Navalmanac Save

This is a Next.js project bootstrapped with create-next-app.

Getting Started

First, create a new .env file from .env.example and add your OpenAI API key found here.

cp .env.example .env

Prerequisites

• Node.js
• Yarn
• wget (on macOS, you can install this with brew install wget)

Next, we'll need to load our data source.

Data Ingestion

Data ingestion happens in two steps.

First, you should download the book / source and format it into something readable. In my case I downloaded the book from here and converted it into md format using Calibre. Add that source to the project folder and update FILENAME in ingest.ts to match the filename.

Next, install dependencies and run the ingestion script:

yarn && yarn ingest

This will parse the data, split text, create embeddings, store them in a vectorstore, and then save it to the data/ directory.

We save it to a directory because we only want to run the (expensive) data ingestion process once.

The Next.js server relies on the presence of the data/ directory. Please make sure to run this before moving on to the next step.

Running the Server

Then, run the development server:

yarn dev

Open http://localhost:3000 with your browser to see the result.

Deploying the server

The production version of this repo is hosted on fly. To deploy your own server on Fly, you can use the provided fly.toml and Dockerfile as a starting point.

Note: As a Next.js app it seems like Vercel is a natural place to host this site. Unfortunately there are limitations to secure websockets using ws with Next.js which requires using a custom server which cannot be hosted on Vercel. Even using server side events, it seems, Vercel's serverless functions seem to prohibit streaming responses (e.g. see here)

Inspirations

This repo borrows heavily from

• ChatLangChain - for the backend and data ingestion logic
• LangChain Chat NextJS - for the frontend.

How To Run on Your Example

If you'd like to chat your own data, you need to:

1. Set up your own ingestion pipeline, and create a similar data/ directory with a vectorstore in it.
2. Change the prompt used in pages/api/util.ts - right now this tells the chatbot to only respond to questions about LangChain, so in order to get it to work on your data you'll need to update it accordingly.

The server should work just the same 😄