Spaces:
Sleeping
Sleeping
File size: 1,930 Bytes
b0ce8a9 9ecb27b b0ce8a9 9ecb27b b0ce8a9 9ecb27b b0ce8a9 9ecb27b b0ce8a9 9ecb27b b0ce8a9 9ecb27b b0ce8a9 9ecb27b b0ce8a9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | from fastapi import APIRouter, HTTPException, Query, status
from typing import Optional
import random
import logging
from .openrouter import OpenRouterClient
from .utils import get_openrouter_client
router = APIRouter()
logger = logging.getLogger(__name__)
FREE_MODELS = [
"openai/gpt-3.5-turbo",
"anthropic/claude-instant-v1",
"google/palm-2-chat-bison",
"meta-llama/llama-2-13b-chat",
"mistralai/mistral-7b-instruct"
]
@router.post("/chat")
async def chat_with_model(
message: str,
model: Optional[str] = None,
temperature: float = Query(0.7, ge=0, le=2),
max_tokens: int = Query(1024, ge=1, le=4096)
):
"""
Chat with a specified model or let the system choose one
"""
if not message.strip():
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="Message cannot be empty"
)
client = get_openrouter_client()
if not model:
model = random.choice(FREE_MODELS)
elif model not in FREE_MODELS:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=f"Model not available in free tier. Available models: {', '.join(FREE_MODELS)}"
)
try:
logger.info(f"Processing chat request with model: {model}")
response = client.chat_completion(
model=model,
messages=[{"role": "user", "content": message}],
temperature=temperature,
max_tokens=max_tokens
)
return {
"model": model,
"response": response["choices"][0]["message"]["content"],
"usage": response.get("usage", {})
}
except Exception as e:
logger.error(f"Error processing chat request: {str(e)}")
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Error processing your request"
) |