111 lines
3.6 KiB
Python
111 lines
3.6 KiB
Python
from abc import ABC, abstractmethod
|
|
|
|
import httpx
|
|
|
|
from app.config import settings
|
|
|
|
|
|
class LLMAdapter(ABC):
|
|
"""Abstract base class for LLM adapters."""
|
|
|
|
@abstractmethod
|
|
async def generate(self, conversation_id: str, message: str) -> str:
|
|
"""Generate a response for the given message.
|
|
|
|
Args:
|
|
conversation_id: The conversation identifier
|
|
message: The user's message
|
|
|
|
Returns:
|
|
The generated response string
|
|
"""
|
|
pass
|
|
|
|
|
|
class LocalAdapter(LLMAdapter):
|
|
"""Local stub adapter for development and testing."""
|
|
|
|
async def generate(self, conversation_id: str, message: str) -> str:
|
|
"""Return a stub response echoing the user message.
|
|
|
|
This is a placeholder that will be replaced with a real local model.
|
|
"""
|
|
return (
|
|
f"[LOCAL STUB MODE] Acknowledged your message. "
|
|
f"You said: \"{message[:100]}{'...' if len(message) > 100 else ''}\". "
|
|
f"This is a stub response - local model not yet implemented."
|
|
)
|
|
|
|
|
|
class RemoteAdapter(LLMAdapter):
|
|
"""Remote adapter that calls an external LLM service via HTTP."""
|
|
|
|
def __init__(self, url: str, token: str | None = None, timeout: float = 30.0):
|
|
"""Initialize the remote adapter.
|
|
|
|
Args:
|
|
url: The remote LLM service URL
|
|
token: Optional bearer token for authentication
|
|
timeout: Request timeout in seconds
|
|
"""
|
|
self.url = url
|
|
self.token = token
|
|
self.timeout = timeout
|
|
|
|
async def generate(self, conversation_id: str, message: str) -> str:
|
|
"""Call the remote LLM service to generate a response.
|
|
|
|
Handles errors gracefully by returning informative error strings.
|
|
"""
|
|
headers = {"Content-Type": "application/json"}
|
|
if self.token:
|
|
headers["Authorization"] = f"Bearer {self.token}"
|
|
|
|
payload = {
|
|
"conversation_id": conversation_id,
|
|
"message": message,
|
|
}
|
|
|
|
try:
|
|
async with httpx.AsyncClient(timeout=self.timeout) as client:
|
|
response = await client.post(self.url, json=payload, headers=headers)
|
|
|
|
if response.status_code != 200:
|
|
return (
|
|
f"[ERROR] Remote LLM returned status {response.status_code}: "
|
|
f"{response.text[:200] if response.text else 'No response body'}"
|
|
)
|
|
|
|
try:
|
|
data = response.json()
|
|
except ValueError:
|
|
return "[ERROR] Remote LLM returned invalid JSON response"
|
|
|
|
if "response" not in data:
|
|
return "[ERROR] Remote LLM response missing 'response' field"
|
|
|
|
return data["response"]
|
|
|
|
except httpx.TimeoutException:
|
|
return f"[ERROR] Remote LLM request timed out after {self.timeout} seconds"
|
|
except httpx.ConnectError:
|
|
return f"[ERROR] Could not connect to remote LLM at {self.url}"
|
|
except httpx.RequestError as e:
|
|
return f"[ERROR] Remote LLM request failed: {str(e)}"
|
|
|
|
|
|
def get_adapter() -> LLMAdapter:
|
|
"""Factory function to create the appropriate adapter based on configuration.
|
|
|
|
Returns:
|
|
An LLMAdapter instance based on the LLM_MODE setting
|
|
"""
|
|
if settings.llm_mode == "remote":
|
|
if not settings.llm_remote_url:
|
|
raise ValueError("LLM_REMOTE_URL must be set when LLM_MODE is 'remote'")
|
|
return RemoteAdapter(
|
|
url=settings.llm_remote_url,
|
|
token=settings.llm_remote_token or None,
|
|
)
|
|
return LocalAdapter()
|