This repository contains a Next.js application that utilizes LangChain.js, Pinecone Database, and OpenAI's GPT-3.5 Turbo API. The main intent of this project is to supply necessary information to chat GPT, store it in a long-term memory (Pinecone vector DB), and then use it as a knowledge base to provide useful responses.
- Node.js
- Yarn
- Pinecone API key
- OpenAI API key
-
Clone the repo
git clone git@github.com:bamerf/ai.git
-
Install dependencies
yarn install
-
Create a
.env.local
file in the root directory and add your credentials for pinecone and openAI. -
Put all necessary files in the
docs
directory. and runyarn generate-embeddings-pinecone
-
Run the development server
yarn dev
-
Open http://localhost:3000 with your browser to see the result. Now you should be able to ask knowledge base relevant questions and get right answers.