Skip to main content

ai_inference

Pydantic models for AI Inference service for chat completions, text completions, and AI model management.

class ChatMessage(*, role: str, content: str | None = None, name: str | None = None, tool_calls: List[Dict[str, Any]] | None = None, tool_call_id: str | None = None) -> None​

Chat message model for AI conversations.

class ChatRequest(*, model: str | None = 'openai-gpt-4', messages: Annotated[List[datalayer_core.models.ai_inference.ChatMessage], MinLen(min_length=1)], temperature: Annotated[float | None, Ge(ge=0.0), Le(le=2.0)] = 0.7, max_tokens: Annotated[int | None, Ge(ge=1)] = 1024, stream: bool | None = False, tools: List[Dict[str, Any]] | None = None, tool_choice: str | Dict[str, Any] | None = None, functions: List[Dict[str, Any]] | None = None, function_call: str | Dict[str, Any] | None = None, parallel_tool_calls: bool | None = None) -> None​

Chat completion request model.

class CompletionRequest(*, model: str | None = 'text-model', prompt: str, temperature: Annotated[float | None, Ge(ge=0.0), Le(le=2.0)] = 0.7, max_tokens: Annotated[int | None, Ge(ge=1)] = 1024, stop: List[str] | None = None, stream: bool | None = False) -> None​

Text completion request model.

class ChatResponseData(*, response: str | None = None, message: Dict[str, Any] | None = None, choices: List[Dict[str, Any]] | None = None, model: str | None = None, usage: Dict[str, Any] | None = None) -> None​

Chat completion response data model.

class CompletionResponseData(*, response: str, model: str | None = None, usage: Dict[str, Any] | None = None) -> None​

Text completion response data model.

class ModelsResponseData(*, models: List[str], aliases: Dict[str, str] = <factory>, categories: Dict[str, List[str]] | None = None) -> None​

Available models response data model.

class HealthResponseData(*, status: str, service: str, version: str | None = None, timestamp: str | None = None) -> None​

Health check response data model.

class EmbeddingRequest(*, model: str | None = 'text-embedding-ada-002', input: str | List[str], encoding_format: str | None = 'float', dimensions: int | None = None) -> None​

Embedding request model.

class EmbeddingData(*, object: str = 'embedding', embedding: List[float], index: int) -> None​

Single embedding data model.

class EmbeddingResponseData(*, object: str = 'list', data: List[datalayer_core.models.ai_inference.EmbeddingData], model: str, usage: Dict[str, Any] | None = None) -> None​

Embedding response data model.