Live & Operational

Lumen Bridge Memory Chat API

Multi-Tenant AI Chat with Advanced Memory Management

22
API Endpoints
21+3
Memory Method
6
System Agents
Sessions
🧠

Memory Method

Advanced conversation management with sliding window of 21 interactions plus 3 rolling summaries for long-term context retention.

🔐

Multi-Tenant

Isolated sessions with UUID identification. Each user gets their own memory space with automatic cleanup of inactive sessions.

🤖

System Agents

Direct access to SearchAgent, TerminalAgent, CodeGenerator, SchemaAgent, RouterAgent - all powered by Lumen Bridge AI.

📊

Embeddings API

Full embeddings suite for semantic search, similarity calculation, batch processing, and automatic chunking for long texts.

💬

Stateless Chat

Optional session-free conversations for quick queries without maintaining memory state - perfect for simple interactions.

📚

Interactive Docs

Swagger UI with try-it-out functionality, complete schemas, and OpenAPI 3.0 specification for client generation.

⚡ Quick Start

1. Create a Session

curl -X POST https://lumen-chat33.codenlighten.org/api/sessions \
-H "Content-Type: application/json" \
-d '{"userId": "your-user-id"}'

2. Send a Message

curl -X POST https://lumen-chat33.codenlighten.org/api/sessions/{sessionId}/chat \
-H "Content-Type: application/json" \
-d '{"message": "Hello! Can you help me with Python?"}'

3. Or Use Stateless Chat

curl -X POST https://lumen-chat33.codenlighten.org/api/chat \
-H "Content-Type: application/json" \
-d '{"message": "What is 2+2?"}'

4. Search the Web

curl -X POST https://lumen-chat33.codenlighten.org/api/search \
-H "Content-Type: application/json" \
-d '{"userQuery": "Latest AI developments"}'

5. Generate Code

curl -X POST https://lumen-chat33.codenlighten.org/api/code \
-H "Content-Type: application/json" \
-d '{"prompt": "Create a function to calculate factorial", "context": {"language": "python"}}'