Documentation
¶
Overview ¶
This example demonstrates the Training/HITL loop:
- Crew.Train() runs the crew N iterations collecting feedback
- Negative feedback (Rating < 0) is persisted and consolidated
- Consolidated advice is injected into the agent's system prompt on subsequent runs
Prerequisites:
- An LLM API key (OpenAI or Ollama)
Usage (OpenAI):
OPENAI_API_KEY=sk-... go run main.go
Usage (Ollama):
OLLAMA_BASE_URL=http://localhost:11434 OLLAMA_MODEL=gemma3:4b go run main.go
Click to show internal directories.
Click to hide internal directories.