https://github.com/Nutlope/turboseek

An AI search engine inspired by Perplexity
https://github.com/Nutlope/turboseek

Last synced: about 2 months ago
JSON representation

An AI search engine inspired by Perplexity

• Host: GitHub
• URL: https://github.com/Nutlope/turboseek
• Owner: Nutlope
• Created: 2024-05-26T09:07:15.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-06-17T18:07:06.000Z (3 months ago)
• Last Synced: 2024-06-17T20:13:36.103Z (3 months ago)
• Language: TypeScript
• Homepage: https://www.turboseek.io/
• Size: 514 KB
• Stars: 538
• Watchers: 6
• Forks: 67
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-azure-openai-llm - turboseek
• StarryDivineSky - Nutlope/turboseek - 3 用于LLMs；用于搜索 API 的 Bing；适用于网站分析。运作方式：回答用户的问题；向必应搜索 API 发出请求，以查找前 6 个结果并显示它们；从 bing 发回的 6 个链接中抓取文本，并将其存储为上下文；向 Mixtral-8x7B 发出请求，其中包含用户的问题 + 上下文，并将其流回给用户；再次向 Llama-3-8B 提出 3 个相关问题，用户可以跟进。 (文本生成、文本对话 / 大语言对话模型及数据)
• project-awesome - Nutlope/turboseek - An AI search engine inspired by Perplexity (TypeScript)

README

        


  

  
TurboSeek






  An open source AI search engine. Powered by Together.ai.



## Tech stack

- Next.js app router with Tailwind

- Together AI for LLM inference

- Mixtral 8x7B & Llama-3 for the LLMs

- Bing for the search API

- Helicone for observability

- Plausible for website analytics

## How it works

1. Take in a user's question

2. Make a request to the bing search API to look up the top 6 results and show them

3. Scrape text from the 6 links bing sent back and store it as context

4. Make a request to Mixtral-8x7B with the user's question + context & stream it back to the user

5. Make another request to Llama-3-8B to come up with 3 related questions the user can follow up with

## Cloning & running

1. Fork or clone the repo

2. Create an account at [Together AI](https://dub.sh/together-ai) for the LLM

3. Create an account at [SERP API](https://serper.dev/) or with Azure ([Bing Search API](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api))

4. Create an account at [Helicone](https://www.helicone.ai/) for observability

5. Create a `.env` (use the `.example.env` for reference) and replace the API keys

6. Run `npm install` and `npm run dev` to install dependencies and run locally

## Future tasks

- [ ] Move back to the Together SDK + simpler streaming

- [ ] Add a tokenizer to smartly count number of tokens for each source and ensure we're not going over

- [ ] Add a regenerate option for a user to re-generate

- [ ] Make sure the answer correctly cites all the sources in the text & number the citations in the UI

- [ ] Add sharability to allow folks to share answers

- [ ] Automatically scroll when an answer is happening, especially for mobile

- [ ] Fix hard refresh in the header and footer by migrating answers to a new page

- [ ] Add upstash redis for caching results & rate limiting users

- [ ] Add in more advanced RAG techniques like keyword search & question rephrasing

- [ ] Add authentication with Clerk if it gets popular along with postgres/prisma to save user sessions

## Inspiration

- Perplexity

- You.com

- Lepton search