RAG Search

Build a knowledge-based AI assistant.

Upload a file, split it into chunks, and prepare it for retrieval. This is the first real step in a RAG pipeline.

Upload document

Supported formats: PDF, TXT, MD

No file selected yet.

Pipeline preview

Right now we are handling ingestion. Retrieval and answer generation come next.

1. Upload file
2. Extract text
3. Split into chunks
4. Create embeddings
5. Retrieve relevant chunks
6. Generate grounded answer

Chunk results

0 chunks

After upload, the generated chunks will appear here.

No chunks yet. Upload a file to see processed text segments.