Quick Start
Get your first knowledge base up and running in just a few steps.
Create a Project
Sign up for a free account and create your first project from the dashboard. Each project is an isolated knowledge base with its own sources and API keys.
Add Your Data
Upload documents, paste text, or crawl a website. VectorBase automatically processes your content, creates embeddings, and indexes everything for semantic search.
Generate an API Key
Go to the API Keys section in your project settings and create a new key. This key authenticates your API requests.
Query Your Knowledge Base
Use the REST API to search and chat with your knowledge base:
curl -X POST https://api.vectorbase.dev/v1/query \
-H "Authorization: Bearer vb_sk_..." \
-H "Content-Type: application/json" \
-d '{
"query": "How do I reset my password?",
"top_k": 5,
"threshold": 0.5
}'API Reference
VectorBase provides a REST API for all operations. All requests require authentication via Bearer token.
/api/v1/queryPerform semantic search across your knowledge base. Returns the most relevant chunks based on vector similarity.
curl -X POST https://api.vectorbase.dev/v1/query \
-H "Authorization: Bearer vb_sk_..." \
-H "Content-Type: application/json" \
-d '{
"query": "How do I reset my password?",
"top_k": 5,
"threshold": 0.5
}'/api/v1/chatRAG-powered chat endpoint. Automatically retrieves relevant context and generates AI responses with source citations.
curl -X POST https://api.vectorbase.dev/v1/chat \
-H "Authorization: Bearer vb_sk_..." \
-H "Content-Type: application/json" \
-d '{
"messages": [
{"role": "user", "content": "What are the pricing plans?"}
],
"stream": true
}'/api/v1/sourcesCreate a new source in your project. Sources can be text, Q&A pairs, websites, or documents.
curl -X POST https://api.vectorbase.dev/v1/sources \
-H "Authorization: Bearer vb_sk_..." \
-H "Content-Type: application/json" \
-d '{
"type": "text",
"name": "Company FAQ",
"content": "Your text content here..."
}'Rate Limits
API requests are rate-limited to 60 requests per minute per project. Rate limit headers are included in all responses:
X-RateLimit-Limit: Maximum requests per windowX-RateLimit-Remaining: Requests remaining in current windowX-RateLimit-Reset: Unix timestamp when the window resets