Hermes Agent: إعداد النماذج

routing:
  simple_tasks: "gpt-4o-mini"
  medium_tasks: "gpt-4o"
  complex_tasks: "gpt-4o"
  code_execution: "claude-3.5-sonnet"
  fallback: "llama3.2"

# ~/.hermes/models.yaml

providers:
  openai:
    api_key: "${OPENAI_API_KEY}"
    base_url: "https://api.openai.com/v1"
    rate_limit: 100
  anthropic:
    api_key: "${ANTHROPIC_API_KEY}"
  ollama:
    base_url: "http://localhost:11434"
    timeout: 120

models:
  gpt-4o:
    provider: openai
    context_window: 128000
    input_cost: 2.50
    output_cost: 10.00
    capabilities:
      - chat
      - vision
      - function_calling
  gpt-4o-mini:
    provider: openai
    context_window: 128000
    input_cost: 0.15
    output_cost: 0.60
    capabilities:
      - chat
      - function_calling
  llama3.2:
    provider: ollama
    context_window: 128000
    input_cost: 0
    output_cost: 0
    capabilities:
      - chat

routing:
  strategy: "capability-based"
  rules:
    - condition: "complexity < 0.3"
      model: "gpt-4o-mini"
    - condition: "complexity >= 0.3 and complexity < 0.7"
      model: "gpt-4o"
    - condition: "task_type == 'code'"
      model: "claude-3.5-sonnet"
    - condition: "offline == true"
      model: "llama3.2"

providers:
  ollama:
    base_url: "http://localhost:11434"

models:
  llama3.2:
    provider: ollama
    context_window: 128000

ollama pull llama3.2
hermes model list --provider ollama

providers:
  vllm:
    base_url: "http://localhost:8000"
    api_format: "openai"

def select_model(task):
    if task.requires_vision:
        return "gpt-4o"
    if task.complexity < 0.3:
        return "gpt-4o-mini"
    if task.type == "code":
        return "claude-3.5-sonnet"
    return config.default_model

routing:
  strategy: "cost-based"
  quality_threshold: 0.8
  max_cost_per_request: 0.05

hermes chat --model gpt-4o
hermes chat --model claude-3.5-sonnet --mode code
hermes chat --model llama3.2 --offline

hermes cost report --month
# ┌──────────────┬──────────┬───────────┬─────────┐
# │ Model        │ Requests │ Tokens In │ Cost    │
# ├──────────────┼──────────┼───────────┼─────────┤
# │ gpt-4o-mini  │ 1,200    │ 2.4M      │ $2.16   │
# │ gpt-4o       │ 80       │ 0.8M      │ $12.00  │
# │ Total        │ 1,280    │ 3.2M      │ $14.16  │
# └──────────────┴──────────┴───────────┴─────────┘