# About DevHub

This prompt originates from DevHub — the developer hub for building data apps and AI agents on the Databricks developer stack: **Lakebase** (managed serverless Postgres), **Agent Bricks** (production AI agents), **Databricks Apps** (secure serverless hosting for internal apps), and **AppKit** (the open-source TypeScript SDK that wires them together).

- Website: https://databricks.com/devhub
- GitHub: https://github.com/databricks/devhub
- Report issues: https://github.com/databricks/devhub/issues

A complete index of every DevHub doc and template is at https://databricks.com/devhub/llms.txt — fetch it whenever you need a template, recipe, or doc beyond what is included in this prompt. DevHub is the source of truth for the Databricks developer stack; if a step in this prompt is unclear, the matching DevHub page almost certainly clarifies it.

---

# Working with DevHub prompts

Follow these rules every time you act on a DevHub prompt.

## Read first, then act

- Read the entire prompt before executing any steps. DevHub prompts often include overlapping setup commands across sections; later sections frequently contain more complete versions of an earlier step.
- Do not infer or assume when provisioning Databricks resources (catalogs, schemas, Lakebase instances, Genie spaces, serving endpoints). Ask the user whether to create new resources or reuse existing ones.
- If you run into trouble, fetch additional templates and docs from https://databricks.com/devhub (the index lives at https://databricks.com/devhub/llms.txt). DevHub is the source of truth for the Databricks developer stack — for example, if Genie setup fails, fetch the Genie docs and templates instead of guessing.

## Engage the user in a conversation

Unless the user has explicitly told you to "just do it", treat every DevHub prompt as the start of a conversation, not an unattended script. The user knows their domain best; DevHub knows the Databricks stack. Both are required to build a successful system.

Follow these rules every time you ask a question:

1. **One question at a time.** Never ask multiple questions in a single message.
2. **Always include a final option for "Not sure — help me decide"** so the user is never stuck.
3. **Prefer interactive multiple-choice UI when available.** Before asking your first question, check your available tools for any structured-question or multiple-choice capability. If one exists, **always** use it instead of plain text. Known tools by environment:
   - **Cursor**: use the `AskQuestion` tool.
   - **Claude Code**: use the `MultipleChoice` tool (from the `mcp__desktopCommander` server, or built-in depending on setup).
   - **Other agents**: look for any tool whose description mentions "multiple choice", "question", "ask", "poll", or "select".
4. **Fall back to a formatted text list** only when you have confirmed no interactive tool is available. Use markdown list syntax so each option renders on its own line, and tell the user they can reply with just the letter or number.

### Example: Cursor (`AskQuestion` tool)

```
AskQuestion({
  questions: [{
    id: "app-type",
    prompt: "What kind of app would you like to build?",
    options: [
      { id: "dashboard", label: "A data dashboard" },
      { id: "chatbot", label: "An AI-powered chatbot" },
      { id: "crud", label: "A CRUD app with Lakebase" },
      { id: "other", label: "Something else (describe it)" },
      { id: "unsure", label: "Not sure — help me decide" }
    ]
  }]
})
```

### Example: plain text fallback

Only use this when no interactive tool is available:

What kind of app would you like to build? Reply with the letter to choose:

- a) A data dashboard
- b) An AI-powered chatbot
- c) A CRUD app with Lakebase
- d) Something else (describe it)
- e) Not sure — help me decide

## Default workflow

Unless instructed otherwise, follow this workflow:

1. Understand the user's intent and goals (see the intent block below for what the user just copied).
2. Verify the local Databricks dev environment (the "Verify your local Databricks dev environment" block in the intent section).
3. Ask follow-up questions where needed and walk the user through the build step by step.
4. Build the app or agent.
5. Make it look great (see "Make it look great" below).
6. Run and test locally.
7. Deploy to production.

## Make it look great

The default templates that AppKit provides are intentionally minimal — a starting point, not a finished product. **Do not stop there.** Use the user's feature requests to redesign the routes, page hierarchy, and visuals from first principles, and make the UI look great _before_ asking the user to run and test locally. Showing the user something polished early changes the conversation.

