from blindference_node.models.base import ModelBackend

class MyBackend(ModelBackend):
    def name(self) -> str:
        return "my-backend"

    def is_available(self) -> bool:
        return True  # Check GPU, API key, etc.

    def supported_models(self) -> list[str]:
        return ["my-model-v1"]

    def run(self, model_id: str, prompt: str) -> str:
        # Must produce identical output for identical (model_id, prompt)
        return "deterministic result"

# my_backend.py
from blindference_node.models.base import ModelBackend

class OllamaBackend(ModelBackend):
    def name(self): return "ollama"
    def is_available(self): return True
    def supported_models(self): return ["ollama:llama3.1"]
    def run(self, model_id, prompt):
        # Your inference logic
        return "result"

blindference-node models add my_backend:OllamaBackend

{
  "custom_backends": ["my_backend:OllamaBackend"]
}

[project.entry-points."blindference.backends"]
ollama = "my_package.backends:OllamaBackend"

pip install blindference-node-ollama

# List all registered backends and availability
blindference-node models list

# Test a specific backend
blindference-node models test --backend groq --model groq:llama-3.3-70b-versatile --prompt "Hello"

# Test all available backends
blindference-node models test --model qwen2.5-7b --prompt "2+2="

# Add a custom backend (validates import before saving)
blindference-node models add my_package.backends:CustomBackend