vercel-labs / gemini-chatbot Goto Github PK

View Code? Open in Web Editor NEW

636.0 11.0 191.0 10.45 MB

Build your own generative UI chatbot using the Vercel AI SDK and Google Gemini

Home Page: https://gemini.vercel.ai

License: Other

TypeScript 98.90% CSS 0.62% JavaScript 0.48%

ai chatbot gemini-pro nextjs react typescript vercel

gemini-chatbot's Introduction

Next.js 14 and App Router-ready AI chatbot.

Next.js AI Chatbot

An open-source AI chatbot app template built with Next.js, the Vercel AI SDK, Google Gemini, and Vercel KV.

Features · Model Providers · Deploy Your Own · Running locally · Authors

Features

Next.js App Router
React Server Components (RSCs), Suspense, and Server Actions
Vercel AI SDK for streaming chat UI
Support for Google Gemini (default), OpenAI, Anthropic, Cohere, Hugging Face, or custom AI chat models and/or LangChain
shadcn/ui
- Styling with Tailwind CSS
- Radix UI for headless component primitives
- Icons from Phosphor Icons
Chat History, rate limiting, and session storage with Vercel KV
NextAuth.js for authentication

Model Providers

This template ships with Google Gemini models/gemini-1.0-pro-001 as the default. However, thanks to the Vercel AI SDK, you can switch LLM providers to OpenAI, Anthropic, Cohere, Hugging Face, or using LangChain with just a few lines of code.

Deploy Your Own

You can deploy your own version of the Next.js AI Chatbot to Vercel with one click:

Running locally

You will need to use the environment variables defined in .env.example to run Next.js AI Chatbot. It's recommended you use Vercel Environment Variables for this, but a .env file is all that is necessary.

Note: You should not commit your .env file or it will expose secrets that will allow others to control access to your various Google Cloud and authentication provider accounts.

Install Vercel CLI: npm i -g vercel
Link local instance with Vercel and GitHub accounts (creates .vercel directory): vercel link
Download your environment variables: vercel env pull

pnpm install
pnpm dev

Your app template should now be running on localhost:3000.

Authors

This library is created by Vercel and Next.js team members, with contributions from:

Jared Palmer (@jaredpalmer) - Vercel
Shu Ding (@shuding_) - Vercel
shadcn (@shadcn) - Vercel
Jeremy Philemon (@jrmyphlmn) - Vercel

gemini-chatbot's People

Contributors

Stargazers

Watchers

Forkers

cosmoops-com devfaraaz mrmps zavier-sanders xahidex sunny0183 abilovelchin heatherb100 aldoyh cs50victor lyong9102 sijan2 rossman22590 kingchary ederekgithub rosemarysalem robcodehub sachinjadeja satvik314 saravansg raghavghattu ozamamurzleen rendermaestro christoph-gl b0kic4 charlypoly beimingmaster coradinibr mlavinb ruru-m07 jpaddeo merzge brijr dalaohuvpn nite-knite iwillcodeu abdalhadi21 tranbavinhson snake-git stuartakeero discoverlance-com fansidele omidshabab smadikanti yacineali74 romandimitri clic-ethiopia fmbento henri-edh chinpeerapat dev-kalavadia cjdcjd10021 facundoinza spookymargiela007 irodneyedwards devsanantonio yoni-klain ceoaitek2023 additor apatwary12 bestfriendai vienpt saotv jetqin williamwrathborne zbeyens metacode0602 haribukke 97revenge aviv-anthonnyolime suleimanabubakar researchaigc sherry2869 bhogeshwarj mehran9 arielcohen4 rrsartneoai maxtimer-hui maxdata ydideh810 roshankainee fancyfoot couragefalco vistritpandey swilliams13 agentofasgard cyberbuck sachins0 drakeyxyxyxyxy abil-shrestha tsounguinzo soumyach youngtiger1 deepak-jha-kgp cynthia427 saleskit24 plummycat calebrlx ashye cfofiu

gemini-chatbot's Issues

Why isn't `streamUI` used?

Hi, thanks for this work.

I'm trying to reconcile this implementation with the docs and am wondering why the streamUi method is not used. Instead, streamText is used and then its result is analyzed within a large if-else block where the correct UI is then sent via a stream created via createStreamableUI. Wouldn't streamUI have been cleaner, where the various tools could have been defined alongside their respective generate functions?

Thanks!

Logged In features not working

when logged in the generations dont work sometimes, is there a way to create a fall back? How can we save the chat histroy?

vercel deploy failed

404 Page

It looks like this when I go to page that is does not exist, I think you should make one or delete the nav for it.

TS no check on actions page

Is gemini not fully supported for generative UI? Could we fix this page to be type safe?

fetch failed?

⨯ node_modules/.pnpm/[email protected][email protected][email protected]/node_modules/next/dist/compiled/react/cjs/react.shared-subset.development.js (182:0) @ fetch
⨯ fetch failed

Amazing app integration with Gemini!

I'm curious, I'm trying to find where the prompt for the AI in the code and also where we can modify it or change it into something else like a medical web-app etc.

How to have a normal inference?

What to modiify to have a normal inference with an arbitrary prompt?

feat: Implement Dark Mode Support

Digest error for fine tuned models

I am getting this error every time a chat is sent.

Oops, something went wrong!
An error occurred in the Server Components render. The specific message is omitted in production builds to avoid leaking sensitive details. A digest property is included on this error instance which may provide additional details about the nature of the error.
Digest: 4232900919

Since there are no instructions on where or how to change the model, I was only able to locate one instantiation of Gemini in the lib/utils/actions.TS which only included Gemini pro vision for the flight ticket action. I think this is causing the air, but I can't be certain.