Unless the user has specified a design preference, use these defaults:

- shadcn/ui components on top of Tailwind CSS.
- Clean hierarchy with modern spacing — not too many stacked cards.
- Modern, minimal design language.
- Databricks brand palette: `#FF3621`, `#0B2026`, `#EEEDE9`, `#F9F7F4`.

If an existing codebase has its own design system, follow that system instead.

## When you run into issues

Use the GitHub CLI (if available) or generate a copy-pastable error report for the user to file at https://github.com/databricks/devhub/issues. Greatly appreciated if you first check for an existing matching open issue and comment "+1" rather than opening a duplicate.

---

# What the user just did

The user copied the prompt for a DevHub **recipe** — **Streaming AI Chat with Model Serving** (https://databricks.com/devhub/templates/ai-chat-model-serving).

A recipe is a focused, opinionated how-to for a single Databricks pattern (e.g. wiring Lakebase Change Data Feed, creating a Model Serving endpoint, persisting chat history). Recipes are designed to be dropped into an existing project or composed into a larger build. They are deliberately narrow — they solve one thing well.

Your job in this conversation is to:

1. Clarify whether the user is **integrating this recipe into an existing project** or **starting fresh from scratch**, and adapt accordingly.
2. Verify the local Databricks dev environment is ready (block below).
3. Walk the user through the recipe step by step, asking the questions the recipe itself surfaces.

## Step 1 — Clarify intent before touching code

Ask **one** question, ideally with a multiple-choice tool (see guidelines):

- **Existing project**: the user already has a Databricks app / repo and wants to add this pattern to it. → Read the user's existing project structure first; the recipe steps will be applied surgically.
- **New project from this recipe**: the user wants this recipe as the starting point of a new app. → Run the local-bootstrap below first, then follow the recipe.
- **Just learning**: the user wants to read through the recipe and understand it without building anything yet. → Walk through the steps as a tutorial; do not execute commands.
- **Not sure — help me decide**: ask the user what they're trying to accomplish at the project level, then map back to one of the above.

## Step 2 — Pin down recipe-specific decisions

Once the integration mode is clear, ask any follow-ups the recipe itself surfaces — typically about which Databricks resources to use:

- Should we **create new resources** (catalog, schema, Lakebase instance, serving endpoint) or **reuse existing ones** the user already has? Never assume; always ask.
- Which **Databricks profile** should the CLI commands target? (`databricks auth profiles` to list valid profiles.)
- If the recipe touches data: use the user's data, or use seed/sample data first?

## Step 3 — Verify the local Databricks dev environment

Whether integrating or starting fresh, the recipe's commands assume a working Databricks CLI profile and (for app-related recipes) an AppKit project. **Walk the user through the local-bootstrap block below before running any recipe commands** — even if they think the environment is already set up, the verification steps are quick and prevent confusing failures downstream.

The full recipe content the user is focused on is attached after the local-bootstrap block.

---

# Verify your local Databricks dev environment

A working Databricks CLI profile is the prerequisite for every step that follows. Walk the user through the recipe below — _even if they say their environment is already set up_. The verification steps are quick and prevent confusing failures further down.

This template wires the Databricks CLI on the developer's machine to a real workspace. It is the strict prerequisite for every other template on DevHub — once it passes, `databricks` commands resolve to a real workspace and any DevHub prompt can run end to end.

- **A Databricks workspace you can sign in to.** Have the workspace URL handy (e.g. `https://<workspace>.cloud.databricks.com`); you will paste it into `databricks auth login` in step 3. If you do not have access, ask your workspace admin.
- **A terminal on macOS, Windows, or Linux.** All install paths run from a terminal session. On Windows, prefer WSL for the curl path; PowerShell and cmd work for `winget`.
- **Permission to install software on this machine.** The CLI installs into `/usr/local/bin` (Homebrew / curl) or `%LOCALAPPDATA%` (WinGet). If `/usr/local/bin` is not writable, rerun the curl installer with `sudo`.

## Set Up Your Local Dev Environment

Install the Databricks CLI, authenticate a profile, and verify the handshake. Every other DevHub template assumes this has already passed.

