Add knowledge to your app

Add private knowledge to your AI in 3 API calls — no vector database setup, no embedding configuration.

1. Ingest a document

   From a URL:

   curl -X POST https://app.neureus.ai/rag/ingest \
     -H "Authorization: Bearer nru_your_key" \
     -H "Content-Type: application/json" \
     -d '{"url": "https://example.com/your-document.pdf"}'

   Or raw text:

   curl -X POST https://app.neureus.ai/rag/ingest \
     -H "Authorization: Bearer nru_your_key" \
     -H "Content-Type: application/json" \
     -d '{"content": "Our refund policy: customers may return items within 30 days...", "title": "Refund Policy"}'

   Response:

   { "documentId": "doc_abc123", "chunks": 12, "status": "indexed" }

2. Query semantically

   curl -X POST https://app.neureus.ai/rag/query \
     -H "Authorization: Bearer nru_your_key" \
     -H "Content-Type: application/json" \
     -d '{"query": "What is the return window?", "topK": 3}'

   Response includes matched chunks and their source documents:

   {
     "results": [
       {
         "content": "customers may return items within 30 days...",
         "documentId": "doc_abc123",
         "score": 0.94
       }
     ]
   }

3. List and delete documents

   # List all ingested documents
   curl https://app.neureus.ai/rag/documents \
     -H "Authorization: Bearer nru_your_key"
   
   # Delete a document and all its chunks
   curl -X DELETE https://app.neureus.ai/rag/documents/doc_abc123 \
     -H "Authorization: Bearer nru_your_key"

Using the SDK

import { Neureus } from '@neureus/sdk';

const client = new Neureus({ apiKey: process.env.NEUREUS_API_KEY! });

// Ingest
const { documentId } = await client.rag.ingest({
  content: 'Your document text here...',
  title: 'My Document',
});

// Query
const results = await client.rag.query({
  query: 'What does it say about returns?',
  topK: 5,
});

console.log(results[0].content);

Supported document types

URLs pointing to: PDF, DOCX, HTML, Markdown, plain text. Raw content string accepts any text.