feat:

added buffer_lock to prevent race condition in high concurrency scenarios
added documentation

doc/examples/docker-compose.yml

@@ -0,0 +1,98 @@
+# Docker Compose example for NOMYO Router with multiple Ollama instances
+
+version: '3.8'
+
+services:
+  # NOMYO Router
+  nomyo-router:
+    image: nomyo-router:latest
+    build: .
+    ports:
+      - "12434:12434"
+    environment:
+      - CONFIG_PATH=/app/config/config.yaml
+      - NOMYO_ROUTER_DB_PATH=/app/token_counts.db
+    volumes:
+      - ./config:/app/config
+      - router-db:/app/token_counts.db
+    depends_on:
+      - ollama1
+      - ollama2
+      - ollama3
+    restart: unless-stopped
+    networks:
+      - nomyo-net
+
+  # Ollama Instance 1
+  ollama1:
+    image: ollama/ollama:latest
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama1-data:/root/.ollama
+    environment:
+      - OLLAMA_NUM_PARALLEL=4
+    restart: unless-stopped
+    networks:
+      - nomyo-net
+
+  # Ollama Instance 2
+  ollama2:
+    image: ollama/ollama:latest
+    ports:
+      - "11435:11434"
+    volumes:
+      - ollama2-data:/root/.ollama
+    environment:
+      - OLLAMA_NUM_PARALLEL=4
+    restart: unless-stopped
+    networks:
+      - nomyo-net
+
+  # Ollama Instance 3
+  ollama3:
+    image: ollama/ollama:latest
+    ports:
+      - "11436:11434"
+    volumes:
+      - ollama3-data:/root/.ollama
+    environment:
+      - OLLAMA_NUM_PARALLEL=4
+    restart: unless-stopped
+    networks:
+      - nomyo-net
+
+  # Optional: Prometheus for monitoring
+  prometheus:
+    image: prom/prometheus:latest
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+    restart: unless-stopped
+    networks:
+      - nomyo-net
+
+  # Optional: Grafana for visualization
+  grafana:
+    image: grafana/grafana:latest
+    ports:
+      - "3000:3000"
+    volumes:
+      - grafana-storage:/var/lib/grafana
+    restart: unless-stopped
+    networks:
+      - nomyo-net
+
+volumes:
+  router-db:
+  ollama1-data:
+  ollama2-data:
+  ollama3-data:
+  grafana-storage:
+
+networks:
+  nomyo-net:
+    driver: bridge

doc/examples/sample-config.yaml

@@ -0,0 +1,37 @@
+# Sample NOMYO Router Configuration
+
+# Basic single endpoint configuration
+endpoints:
+  - http://localhost:11434
+
+max_concurrent_connections: 2
+
+# Multi-endpoint configuration with local Ollama instances
+# endpoints:
+#   - http://ollama-worker1:11434
+#   - http://ollama-worker2:11434
+#   - http://ollama-worker3:11434
+
+# Mixed configuration with Ollama and OpenAI endpoints
+# endpoints:
+#   - http://localhost:11434
+#   - https://api.openai.com/v1
+
+
+# API keys for remote endpoints
+# Use ${VAR_NAME} syntax to reference environment variables
+api_keys:
+  # Local Ollama instances typically don't require authentication
+  "http://localhost:11434": "ollama"
+
+  # Remote Ollama instances
+  # "http://remote-ollama:11434": "ollama"
+
+  # OpenAI API
+  # "https://api.openai.com/v1": "${OPENAI_KEY}"
+
+  # Anthropic API
+  # "https://api.anthropic.com/v1": "${ANTHROPIC_KEY}"
+
+  # Other OpenAI-compatible endpoints
+  # "https://api.mistral.ai/v1": "${MISTRAL_KEY}"