cerebras

Cerebras LLM provider (OpenAI-compatible chat endpoint).

`fastvideo.entrypoints.streaming.prompt.providers.cerebras.complete_openai_compatible`

complete_openai_compatible(*, api_key: str | None, api_key_hint: str, base_url: str, provider_name: str, request: LLMRequest) -> LLMResponse

Issue a chat-completions call and decode the OpenAI response.

`fastvideo.entrypoints.streaming.prompt.providers.cerebras.LLMRequest`

LLMRequest(messages: list[LLMMessage], model: str, max_tokens: int | None = None, temperature: float | None = None, timeout_ms: int | None = None)

`fastvideo.entrypoints.streaming.prompt.providers.cerebras.LLMResponse`

LLMResponse(content: str, provider: str, model: str, latency_ms: float, fallback_used: bool = False)

`fastvideo.entrypoints.streaming.prompt.providers.cerebras.CerebrasProvider`

CerebrasProvider(api_key: str | None = None, base_url: str = _DEFAULT_BASE_URL, name: str = 'cerebras')

Cerebras inference adapter.

api_key falls back to CEREBRAS_API_KEY when unset.

Source

@dataclass
class CerebrasProvider:
    """Cerebras inference adapter.
``api_key`` falls back to ``CEREBRAS_API_KEY`` when unset.
&quot;&quot;&quot;

api_key: str | None = None
base_url: str = _DEFAULT_BASE_URL
name: str = &quot;cerebras&quot;

def __post_init__(self) -&gt; None:
    if self.api_key is None:
        self.api_key = os.environ.get(_API_KEY_ENV)

async def complete(self, request: LLMRequest) -&gt; LLMResponse:
    return await complete_openai_compatible(
        api_key=self.api_key,
        api_key_hint=_API_KEY_ENV,
        base_url=self.base_url,
        provider_name=self.name,
        request=request,
    )</code></pre></details>
fastvideo.entrypoints.streaming.prompt.providers.cerebras.CerebrasProvider.complete
complete(request: LLMRequest) -> LLMResponse
Source
async def complete(self, request: LLMRequest) -> LLMResponse:
    return await complete_openai_compatible(
        api_key=self.api_key,
        api_key_hint=_API_KEY_ENV,
        base_url=self.base_url,
        provider_name=self.name,
        request=request,
    )