https://github.com/Nutlope/turboseek
An AI search engine inspired by Perplexity
https://github.com/Nutlope/turboseek
Last synced: about 1 month 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 (11 months ago)
- Default Branch: main
- Last Pushed: 2024-06-24T09:47:30.000Z (10 months ago)
- Last Synced: 2024-07-31T15:01:25.860Z (9 months ago)
- Language: TypeScript
- Homepage: https://www.turboseek.io/
- Size: 514 KB
- Stars: 754
- Watchers: 6
- Forks: 95
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- 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。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
- awesome - Nutlope/turboseek - An AI search engine inspired by Perplexity (TypeScript)
- jimsghstars - Nutlope/turboseek - An AI search engine inspired by Perplexity (TypeScript)
README
An open source AI search engine. Powered by Together.ai.
> If you want to learn how to build this, check out [**the tutorial**](https://docs.together.ai/docs/ai-search-engine)!
## Tech stack
- Next.js app router with Tailwind
- Together AI for LLM inference
- Llama 3.1 8B and 70B for the LLMs
- Bing / Serper API 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 Llama 3.1 70B with the user's question + context & stream it back to the user
5. Make another request to Llama 3.1 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://togetherai.link) 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