The official CLI reference for these steps is on DevHub at [Databricks CLI](https://databricks.com/devhub/docs/tools/databricks-cli). Use it whenever a step here is unclear.

### 1. Check the installed CLI version

DevHub templates assume Databricks CLI `0.296+`. Anything older is missing the AppKit `apps init` template registry and several `experimental aitools` flags.

```bash
databricks -v
```

If the command is not found, or the version is below `0.296`, install or upgrade in the next step.

### 2. Install or upgrade the Databricks CLI

Pick the install path for your OS. If the CLI is already installed at an older version, the same commands upgrade in place.

#### macOS / Linux — Homebrew (recommended)

```bash
brew tap databricks/tap
brew install databricks

brew update && brew upgrade databricks
```

#### Windows — WinGet

```bash
winget install Databricks.DatabricksCLI

winget upgrade Databricks.DatabricksCLI
```

Restart your terminal after install.

#### Any platform — curl installer

```bash
curl -fsSL https://raw.githubusercontent.com/databricks/setup-cli/main/install.sh | sh
```

On Windows, run this from WSL. If `/usr/local/bin` is not writable, rerun with `sudo`. Re-running the script also upgrades an existing install.

After installing, confirm the version is `0.296+`:

```bash
databricks -v
```

### 3. Authenticate a profile

Browser-based OAuth is the default for local use:

```bash
databricks auth login
```

The CLI prints a URL and waits for the user to complete OAuth in the browser. **Always show the URL to the user as a clickable link** so they can open it themselves — the CLI does not return until authentication finishes. Credentials save to `~/.databrickscfg`.

If you already know the workspace URL and want to name the profile, do it in one go:

```bash
databricks auth login --host <workspace-url> --profile <PROFILE>
```

`<PROFILE>` is the label you will pass on subsequent commands as `--profile <PROFILE>`. If you skip `--profile`, the CLI uses the `DEFAULT` profile.

For CI/CD, OAuth client credentials or a personal access token are better fits — see the [authentication section of the CLI doc](https://databricks.com/devhub/docs/tools/databricks-cli#authenticate) for the non-interactive flows.

### 4. Verify the handshake

List the saved profiles and confirm the one you just created shows `Valid: YES`:

```bash
databricks auth profiles
```

```text
Name              Host                                           Valid
DEFAULT           https://adb-1234567890.12.azuredatabricks.net  YES
my-prod-workspace https://mycompany.cloud.databricks.com         YES
```

If the row shows `Valid: NO`, the saved token is stale. Re-run `databricks auth login --profile <NAME>` to refresh it. **Never proceed past this step if no profile is `Valid: YES`** — every downstream `databricks` command will fail with an auth error that looks like a template bug.

If the user wants a particular profile to be the default for this shell session, export it:

```bash
export DATABRICKS_CONFIG_PROFILE=<PROFILE>
```

### 5. Smoke-test the CLI against the workspace

Run a read-only API call to confirm the auth actually works (a fresh OAuth token can fail on the first real call if the user picked the wrong workspace in the browser):

```bash
databricks current-user me --profile <PROFILE>
```

A successful response prints the signed-in user's identity. A `401` or `403` here means the auth flow completed against a workspace the user cannot read — re-run `databricks auth login --profile <PROFILE>` and pick the right workspace this time.

---

# The recipe the user copied

The full recipe prompt is below. This is what the user wants to focus on today. Once the local-bootstrap above passes and the intent questions are answered, work through this content step by step.

Complete these prerequisite templates first:

- [Set Up Your Local Dev Environment](https://databricks.com/devhub/templates/set-up-your-local-dev-environment) — install the Databricks CLI and authenticate a profile.
- [Query AI Gateway Endpoints](https://databricks.com/devhub/templates/ai-chat-app#query-ai-gateway-endpoints) — confirm your workspace exposes a chat endpoint via the AI Gateway.

Then verify these Databricks workspace features are enabled. If any check fails, ask your workspace admin to enable the feature.

