update readme

Author: alrocar

.gitignore

@@ -1,2 +1,3 @@
+.DS_Store
 node_modules
 tinybird/mock/*.ndjson

README.md

@@ -1,21 +1,36 @@
 # AI Analytics Template
 
-This is a template for a Logs Explorer web application. It is built with Next.js and Tinybird.
+This is a template for an AI analytics dashboard and cost calculator. It is built with Next.js and [Tinybird](https://tinybird.co).
 
 Use this template to bootstrap a multi-tenant, user-facing LLM analytics dashboard and cost calculator. Fork it and make it your own!
 
+Features:
+
+- Multi-tenant user-facing dashboard
+- AI cost calculator
+- Vector search
+- Ask AI integration
+
+Stack:
+
+- [Next.js](https://nextjs.org/)
+- [Tinybird](https://tinybird.co)
+- [OpenAI](https://openai.com/)
+- [Vercel AI SDK](https://sdk.vercel.ai/docs/introduction)
+- [Clerk](https://clerk.com/)
+
 ## Live Demo
 
-https://ai-analytics.tinybird.app
+- https://ai-analytics.tinybird.app
 
-## Local Development
+## Quick Start
 
 Get started by forking the GitHub repository and then customizing it to your needs.
 
 Start Tinybird locally:
 
 ```
-curl -L https://tbrd.co/fwd | sh
+curl https://tinybird.co | sh
 cd tinybird
 tb local start
 tb login
@@ -32,8 +47,9 @@ Edit the .env file with your Tinybird API key and other configuration.
 ```
 
 ```
-NEXT_PUBLIC_TINYBIRD_API_KEY=<YOUR_TINYBIRD_READ_PIPES_TOKEN>
 NEXT_PUBLIC_TINYBIRD_API_URL=http://localhost:7181
+# read_pipes token
+NEXT_PUBLIC_TINYBIRD_API_KEY=
 ```
 
