Introduction
Welcome to Cortefy - a powerful semantic memory API that enables you to store, search, and retrieve information using vector embeddings and semantic similarity.
What is Cortefy?
Cortefy is a semantic memory API that allows you to:
- Ingest text content and automatically chunk it into searchable memories
- Search your memories using semantic similarity (vector search)
- Organize memories into containers for better organization
- Scale with async embedding generation and efficient vector storage
Key Features
- 🚀 Fast Semantic Search - Find relevant content using natural language queries
- 📦 Container Organization - Group memories by project, user, or topic
- ⚡ Async Processing - Embeddings generated asynchronously for fast ingestion
- 🔐 API Key Authentication - Secure access with API keys
- 🎯 Flexible Chunking - Configurable text chunking strategies
- 📊 Metadata Support - Attach custom metadata to memories
Quick Start
from cortefy import Cortefy
# Initialize client
client = Cortefy(api_key="your-api-key")
# Ingest content
result = client.memories.add(
content="Machine learning enables computers to learn from data",
container="ai-research"
)
# Search memories
results = client.search.query(
q="What is machine learning?",
containerTag="ai-research"
)Next Steps
- Get Started - Set up your API key and make your first request
- API Reference - Complete API documentation
- Examples - Code examples and use cases