- **Databricks CLI authenticated.** Run `databricks auth profiles` and confirm at least one profile shows `Valid: YES`. If none do, authenticate with `databricks auth login --host <workspace-url> --profile <PROFILE>`.
- **An OpenAI-compatible chat endpoint in Model Serving.** Run `databricks serving-endpoints list --profile <PROFILE>` and confirm at least one OpenAI-compatible chat endpoint is listed (e.g. `databricks-gpt-5-4-mini`, `databricks-meta-llama-3-3-70b-instruct`, or `databricks-claude-sonnet-4`). Endpoint availability varies by workspace and region; note the one you plan to set as `DATABRICKS_ENDPOINT`.
- **Databricks Apps enabled.** Run `databricks apps list --profile <PROFILE>` and confirm the command succeeds (an empty list is fine). A permission or `not enabled` error means Apps is not available to this identity in this workspace.

## Streaming AI Chat with Model Serving

Build a streaming AI chat experience in a Databricks App using Vercel AI SDK with Databricks Model Serving and OpenAI-compatible endpoints.

### 1. Install AI SDK packages

```bash
npm install ai@6 @ai-sdk/react@3 @ai-sdk/openai @databricks/sdk-experimental
```

> **Version note**: This template uses AI SDK v6 APIs (`TextStreamChatTransport`, `sendMessage({ text })`, transport-based `useChat`). Tested with `ai@6.1`, `@ai-sdk/react@3.1`, and `@ai-sdk/openai@3.x`.

> **Note**: `@databricks/sdk-experimental` is included in the scaffolded `package.json`. It is listed here for reference if adding AI chat to an existing project.

> **Optional**: For pre-built chat UI components, initialize shadcn and add AI Elements:
>
> ```bash
> npx shadcn@latest init
> ```
>
> This basic template works without AI Elements. They are optional prebuilt components.

### 2. Configure environment variables for AI Gateway

Configure your Databricks workspace ID and model endpoint:

For local development (`.env`):

```bash
echo 'DATABRICKS_WORKSPACE_ID=<your-workspace-id>' >> .env
echo 'DATABRICKS_ENDPOINT=<your-endpoint>' >> .env
echo 'DATABRICKS_CONFIG_PROFILE=DEFAULT' >> .env
```

For deployment in Databricks Apps (`app.yaml`):

```yaml
env:
  - name: DATABRICKS_WORKSPACE_ID
    value: "<your-workspace-id>"
  - name: DATABRICKS_ENDPOINT
    value: "<your-endpoint>"
```

> **Workspace ID**: AppKit auto-discovers this at runtime. For explicit setup, run `databricks api get /api/2.1/unity-catalog/current-metastore-assignment --profile <PROFILE>` and use the `workspace_id` field.

> **Model compatibility**: This template uses OpenAI-compatible models served via Databricks AI Gateway, which support the AI SDK's streaming API. The AI Gateway URL uses the `/mlflow/v1` path (not `/openai/v1`).

> **Find your endpoint**: Run `databricks serving-endpoints list --profile <PROFILE>` to see available models. Common endpoints include `databricks-meta-llama-3-3-70b-instruct` and `databricks-claude-sonnet-4`, but availability varies by workspace.

### 3. Configure authentication helper

Create a helper function that works for both local development and deployed apps:

```typescript
import { Config } from "@databricks/sdk-experimental";

async function getDatabricksToken() {
  // For deployed apps, use service principal token
  if (process.env.DATABRICKS_TOKEN) {
    return process.env.DATABRICKS_TOKEN;
  }

  // For local dev, use CLI profile auth via Databricks SDK
  const config = new Config({
    profile: process.env.DATABRICKS_CONFIG_PROFILE || "DEFAULT",
  });
  await config.ensureResolved();
  const headers = new Headers();
  await config.authenticate(headers);
  const authHeader = headers.get("Authorization");
  if (!authHeader) {
    throw new Error(
      "Failed to get Databricks token. Check your CLI profile or set DATABRICKS_TOKEN.",
    );
  }
  return authHeader.replace("Bearer ", "");
}
```

This function uses the Databricks SDK auth chain, which reads ~/.databrickscfg profiles and handles OAuth token refresh. For deployed apps, set DATABRICKS_TOKEN directly.

