Create a Knowledge Base

Index your documents for semantic search and retrieval-augmented generation. Knowledge bases chunk, embed, and store your content for fast vector similarity search.

Knowledge bases give your AI agents the ability to search and retrieve relevant information from your documents. This guide walks through creating a KB, adding a source, waiting for indexing, and testing semantic search.

Prerequisites:

• A completed source (see Upload a Document guide)

1. Create the knowledge base

   Choose a name and indexing strategy. The default strategy works well for most documents.

   Endpoint: POST /api/knowledge-bases

   Python

   response = requests.post(
       f"{BASE_URL}/api/knowledge-bases",
       headers=headers,
       json={
           "name": "Product Docs",
           "description": "Product documentation and guides",
       },
   )
   kb = response.json()
   kb_id = kb["id"]
   print(f"KB created: {kb_id}")
   

   Response:

   {
     "id": "kb-uuid",
     "name": "Product Docs",
     "description": "Product documentation and guides",
     "created_at": "2026-01-01T00:00:00Z"
   }
   
2. Add a source to the knowledge base

   Link an uploaded source (from the previous guide) to trigger indexing. The source’s extracted content is chunked, embedded, and stored.

   Endpoint: POST /api/knowledge-bases/{id}/sources

   Indexing runs asynchronously. For large documents this can take 30 seconds or more.

   Python

   response = requests.post(
       f"{BASE_URL}/api/knowledge-bases/{kb_id}/sources",
       headers=headers,
       json={"source_id": source_id},
   )
   print(response.json())
   
3. Check indexing status

   Fetch the knowledge base to see the status of each indexed source. Wait until all sources show ‘indexed’.

   Endpoint: GET /api/knowledge-bases/{id}

   Python

   response = requests.get(
       f"{BASE_URL}/api/knowledge-bases/{kb_id}",
       headers=headers,
   )
   kb = response.json()
   for src in kb.get("indexed_sources", []):
       print(f"Source {src['source_id']}: {src['index_status']}")
   
4. Test search

   Run a semantic search query against the knowledge base to verify indexing worked.

   Endpoint: POST /api/knowledge-bases/{id}/search

   Python

   response = requests.post(
       f"{BASE_URL}/api/knowledge-bases/{kb_id}/search",
       headers=headers,
       json={"query": "How do I get started?", "top_k": 5},
   )
   results = response.json()
   for r in results.get("results", []):
       print(f"Score: {r['score']:.3f} — {r['text'][:80]}...")
   

What’s Next

Build an Agent

Create an agent that uses your knowledge base.

Knowledge Bases & Indexing

Deep dive into chunking and embeddings.

Knowledge Bases API Reference

Full endpoint documentation.