https://github.com/lambda-science/dnd-qa

https://github.com/lambda-science/dnd-qa

Last synced: about 15 hours ago
JSON representation

• Host: GitHub
• URL: https://github.com/lambda-science/dnd-qa
• Owner: lambda-science
• License: mit
• Created: 2023-03-10T17:12:10.000Z (almost 2 years ago)
• Default Branch: master
• Last Pushed: 2024-01-30T08:51:53.000Z (12 months ago)
• Last Synced: 2025-01-09T23:46:26.992Z (8 days ago)
• Language: Python
• Size: 4.94 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# 🗡️D&D Spell QA Bot🗡️

This is a chatbot that can answer questions about **Dungeon and Dragons spells** based on this [database](https://www.aidedd.org/dnd-filters/spells-5e.php) and built with LangChain and OpenAI API. Usefull to find informations quickly instead of browsing through 50 pages of PDF.

The creator of this bot is **[Corentin Meyer (@corentinm_py)](https://twitter.com/corentinm_py)**.  

💪 This bot it based on Notion Question-Answering demo from [LangChain](https://github.com/hwchase17/langchain)

# 🌲 Environment Setup

In order to set your environment up to run the code here, first install all requirements and then launch streamlit app:

```shell

python -m venv .venv

source .venv/bin/activate

pip install -r requirements.txt

streamlit run main.py

```

Then set your OpenAI API key (if you don't have one, get one [here](https://beta.openai.com/playground))

```shell

export OPENAI_API_KEY=....

```

## 🚀 Code to deploy on StreamLit

The code to run the StreamLit app is in `main.py`.

Note that when setting up your StreamLit app you should make sure to add `OPENAI_API_KEY` as a secret environment variable.

## 🧑 Reproduce the embedding and stuff

Run the following command to ingest the data.

```shell

python ingest.py

```

Boom! Now you're done, and you can ask it questions like:

```shell

python qa.py "What's the size of tsunami spell ?"

```