RAG Quickstart : with default settings

Getting your RAG application built in under 30 seconds.

1. Create a New RAG Application

From the RAG Applications dashboard, click Create.

Two options appear:

• Create with Default Settings — Recommended for your first app. This option auto-applies standard ingestion, chunking, and retrieval defaults so you can focus on naming your app, selecting an LLM, and providing data.

• Create with Custom Settings — Gives you full control over ingestion, chunking, vectorization, and retrieval. Best for advanced use cases.

Select Create with Default Settings.

2. Name Your Application and Select Your LLM

The Create RAG App form opens. Enter a name for your RAG application in the RAG Application Name field. The name must use only underscores (_) and alphanumeric characters.

Use descriptive names such as policy_app_v1 or review_retrieval_rag to make it easier to manage multiple RAG applications later.

Select the Large Language Model (LLM) — the AI model that generates answers — your application will use. If you have not configured an LLM yet, click the LLM configuration link (+) to set one up.

Supported providers include:

• OpenAI (e.g., GPT-4o, GPT-4.1, GPT-3.5 Turbo)

• Azure OpenAI Service

• Amazon Bedrock

• Hosted models such as LLaMA

• Gemini (Google) and others, depending on your deployment

3. Add Your Data Source

Provide the data the RAG app will index and retrieve from. Three options are available:

1. Pick from Data Storage — Use already-connected storage such as AWS S3, GCS, or internal databases. Supported file formats: PDF, Word, PowerPoint, Excel, Markdown, plain text.

2. Upload from Computer — Drag and drop or select files from your local machine. Size limit: 5 MB per file.

3. Links and Web Crawling — Crawl one or more URLs to extract text from public or authenticated web pages. Useful for documentation sites, FAQs, policy pages, or intranet knowledge bases.

Start with a few representative documents to validate your workflow before uploading large volumes.

The Create RAG App form — enter a name, select an LLM, and choose a data source

Option A: Pick from Data Storage

If you select Pick from Data Storage, choose the file format and the connected data storage to pull from.

Selecting Pick from Data Storage — choose file format and the target data storage

Select the File format from the dropdown. Supported formats include Audio/Video, Image, Excel, Markdown, PDF, Plain Text, and PowerPoint.

Select the file format — choose one or more types that match your source documents

After selecting a format, choose the Data Storage connector. The folder structure for the selected storage appears below. Expand folders to navigate to your data.

Select the data storage connector — the folder structure expands so you can navigate to your files

Select the files to include. Use the File pattern field to filter by filename. Check the files you want to index, then optionally enable Automatically add new files to keep the app updated as new documents arrive.

Select specific files from the connected storage — use the file pattern filter to narrow the list

Option B: Links and Web Crawling

If you select Links and Web Crawling, the form updates to show a web crawler configuration.

Links and Web Crawling — enter a URL and configure crawl scope and behaviour

Webpage URL (required) — Paste the URL of the website or page to crawl (for example, https://docs.example.com or https://company.com/policies).

Configure the crawl scope using the following options:

Option	Description
Protected URL	Check if the URL requires authentication. You will be prompted for credentials.
Crawl sub-domain	Also crawl pages under sub-domains of the root URL.
Javascript enabled for the website	Capture content that loads dynamically via JavaScript. Adds overhead but ensures dynamic pages are fully extracted.
Include path	An inclusion pattern (e.g., /docs/) to restrict crawling to specific URL paths.
Exclude path	An exclusion pattern (e.g., /blog/) to skip specific URL paths.
Use sitemap.xml	Use the site's sitemap to speed up page discovery.
Use robots text	Respect the site's robots.txt crawl instructions.

Advanced settings (optional) — expand to configure crawler behaviour and HTML processing.

Advanced settings — configure crawl depth, concurrency, and HTML extraction behaviour

Crawler Settings:

Setting	Description
Max crawling depth	How many link levels deep to follow from the starting URL.
Max pages	Maximum number of pages to crawl in a single run.
Max concurrency	Number of pages to crawl simultaneously.
Browser Caching	Reuse browser cache across requests to speed up crawling.
Enable rate limiting	Cap request frequency to avoid overloading the target server.
Crawler type	Select the crawl strategy suited to the site's structure.

HTML Processing:

Setting	Description
Wait for dynamic content (seconds)	Pause before extracting content so JavaScript has time to render.
Remove HTML element	Specify HTML tags or selectors to strip from extracted content (e.g., nav, footer).
Expand clickable elements	Attempt to expand collapsed tabs or accordions before extraction.
Remove cookie warning	Suppress cookie consent dialogs during crawling.
Save PDF/docx files	Download and ingest linked PDF or Word files discovered during the crawl.

Click Create App once the URL and crawl settings are configured.

4. Review and Create

Once your data source and LLM are configured, click Create App.

Your app appears in the RAG Applications dashboard with its name, creator, and status indicators for Ingestion, Vectorization, and Retrieval.

• Ingestion — whether your data was successfully pulled in

• Vectorization — whether embeddings were created

• Retrieval — whether queries can be run successfully

If any step has not started, click View Details to re-run ingestion or fix issues.

Example Use Case: Policy Document Retrieval

To build a policy assistant for employees, upload company policy PDFs into your RAG application:

• The LLM (for example, GPT-4o) handles natural language understanding.

• The retrieval pipeline fetches only relevant sections (for example, "What's the leave policy for probation employees?").

• Employees get precise, contextual answers instead of skimming long PDFs.

Key Notes

• Default settings handle chunking, embedding, and retrieval strategies automatically. You can switch to Custom Settings later for fine-tuning.

• Be aware of free-tier limits (file size, web crawling cap). For production, connect your own S3, MongoDB, or vector database.

• Do not upload sensitive data to the default workspace — configure secure storage first.