Forked from Mckay Wrigley's https://github.com/mckaywrigley/paul-graham-gpt

Berkshire Hathaway GPT

AI-powered search and chat for [Berkshire Hathaway's] annual letters.

All code & data used is 100% open-source.

Dataset

The dataset is a CSV file containing all text & embeddings used.

I recommend getting familiar with fetching, cleaning, and storing data as outlined in the scraping and embedding scripts below, but feel free to skip those steps and just use the dataset.

How It Works

Berkshire Hathaway GPT provides 2 things:

1. A search interface.
2. A chat interface.

Search

Search was created with Azure OpenAI Embeddings (text-embedding-ada-002).

First, we loop over the essays and generate embeddings for each chunk of text.

Then in the app we take the user's search query, generate an embedding, and use the result to find the most similar passages from the book.

The comparison is done using cosine similarity across our database of vectors.

Our database is a Postgres database with the pgvector extension hosted on Supabase.

Results are ranked by similarity score and returned to the user.

Chat

Chat builds on top of search. It uses search results to create a prompt that is fed into GPT-3.5-turbo.

This allows for a chat-like experience where the user can ask questions about the book and get answers.

Running Locally

Here's a quick overview of how to run it locally.

Requirements

1. Set up Azure OpenAI

You'll need an Azure OpenAI API key to generate embeddings.

2. Set up Supabase and create a database

Note: You don't have to use Supabase. Use whatever method you prefer to store your data. But I like Supabase and think it's easy to use.

There is a schema.sql file in the root of the repo that you can use to set up the database.

Run that in the SQL editor in Supabase as directed.

I recommend turning on Row Level Security and setting up a service role to use with the app.

Repo Setup

3. Clone repo

git clone https://github.com/dino1729/berkshire-hathaway-gpt.git

4. Install dependencies

npm i

5. Set up environment variables

Create a .env.local file in the root of the repo with the following variables:

AZURE_OPENAI_APIKEY=
AZURE_OPENAI_ENDPOINT=
AZURE_OPENAI_DEPLOYMENT=
AZURE_OPENAI_MODEL=
AZURE_OPENAI_VERSION=

NEXT_PUBLIC_SUPABASE_URL=
SUPABASE_SERVICE_ROLE_KEY=

Dataset

6. Run scraping script

npm run scrape

This scrapes all of the essays from Berkshire Hathaway's website and saves them to a json file.

7. Run embedding script

npm run embed

This reads the json file, generates embeddings for each chunk of text, and saves the results to your database.

There is a 900ms delay between each request to avoid rate limiting.

This process will take a while

App

8. Run app

npm run dev

Credits

Thanks, Warren Buffet!

I highly recommend you read Berkshire Hathaway's annual letters.