Easily add a recommendation engine to your Nextjs blog — Today we’re going to learn how to build a recommendation system for a social publishing platform like Medium. I wanted to share what I learned building the popular Obsidian plugin AVA that recommends your notes. The whole project’s source code we are going to build is available here You can…

In this example, we will ask GPT to pick the right dataset to search when a user asks a question and then answer the user's question. ⚠️ You can otherwise simplify this example by using Embedbase Cloud instead of running it yourself. If so, you can jump to the Seed…

Learn to build ChatGPT for X — Today we’re going to learn how to build a system to ask ChatGPT questions and get accurate answers about your documentation. We are going to use OpenAI and Embedbase. The whole project we are going to build is available here. You can also try an interactive version at https://docs.embedbase.xyz. Overview

Embedbase helps you deploy embeddings-powered applications to the cloud. This tutorial builds on top of the following OpenAI tutorial. Below you’ll find how you can change just a few lines of code and take the OpenAI tutorial from localhost to prod. You can try the full process by downloading the…

How to implement Natural language search with Embedbase Edit descriptionwww.youtube.com Embedbase is an open-source API for building, storing & retrieving embeddings. Today we will build a search engine for Paul Graham’s essays that we will use with Apple Siri Shortcuts, e.g. asking Siri questions about these essays. “Embeddings” are a concept in machine learning that allows you to compare data. …

Seeker is A modular Language Model (LM) that uses a search engine to stay relevant and up-to-date. The method is a single transformer that is called iteratively to generate: (i) a search query, (ii) a knowledge sequence, (iii) and a final response. When applied to dialogue, it is superior to…

TLDR: codex.louis030195.com Recently, OpenAI released a new model for code completion based on GPT-3^1, which is also behind GitHub Copilot^2 the coding assistant that allows you to skip straight to interesting code. I found that Codex works well to turn LaTex into code, I hope someone in the future will build a very specialized app that is pretty good at turning white papers with mathematical equations into code directly. I suspect it could speed up research a lot.

Using https://obsidian.md/ and https://beta.openai.com/? See some of my outputs https://forum.obsidian.md/t/fine-tuning-openai-api-gpt3-on-your-second-brain-obsidian/21849

Welcome to my humble attempt to raise my and your awareness about how to learn. I do not pretend to know anything, however! Knowing how to learn is one of the most valuable life skills. Unfortunately, little effort is applied to teach this, surprisingly. Frequently, we assume that we know…