🤖Ask questions about any CSV dataset using ChatGPT with document retrieval. The default data set is information about ChatGPT Plugins.
💪 Built with [LangChain]
In order to set your environment up to run the code here, first install all requirements:
pip install -r requirements.txt
Then set your OpenAI API key (if you don't have one, get one here) as a system environment variable:
export OPENAI_API_KEY=....
- Python script 'ingest.py' to embed your data
- Python script 'debug_chains.py' for setting up the Debug Retrieval Question-Answering chain
- Python script 'qa.py' for running the Question-Answering system
- Instructions for ingesting your own dataset and running the QA system
In order to ask a question, run the command below and follow the prompts: python qa.py
The prompt preserves your previous questions, and it should be able to recall what you've previously asked or the information it has shared with you.
Export your dataset to CSV and place it in a folder named "Data" in the root directory of the project.
Run the following command to ingest the data:
python ingest.py
python qa.py