This is a LlamaIndex project using Next.js that is ejected from llamaindex-server via npm eject command.

npm install
npm run dev

Open http://localhost:3000 with your browser to see the result.

The same as llamaindex-server, you can customize the application via .env file.

Here's the examples of how to migrate from LlamaIndexServer configs to Next.js project:

// src/index.ts
new LlamaIndexServer({
  workflow: workflowFactory,
  suggestNextQuestions: true,
  uiConfig: {
    devMode: true,
    llamaCloudIndexSelector: true,
    starterQuestions: ["Summarize the document", "What are the key points?"],
    componentsDir: "components",
    layoutDir: "layout",
  },
}).start();

.env file:

SUGGEST_NEXT_QUESTIONS=true # Whether to suggest next questions (`suggestNextQuestions`)
COMPONENTS_DIR=components # Directory for custom components (`componentsDir`)

NEXT_PUBLIC_DEV_MODE=true # Whether to enable dev mode (`devMode`)
NEXT_PUBLIC_STARTER_QUESTIONS=[] # Initial questions to display in the chat (`starterQuestions`)
NEXT_PUBLIC_SHOW_LLAMACLOUD_SELECTOR=true # Whether to show LlamaCloud selector for frontend (`llamaCloudIndexSelector`)
NEXT_PUBLIC_USE_COMPONENTS_DIR=true # Whether to use components directory for frontend

For customizing layout, you can directly edit the layout files in the generated nextjs project (app/components/ui/chat/layout).

• Generate Datasource (in case having ./data folder): npm run generate
• Typecheck: npm run typecheck
• Lint: npm run lint
• Format: npm run format
• Build & Start: npm run build && npm run start

To learn more about LlamaIndex, take a look at the following resources:

• LlamaIndex Documentation - learn about LlamaIndex (Python features).
• LlamaIndexTS Documentation - learn about LlamaIndex (Typescript features).

You can check out the LlamaIndexTS GitHub repository - your feedback and contributions are welcome!