Inline Citations Demo
Inline Citations Demo
Generate content with embedded citations and clickable references. Includes source verification and formatting for research writing.
Problems solved
- Render research answers with inline citation components
- Map cited sources to clickable references in the UI
- Support fact-checked writing workflows in chat
Use cases
- Academic writing assistants
- Research content creation tools
- Policy briefs with source footnotes
- Journalism drafts that keep citations inline
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: OPENAI_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
OPENAI_API_KEYGet key
Capabilities
AI SDK APIs
streamObjectProviders
Files added
7 filesapp/page.tsxapp/layout.tsxlib/request-utils.tslib/schema.tscomponents/inline-citation-demo.tsxapp/api/citation/route.tsREADME.md
Dependencies
8 totalnpm packages
5
Registry components
Critical files
citation/route.tsAPI route implementing AI citation generation: uses streamObject with a citationSchema to generate content with inline numbered citations and real source URLs.
lib/schema.tsDefines the citationSchema used by streamObject: structured output with content string and citations array (number, title, url, description, quote).
Requirements
- Complexity
- Beginner
- Setup time
- ~15 minutes
- Node
- 24+
- Memory
- 512MB