 Start the Next.js application:
@@ -50,4 +66,86 @@ Open the application in your browser:
 http://localhost:3000
 ```
 
-To use the AI features, click on Settings in the dashboard and in put an Open AI API key
+## Multi-tenancy
+
+Create a Clerk project and set up these environment variables in your Next.js application:
+
+```
+# workspace ID for multi-tenant JWT tokens
+TINYBIRD_WORKSPACE_ID=
+# workspace admin token for multi-tenant JWT tokens
+TINYBIRD_JWT_SECRET=
+
+# Clerk publishable key
+NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=
+# Clerk secret key
+CLERK_SECRET_KEY=
+# Clerk sign in URL
+NEXT_PUBLIC_CLERK_SIGN_IN_URL=/sign-in
+NEXT_PUBLIC_CLERK_SIGN_UP_URL=/sign-up
+NEXT_PUBLIC_CLERK_AFTER_SIGN_IN_URL=/
+NEXT_PUBLIC_CLERK_AFTER_SIGN_UP_URL=/
+```
+
+The [middleware](https://github.com/tinybirdco/ai-analytics-template/blob/main/dashboard/ai-analytics/src/middleware.ts) will get the `org:name` permission from the Clerk user and use it to create a Tinybird JWT token with the `organization` dimension fixed to that value. Read more about Tinybird JWT tokens [here](https://www.tinybird.co/docs/forward/get-started/authentication#json-web-tokens-jwts).
+
+[Watch a video of the Clerk + Tinybird JWT token flow](./assets/clerk-tinybird-jwt.mp4)
+
+## AI features
+
+To use the AI features, click on Settings in the dashboard and input an Open AI API key.
+
+See the `search` and `extract-cost-parameters` [API routes](https://github.com/tinybirdco/ai-analytics-template/tree/main/dashboard/ai-analytics/src/app/api) for more details on how the AI features work.
+
+[Watch a video of the AI cost calculator](./assets/ai-cost-calculator.mp4)
+
+## Vector search
+
+The vector search is powered by Tinybird, but embeddings need to be calculated in a separate process. See the [generate-embedding](https://github.com/tinybirdco/ai-analytics-template/blob/main/dashboard/ai-analytics/src/app/api/generate-embedding/route.ts) route for more details.
+
+The process is:
+
+- The user inputs a query and clicks the search button.
+- The query is sent to the `generate-embedding` route to get the embedding.
+- The embedding is sent to the Tinybird `llm_messages` as a query parameter.
+- `llm_messages` use `cosineDistance` to find the most similar vectors.
+- The frontend shows the table rows with the most similar vectors.
+
+## Deployment
+
+- Fork and connect this repository to Vercel.
+- Set the environment variables in Vercel.
+- Configure the [CI/CD GitHub actions](https://github.com/tinybirdco/ai-analytics-template/tree/main/.github/workflows) to deploy to Tinybird.
+
+## Instrumentation
+
+Check the examples folder for instrumentation examples for:
+
+- LiteLLM (python)
+- Vercel AI SDK (typescript)
+
+## Mock data
+
+For local testing, generate mock data with the following commands:
+
+```sh
+cd tinybird/mock
+npm install
+npm run generate -- --start-date 2025-02-01 --end-date 2025-03-31 --events-per-day 100 --output ../fixtures/llm_events.ndjson
+```
+
+The [generate-llm-events.js](https://github.com/tinybirdco/ai-analytics-template/blob/main/tinybird/mock/generate-llm-events.js) script generates the embeddings.
+
+## Contributing
+
+Please open an issue or submit a pull request.
+
+## Support
+
+Join the Tinybird Slack community to get help with your project.
+
+## License
+
+MIT License
+
+Copyright (c) 2025 Tinybird.co

assets/ai-cost-calculator.mp4

@@ -16,10 +16,6 @@ bun dev
 
 Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
 
-You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file.
-
-This project uses [`next/font`](https://nextjs.org/docs/app/building-your-application/optimizing/fonts) to automatically optimize and load [Geist](https://vercel.com/font), a new font family for Vercel.
-
 ## Learn More
 
 To learn more about Next.js, take a look at the following resources:

assets/clerk-tinybird-jwt.mp4

@@ -16,7 +16,7 @@ export default clerkMiddleware(async (auth) => {
     console.log('No user or session found')
 
     const response = NextResponse.next()
-    response.headers.set('x-tinybird-token', process.env.TINYBIRD_JWT_SECRET || '')
+    response.headers.set('x-tinybird-token', process.env.NEXT_PUBLIC_TINYBIRD_API_KEY || '')
     return response
   }
 
@@ -67,7 +67,7 @@ export default clerkMiddleware(async (auth) => {
   } catch (error) {
     console.error('Middleware error:', error)
     const response = NextResponse.next()
-    response.headers.set('x-tinybird-token', process.env.TINYBIRD_JWT_SECRET || '')
+    response.headers.set('x-tinybird-token', process.env.NEXT_PUBLIC_TINYBIRD_API_KEY || '')
     return response
   }
 })

dashboard/ai-analytics/README.md

@@ -0,0 +1,37 @@
+This is a [Tinybird project](https://www.tinybird.co/docs/forward) for the AI analytics template.
+
+It has a single table `llm_events` that stores LLM events with usage metrics, costs, and metadata.
+
+Endpoints:
+
+- `generic_counter` shows cost by several dimensions.
+- `llm_usage` is used to build time series charts.
+- `llm_messages` is used to build the vector search.
+
+## Local development
+
+Start Tinybird locally:
+
+```
+curl https://tinybird.co | sh
+cd tinybird
+tb local start
+tb login
+tb dev
+```
+
+Generate mock data:
+
+```
+cd tinybird/mock
+npm install
+npm run generate -- --start-date 2025-02-01 --end-date 2025-03-31 --events-per-day 100 --output ../fixtures/llm_events.ndjson
+```
+
+## Deploy to cloud
+
+Use the [CI/CD GitHub actions](https://github.com/tinybirdco/ai-analytics-template/tree/main/.github/workflows) in this repository to deploy to Tinybird or the Tinybird CLI:
+
+```
+tb --cloud deploy
+```