DiscovAI

An AI-powered search engine for AI tools, or your own data.

https://github.com/user-attachments/assets/2cdc92d0-d0c9-4098-8166-260e973783f0

Please feel free to contact me on Twitter or create an issue if you have any questions.

💻 Live Demo

DiscovAI.io (use it for free without signin or credit card)

🗂️ Overview

• 🛠 Features
• 🧱 Tech-Stack
• 🚀 Quickstart
• 🌐 Deploy

🛠 Features

• Vector-based Search: Converts user queries into vectors for precise similarity matching in our AI product database.

• Redis-powered Caching: Utilizes Redis to cache search results and outputs, significantly improving response times for repeated queries.

• Comprehensive AI Database: Maintains an up-to-date collection of AI products across various categories and industries.

• LLM-powered Responses: Leverages large language models to provide detailed, context-aware answers based on search results.

• User-friendly Interface: Offers an intuitive design for effortless navigation and efficient AI product discovery.

🧱 Stack

• App framework: Next.js
• Text streaming: Vercel AI SDK
• LLM Model: gpt-4o-mini
• Database: Supabase
• Vector: Pgvector
• Embedding Model: Jina AI
• Redis Cache: Upstash
• Component library: shadcn/ui
• Headless component primitives: Radix UI
• Styling: Tailwind CSS

🚀 Quickstart

1. Clone repo

run the following command to clone the repo:

git clone https://github.com/DiscovAI/DiscovAI-search

2. Install dependencies

cd discovai-search
pnpm i

3. Setting up Supabase

create a supabase project, then run the src/db/init.sql in SQL Editor to setup database

4. Setting up Upstash

Follow the guide below to set up Upstash Redis. Create a database and obtain UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN. Refer to the Upstash guide for instructions on how to proceed.

4. Fill out secrets

cp .env.local.example .env.local

Your .env.local file should look like this:

# Required

# for match documents
NEXT_PUBLIC_SUPABASE_URL=
NEXT_PUBLIC_SUPABASE_ANON_KEY=

# for embedding query, retrieved here: https://jina.ai/embeddings/
JINA_API_KEY=

# for llm output, retrieved here: https://platform.openai.com/api-keys
OPENAI_API_KEY=
OPENAI_API_URL=

# for llm cache and serach cache
UPSTASH_REDIS_REST_URL=
UPSTASH_REDIS_REST_TOKEN=

5. Run app locally

pnpm dev

You can now visit http://localhost:3000.

🌐 Deploy

You can deploy on any saas platform like vercel, zeabur, cloudflare pages.

🌟 History