File size: 4,874 Bytes
d5686dc |
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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 |
import json
import uuid
from typing import List, Dict, Any
from datetime import datetime
from aiohttp import ClientSession
from api.logger import setup_logger
logger = setup_logger(__name__)
class GizAIProvider:
# Class variables
url = "https://app.giz.ai/assistant/"
api_endpoint = "https://app.giz.ai/api/data/users/inferenceServer.infer"
working = True
supports_system_message = True
supports_message_history = True
# Chat models
default_model = 'chat-gemini-flash'
chat_models = [
default_model,
'chat-gemini-pro',
'chat-gpt4m',
'chat-gpt4',
'claude-sonnet',
'claude-haiku',
'llama-3-70b',
'llama-3-8b',
'mistral-large',
'chat-o1-mini'
]
# Image models
image_models = [
'flux1',
'sdxl',
'sd',
'sd35',
]
models = [*chat_models, *image_models]
model_aliases = {
# Chat model aliases
"gemini-flash": "chat-gemini-flash",
"gemini-pro": "chat-gemini-pro",
"gpt-4o-mini": "chat-gpt4m",
"gpt-4o": "chat-gpt4",
"claude-3.5-sonnet": "claude-sonnet",
"claude-3-haiku": "claude-haiku",
"llama-3.1-70b": "llama-3-70b",
"llama-3.1-8b": "llama-3-8b",
"o1-mini": "chat-o1-mini",
# Image model aliases
"sd-1.5": "sd",
"sd-3.5": "sd35",
"flux-schnell": "flux1",
}
@classmethod
def get_model(cls, model: str) -> str:
if model in cls.models:
return model
elif model in cls.model_aliases:
return cls.model_aliases[model]
else:
return cls.default_model
@classmethod
def is_image_model(cls, model: str) -> bool:
return model in cls.image_models
@classmethod
async def create_async_generator(
cls,
model: str,
messages: List[Dict[str, Any]],
max_tokens: int,
top_p: float,
temperature: float,
stream: bool = True,
**kwargs
):
model = cls.get_model(model)
headers = {
'Accept': 'application/json, text/plain, */*',
'Accept-Language': 'en-US,en;q=0.9',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Content-Type': 'application/json',
'Origin': 'https://app.giz.ai',
'Pragma': 'no-cache',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 '
'(KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36',
'sec-ch-ua': '"Not?A_Brand";v="99", "Chromium";v="130"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Linux"'
}
async with ClientSession() as session:
if cls.is_image_model(model):
# Image generation
prompt = messages[-1]["content"]
data = {
"model": model,
"input": {
"width": "1024",
"height": "1024",
"steps": 4,
"output_format": "webp",
"batch_size": 1,
"mode": "plan",
"prompt": prompt
}
}
async with session.post(
cls.api_endpoint,
headers=headers,
data=json.dumps(data),
) as response:
response.raise_for_status()
response_data = await response.json()
if response_data.get('status') == 'completed' and response_data.get('output'):
for url in response_data['output']:
yield {"images": url, "alt": "Generated Image"}
else:
# Chat completion
data = {
"model": model,
"input": {
"messages": [
{
"type": "human",
"content": " ".join([msg['content'] for msg in messages])
}
],
"mode": "plan"
},
"noStream": True
}
async with session.post(
cls.api_endpoint,
headers=headers,
data=json.dumps(data),
) as response:
response.raise_for_status()
result = await response.json()
yield result.get('output', '')
|