The Knowledge Base
Your AI Agent Needs

# Semantic search - flat (exact, default)
curl -X POST http://localhost:11023/v1/vector-search \
  -H "Content-Type: application/json" \
  -d '{
    "collection": "kb",
    "query": "how do I cancel my subscription?",
    "topK": 5,
    "threshold": 0.7,
    "includeContent": true
  }'

# HNSW - fast approximate nearest neighbor
curl -X POST http://localhost:11023/v1/vector-search \
  -d '{"collection":"kb", "query":"refund", "topK":5, "algorithm":"hnsw"}'

# IVF - clustered search for large collections
curl -X POST http://localhost:11023/v1/vector-search \
  -d '{"collection":"kb", "query":"refund", "topK":5, "algorithm":"ivf"}'

# PQ - compressed, memory-efficient search
curl -X POST http://localhost:11023/v1/vector-search \
  -d '{"collection":"kb", "query":"refund", "topK":5, "algorithm":"pq"}'

# Simple search with BM25 scoring
curl -X POST http://localhost:11023/v1/fts \
  -H "Content-Type: application/json" \
  -d '{
    "collection": "blog",
    "query": "markdown database tutorial",
    "limit": 10,
    "algorithm": "bm25"
  }'

# Boolean search (AND, OR, NOT, +required, -excluded)
curl -X POST http://localhost:11023/v1/fts \
  -H "Content-Type: application/json" \
  -d '{
    "collection": "blog",
    "query": "rust AND performance NOT garbage",
    "mode": "boolean"
  }'

# Phrase search — exact word sequence
curl -X POST http://localhost:11023/v1/fts \
  -H "Content-Type: application/json" \
  -d '{
    "collection": "blog",
    "query": "\"machine learning\"",
    "mode": "phrase"
  }'

# Proximity search — terms within 5 words
curl -X POST http://localhost:11023/v1/fts \
  -H "Content-Type: application/json" \
  -d '{
    "collection": "blog",
    "query": "\"database performance\"~5",
    "mode": "proximity",
    "distance": 5
  }'

curl -X POST http://localhost:11023/v1/search \
  -H "Content-Type: application/json" \
  -d '{
    "collection": "blog",
    "filterMeta": {
      "category": ["tutorial"],
      "status": ["published"]
    },
    "sort": "updatedAt",
    "limit": 10
  }'

from mddb import MDDB

# TCP connection
db = MDDB.connect('localhost:11023', 'write').collection('kb')

# Unix Domain Socket (MDDB 2.9.14+, zero-network local transport)
# db = MDDB.connect('unix:/tmp/mddb.sock', 'write').collection('kb')

# Add document
db.add('faq', 'en_US', {'category': ['billing']}, '# Billing FAQ\n\nCancel in Settings.')

# Vector search (RAG pipeline step 1)
results = db.vector_search('how to cancel?', top_k=3, include_content=True)

# Full-text search
results = db.fts_search('billing refund', limit=10)

# Webhooks
db.register_webhook('https://app.com/hook', ['doc.added'], 'kb')

# Import from URL
db.import_url('https://example.com/docs.md', 'en_US')

# TTL
db.set_ttl('temp-key', 'en', 3600)  # expires in 1h

<?php
require_once 'mddb.php';

// TCP connection
$db = mddb::connect('localhost:11023', 'write');

// Unix Domain Socket (MDDB 2.9.14+)
// $db = mddb::connect('unix:/tmp/mddb.sock', 'write');

// Add document
$db->collection('blog')->add('hello', 'en_US', ['category' => ['tutorial']], '# Hello');

// Vector search
$results = $db->collection('kb')->vectorSearch('cancel subscription', 5, 0.7, true);

// Full-text search
$results = $db->collection('blog')->ftsSearch('database tutorial', 10);

// Webhooks
$db->registerWebhook('https://app.com/hook', ['doc.added', 'doc.updated']);

// Import from URL
$db->collection('docs')->importUrl('https://example.com/post.md', 'en_US');

// TTL
$db->collection('cache')->setTtl('temp', 'en', 3600);

# Docker (Easiest) - for Windsurf / Claude Desktop
# Configure ~/.windsurf/mcp.json:
{
  "mcpServers": {
    "mddb": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm", "--network", "host",
        "-e", "MDDB_GRPC_ADDRESS=localhost:11024",
        "-e", "MDDB_REST_BASE_URL=http://localhost:11023",
        "-e", "MDDB_MCP_STDIO=true",
        "tradik/mddb:latest"
      ]
    }
  }
}

# MCP provides 79 built-in tools including:
# - add_document, search_documents, semantic_search
# - full_text_search, hybrid_search, cross_search
# - classify_document, find_duplicates
# - geo_search, geo_within, geo_encode, geo_decode, geo_stats
# - automation, webhooks, schemas, backups
# - collection config, revisions, aggregate, and more