tyndale-ai-service/app/main.py

80 lines
2.2 KiB
Python

import logging
import uuid
from fastapi import FastAPI, HTTPException
from app.config import settings, MAX_MESSAGE_LENGTH
from app.llm.adapter import get_adapter
from app.schemas import ChatRequest, ChatResponse, HealthResponse
# Configure logging
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
)
logger = logging.getLogger(__name__)
# Create FastAPI app
app = FastAPI(
title="Tyndale AI Service",
description="LLM Chat Service for algorithmic trading support",
version="0.1.0",
)
@app.get("/health", response_model=HealthResponse)
async def health_check() -> HealthResponse:
"""Health check endpoint."""
return HealthResponse(status="ok")
@app.post("/chat", response_model=ChatResponse)
async def chat(request: ChatRequest) -> ChatResponse:
"""Process a chat message through the LLM adapter.
- Validates message length
- Generates conversation_id if not provided
- Routes to appropriate LLM adapter based on LLM_MODE
"""
# Validate message length
if len(request.message) > MAX_MESSAGE_LENGTH:
raise HTTPException(
status_code=400,
detail=f"Message exceeds maximum length of {MAX_MESSAGE_LENGTH:,} characters. "
f"Your message has {len(request.message):,} characters.",
)
# Generate or use provided conversation_id
conversation_id = request.conversation_id or str(uuid.uuid4())
# Log request metadata (not content)
logger.info(
"Chat request received",
extra={
"conversation_id": conversation_id,
"message_length": len(request.message),
"mode": settings.llm_mode,
},
)
# Get adapter and generate response
adapter = get_adapter()
response_text = await adapter.generate(conversation_id, request.message)
# Log response metadata
logger.info(
"Chat response generated",
extra={
"conversation_id": conversation_id,
"response_length": len(response_text),
"mode": settings.llm_mode,
},
)
return ChatResponse(
conversation_id=conversation_id,
response=response_text,
mode=settings.llm_mode,
sources=[],
)