4e2450e800
- Removed the backend client compatibility wrapper and associated methods to streamline backend integration. - Updated session management to utilize control plane gateways and runtime configuration providers. - Adjusted TTS service implementations to remove the EdgeTTS service and simplify service dependencies. - Enhanced documentation to reflect changes in backend integration and service architecture. - Updated configuration files to remove deprecated TTS provider options and clarify available settings.
68 lines
2.0 KiB
Python
68 lines
2.0 KiB
Python
"""LLM extension port contracts."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
from typing import Any, AsyncIterator, Awaitable, Callable, Dict, List, Optional, Protocol
|
|
|
|
from services.base import LLMMessage, LLMStreamEvent
|
|
|
|
KnowledgeRetrieverFn = Callable[..., Awaitable[List[Dict[str, Any]]]]
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class LLMServiceSpec:
|
|
"""Resolved runtime configuration for LLM service creation."""
|
|
|
|
provider: str
|
|
model: str
|
|
api_key: Optional[str] = None
|
|
base_url: Optional[str] = None
|
|
system_prompt: Optional[str] = None
|
|
temperature: float = 0.7
|
|
knowledge_config: Dict[str, Any] = field(default_factory=dict)
|
|
knowledge_searcher: Optional[KnowledgeRetrieverFn] = None
|
|
|
|
|
|
class LLMPort(Protocol):
|
|
"""Port for LLM providers."""
|
|
|
|
async def connect(self) -> None:
|
|
"""Establish connection to LLM provider."""
|
|
|
|
async def disconnect(self) -> None:
|
|
"""Release LLM resources."""
|
|
|
|
async def generate(
|
|
self,
|
|
messages: List[LLMMessage],
|
|
temperature: float = 0.7,
|
|
max_tokens: Optional[int] = None,
|
|
) -> str:
|
|
"""Generate a complete assistant response."""
|
|
|
|
async def generate_stream(
|
|
self,
|
|
messages: List[LLMMessage],
|
|
temperature: float = 0.7,
|
|
max_tokens: Optional[int] = None,
|
|
) -> AsyncIterator[LLMStreamEvent]:
|
|
"""Generate streaming assistant response events."""
|
|
|
|
|
|
class LLMCancellable(Protocol):
|
|
"""Optional extension for interrupting in-flight LLM generation."""
|
|
|
|
def cancel(self) -> None:
|
|
"""Cancel an in-flight generation request."""
|
|
|
|
|
|
class LLMRuntimeConfigurable(Protocol):
|
|
"""Optional extension for runtime config updates."""
|
|
|
|
def set_knowledge_config(self, config: Optional[Dict[str, Any]]) -> None:
|
|
"""Apply runtime knowledge retrieval settings."""
|
|
|
|
def set_tool_schemas(self, schemas: Optional[List[Dict[str, Any]]]) -> None:
|
|
"""Apply runtime tool schemas used for tool calling."""
|