Improve README

sky-dust-intelligence · Oct 5, 2023 · 0519ac9 · 0519ac9
1 parent fd0f342
commit 0519ac9
Showing 1 changed file with 16 additions and 18 deletions.
diff --git a/README.md b/README.md
@@ -21,32 +21,18 @@
 - [Next.js](https://nextjs.org) App Router
 - React Server Components (RSCs), Suspense, and Server Actions
 - [Vercel AI SDK](https://sdk.vercel.ai/docs) for streaming chat UI
-- Support for OpenAI (default), Anthropic, Hugging Face, or custom AI chat models and/or LangChain
+- [Humanloop](https://humanloop.com) integration for observability, logging and monitoring
 - Edge runtime-ready
 - [shadcn/ui](https://ui.shadcn.com)
   - Styling with [Tailwind CSS](https://tailwindcss.com)
   - [Radix UI](https://radix-ui.com) for headless component primitives
   - Icons from [Phosphor Icons](https://phosphoricons.com)
 
-## Model Providers
-
-This template ships with OpenAI `gpt-3.5-turbo` as the default. However, thanks to the [Vercel AI SDK](https://sdk.vercel.ai/docs), you can switch LLM providers to [Anthropic](https://anthropic.com), [Hugging Face](https://huggingface.co), or using [LangChain](https://js.langchain.com) 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:
-
-[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?demo-title=Next.js+Chat&demo-description=A+full-featured%2C+hackable+Next.js+AI+chatbot+built+by+Vercel+Labs&demo-url=https%3A%2F%2Fchat.vercel.ai%2F&demo-image=%2F%2Fimages.ctfassets.net%2Fe5382hct74si%2F4aVPvWuTmBvzM5cEdRdqeW%2F4234f9baf160f68ffb385a43c3527645%2FCleanShot_2023-06-16_at_17.09.21.png&project-name=Next.js+Chat&repository-name=nextjs-chat&repository-url=https%3A%2F%2Fgithub.com%2Fvercel-labs%2Fai-chatbot&from=templates&skippable-integrations=1&env=OPENAI_API_KEY%2CAUTH_GITHUB_ID%2CAUTH_GITHUB_SECRET%2CAUTH_SECRET&envDescription=How+to+get+these+env+vars&envLink=https%3A%2F%2Fgithub.com%2Fvercel-labs%2Fai-chatbot%2Fblob%2Fmain%2F.env.example&teamCreateStatus=hidden&stores=[{"type":"kv"}])
-
 ## Running locally
 
-You will need to use the environment variables [defined in `.env.example`](.env.example) to run Next.js AI Chatbot. It's recommended you use [Vercel Environment Variables](https://vercel.com/docs/concepts/projects/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 OpenAI and authentication provider accounts.
+You will need to populate the two evironment variables shown in `.env.example`. Copy this file to a file called `.env`. You can retrieve you OpenAI API key [here](https://platform.openai.com/account/api-keys) and your Humanloop API key [here](https://app.humanloop.com/account/api-keys).
 
-1. Install Vercel CLI: `npm i -g vercel`
-2. Link local instance with Vercel and GitHub accounts (creates `.vercel` directory): `vercel link`
-3. Download your environment variables: `vercel env pull`
+To run the application locally, simply run:
 
 ```bash
 npm install
@@ -55,6 +41,18 @@ npm run dev
 
 Your app template should now be running on [localhost:3000](http://localhost:3000/).
 
+## Humanloop
+
+In `app/api/chat/route.ts`, LLM chat calls are made via Humanloop's TypeScript SDK. Note that this file is an example of a Next.js [Route Handler](https://nextjs.org/docs/app/building-your-application/routing/route-handlers). This means it will run server-side, and therefore does not expose your OpenAI and Humanloop API keys to the client. This backend Route Handler is called from `components/chat.tsx` with the Vercel SDK's `useChat` hook.
+
+After sending and receiving some chat messages in your app, visit the [Humanloop app](https://app.humnaloop.com), and you will see a project called `sdk-example`. Visit the `Logs` tab and you will find all the chat histories from your running application.
+
+## Deploy Your Own
+
+You can deploy your own version of the Next.js AI Chatbot to Vercel with one click:
+
+[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?demo-title=Next.js+Chat&demo-description=A+full-featured%2C+hackable+Next.js+AI+chatbot+built+by+Vercel+Labs&demo-url=https%3A%2F%2Fchat.vercel.ai%2F&demo-image=%2F%2Fimages.ctfassets.net%2Fe5382hct74si%2F4aVPvWuTmBvzM5cEdRdqeW%2F4234f9baf160f68ffb385a43c3527645%2FCleanShot_2023-06-16_at_17.09.21.png&project-name=Next.js+Chat&repository-name=nextjs-chat&repository-url=https%3A%2F%2Fgithub.com%2Fvercel-labs%2Fai-chatbot&from=templates&skippable-integrations=1&env=OPENAI_API_KEY%2CAUTH_GITHUB_ID%2CAUTH_GITHUB_SECRET%2CAUTH_SECRET&envDescription=How+to+get+these+env+vars&envLink=https%3A%2F%2Fgithub.com%2Fvercel-labs%2Fai-chatbot%2Fblob%2Fmain%2F.env.example&teamCreateStatus=hidden&stores=[{"type":"kv"}])
+
 ## Authors
 
 Credit for the foundational design, app, and implementation is due to [Vercel](https://vercel.com) and their [AI Chatbot Template](https://github.com/vercel-labs/ai-chatbot) with contributions from:
@@ -63,4 +61,4 @@ Credit for the foundational design, app, and implementation is due to [Vercel](h
 - Shu Ding ([@shuding\_](https://twitter.com/shuding_)) - [Vercel](https://vercel.com)
 - shadcn ([@shadcn](https://twitter.com/shadcn)) - [Contractor](https://shadcn.com)
 
-We've mostly just ripped out the good (but more complicated) auth and KV store, and powered the AI chatbot with [Humanloop](https://humanloop.com) to make it easier to customise, evaluate and improve the underlying AI.
+We've mostly just ripped out the good (but more complicated) auth and KV store, and powered the AI chatbot with [Humanloop](https://humanloop.com) to make it easier to customise, evaluate and improve the underlying AI.