NotionNLP

Inspiration

I write daily journals on my notion page and I thought adding some NLP such as sentiments would be nice. When this hackathon came out, I thought it was the perfect opportunity to test the idea. I digged through the API and decided to extract sentiment, important topics, and emotional traits out of my journal entries

What it does

It takes your journal entries in Notion and enriches it with information about sentiment analysis, main topics, and emotional traits.

How we built it

I built it with notion-py-sdk and the nlapi-python python packages, which allowed me to interact with both APIs. I used Github Actions to generate NLP information for my latest entries to automate the entire process.

Challenges we ran into

I ran into a lot of challenges on how to get the right information out of the expert.ai API calls. Working with the notion API was also challenging, it's very limiting currently and there are not a lot of documentation or examples on how to do a lot of things such as creating a new property and adding them, getting contents out of a page etc. Lastly, I had issues with accessing secrets for github actions.

Accomplishments that we're proud of

I'm proud of realizing my idea and creating something that I actually use in my day-to-day life and I'm excited to see where this project goes. I'm also glad I got to try out the Notion API.

What we learned

I learned about how to access secrets for github actions, how to interact with the notion API, and parsing arguments for python functions

What's next for NotionNLP

I plan to store the API call results into MongoDB and visualize it in streamlit. Also, I plan to extract more insights out of the text by exploring other options that expert.ai provides.

Built With

• expert-ai
• notion
• notion-api
• python