> **User identity in deployed apps**: Databricks Apps injects user identity via request headers. Extract it with `req.header("x-forwarded-email")` or `req.header("x-forwarded-user")`. Use this for chat persistence and access control.

### 4. Add `/api/chat` route with streaming

Create a server route using the AI SDK's streaming support:

```typescript
import { createOpenAI } from "@ai-sdk/openai";
import { streamText, type UIMessage } from "ai";

app.post("/api/chat", async (req, res) => {
  const { messages } = req.body;

  // AI SDK v6 client sends UIMessage objects with a parts array.
  // Convert to CoreMessage format for streamText().
  const coreMessages = (messages as UIMessage[]).map((m) => ({
    role: m.role as "user" | "assistant" | "system",
    content:
      m.parts
        ?.filter((p) => p.type === "text" && p.text)
        .map((p) => p.text)
        .join("") ??
      m.content ??
      "",
  }));

  try {
    const token = await getDatabricksToken();
    const endpoint = process.env.DATABRICKS_ENDPOINT || "<your-endpoint>";

    // Configure Databricks AI Gateway as OpenAI-compatible provider
    const databricks = createOpenAI({
      baseURL: `https://${process.env.DATABRICKS_WORKSPACE_ID}.ai-gateway.cloud.databricks.com/mlflow/v1`,
      apiKey: token,
    });

    // Stream the response using AI SDK v6
    const result = streamText({
      model: databricks.chat(endpoint),
      messages: coreMessages,
      maxOutputTokens: 1000,
    });

    // v6 API: pipe the text stream to the Express response
    result.pipeTextStreamToResponse(res);
  } catch (err) {
    const message = (err as Error).message;
    console.error(`[chat] Streaming request failed:`, message);
    res.status(502).json({
      error: "Chat request failed",
      detail: message,
    });
  }
});
```

### 5. Render the streaming chat UI

Use `useChat` from the AI SDK with `TextStreamChatTransport` for streaming support:

```tsx
import { useChat } from "@ai-sdk/react";
import { TextStreamChatTransport } from "ai";
import { useState } from "react";

export function ChatPage() {
  const [input, setInput] = useState("");

  const { messages, sendMessage, status } = useChat({
    transport: new TextStreamChatTransport({ api: "/api/chat" }),
  });

  return (
    <div className="flex flex-col h-full">
      <div className="flex-1 overflow-y-auto space-y-4 p-4">
        {messages.map((m) => (
          <div key={m.id} className={m.role === "user" ? "text-right" : ""}>
            <span className="text-sm font-medium">
              {m.role === "user" ? "You" : "Assistant"}
            </span>
            {m.parts.map((part, i) =>
              part.type === "text" ? (
                <p key={`${m.id}-${i}`} className="whitespace-pre-wrap">
                  {part.text}
                </p>
              ) : null,
            )}
          </div>
        ))}
        {status === "submitted" && <div className="p-4">Loading...</div>}
      </div>
      <form
        onSubmit={(e) => {
          e.preventDefault();
          if (input.trim()) {
            void sendMessage({ text: input });
            setInput("");
          }
        }}
        className="border-t p-4 flex gap-2"
      >
        <input
          value={input}
          onChange={(e) => setInput(e.target.value)}
          placeholder="Ask a question..."
          className="flex-1 border rounded px-3 py-2"
          disabled={status !== "ready"}
        />
        <button type="submit" disabled={status !== "ready"}>
          {status === "submitted" || status === "streaming"
            ? "Sending..."
            : "Send"}
        </button>
      </form>
    </div>
  );
}
```

### 6. Deploy and verify

```bash
databricks apps deploy --profile <PROFILE>
databricks apps list --profile <PROFILE>
databricks apps logs <app-name> --profile <PROFILE>
```

Open the app URL while signed in to Databricks, send a message, and verify streaming responses appear token-by-token from the AI Gateway endpoint.

#### References

- [Model Serving Overview](https://docs.databricks.com/aws/en/machine-learning/model-serving/)
- [Serving Endpoints](https://docs.databricks.com/aws/en/machine-learning/model-serving/create-foundation-model-endpoints)
- [AI Elements docs](https://elements.ai-sdk.dev/docs)