Current Project: Reading books about entrepreneurs and sharing what I learned from them via blog posts and audio podcasts

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• I’m trying to enhance a large language model (LLM) with specific information using retrieval-augmented generation (RAG). I’m not technical, so I’ve struggled with this.

What I learned:

• I probably can use a combination of a book scanner and an LLM to create a large percentage of a book digest.
• Creating a record (e.g., digest, profile, or something else) for each entrepreneur and enriching it with information from various books is likely the best approach to creating the best data set about entrepreneurs. But there’s a step beyond this I need to figure out.
• ChatGPT’s custom GPTs are helpful, but they have many limitations, and getting the prompting right requires extensive testing.

Those are my struggles and learnings from the week!