Language Interface: Interact with CMIP6 data using conversational queries.
• Dynamic Data Retrieval: Leverages vector search and language models to fetch relevant climate data.

Setup

1. Clone the Repository

git clone https://github.com/CliDyn/cmip6_gpt
cd cmip6_gpt

2. Create a virtual environment and install the required packages:

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

3. Install Dependencies

pip install -r requirements.txt

4. Configure API Keys. Create a .streamlit/secrets.toml file in the project root directory with the following content:

# .streamlit/secrets.toml
[openai]
api_key = "your-openai-api-key"

[LANGCHAIN]
# Add any LangChain-specific configurations here if necessary
LANGCHAIN_TRACING_V2 = 'true'
LANGCHAIN_ENDPOINT = 'https://api.smith.langchain.com'
LANGCHAIN_API_KEY = 'your-langhcain-api-key'

Usage

Run the Streamlit application:

streamlit run main.py

Open your web browser and navigate to http://localhost:8501 to access the application.