Spaces:
Running
Running
from fastapi import FastAPI, HTTPException | |
from pydantic import BaseModel | |
import requests | |
import json | |
app = FastAPI() | |
# Model and API Key validation | |
valid_api_keys = ['PARTH-SADARIA-NI-API-CHAWI', 'HEET-NI-CHEESEWADI-API-KEY'] | |
model_aliases = { | |
'Llama-3.1-Nemotron-70B-Instruct': 'nvidia/Llama-3.1-Nemotron-70B-Instruct', | |
'Meta-Llama-3.1-8B-Instruct': 'meta-llama/Meta-Llama-3.1-8B-Instruct', | |
'Meta-Llama-3.1-70B-Instruct': 'meta-llama/Meta-Llama-3.1-70B-Instruct', | |
'Meta-Llama-3.1-70B-Instruct-Turbo': 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', | |
'Meta-Llama-3.1-405B-Instruct': 'meta-llama/Meta-Llama-3.1-405B-Instruct', | |
'Llama-3.2-11B-Vision-Instruct': 'meta-llama/Llama-3.2-11B-Vision-Instruct', | |
'Meta-Llama-3-8B-Instruct': 'meta-llama/Meta-Llama-3-8B-Instruct', | |
} | |
class Payload(BaseModel): | |
model: str | |
messages: list | |
async def get_completion(payload: Payload): | |
api_key = payload.headers.get("Authorization") | |
# API Key validation | |
if api_key not in valid_api_keys: | |
raise HTTPException(status_code=403, detail="Forbidden: Invalid API key") | |
# Model alias resolution | |
user_model = payload.model | |
full_model_name = model_aliases.get(user_model, user_model) | |
is_deepinfra_model = full_model_name in model_aliases.values() | |
# Determine the URL to send the request to | |
url = "https://api.deepinfra.com/v1/openai/chat/completions" if is_deepinfra_model else "https://gpt.tiptopuni.com/api/openai/v1/chat/completions" | |
# Send the API request to the appropriate service | |
response = requests.post(url, json={**payload.dict(), "model": full_model_name}) | |
if response.status_code != 200: | |
raise HTTPException(status_code=response.status_code, detail="Failed to fetch data") | |
# Return the response from the model API | |
return response.json() | |
# Run the server with Uvicorn using the 'main' module | |
if __name__ == "__main__": | |
import uvicorn | |
uvicorn.run(app, host="0.0.0.0", port=8000) | |