mirror of
https://github.com/xtekky/gpt4free.git
synced 2024-12-25 04:01:52 +03:00
a358b28f47
* refactor(g4f/Provider/Airforce.py): improve model handling and filtering - Add hidden_models set to exclude specific models - Add evil alias for uncensored model handling - Extend filtering for model-specific response tokens - Add response buffering for streamed content - Update model fetching with error handling * refactor(g4f/Provider/Blackbox.py): improve caching and model handling - Add caching system for validated values with file-based storage - Rename 'flux' model to 'ImageGeneration' and update references - Add temperature, top_p and max_tokens parameters to generator - Simplify HTTP headers and remove redundant options - Add model alias mapping for ImageGeneration - Add file system utilities for cache management * feat(g4f/Provider/RobocodersAPI.py): add caching and error handling - Add file-based caching system for access tokens and sessions - Add robust error handling with specific error messages - Add automatic dialog continuation on resource limits - Add HTML parsing with BeautifulSoup for token extraction - Add debug logging for error tracking - Add timeout configuration for API requests * refactor(g4f/Provider/DarkAI.py): update DarkAI default model and aliases - Change default model from llama-3-405b to llama-3-70b - Remove llama-3-405b from supported models list - Remove llama-3.1-405b from model aliases * feat(g4f/Provider/Blackbox2.py): add image generation support - Add image model 'flux' with dedicated API endpoint - Refactor generator to support both text and image outputs - Extract headers into reusable static method - Add type hints for AsyncGenerator return type - Split generation logic into _generate_text and _generate_image methods - Add ImageResponse handling for image generation results BREAKING CHANGE: create_async_generator now returns AsyncGenerator instead of AsyncResult * refactor(g4f/Provider/ChatGptEs.py): update ChatGptEs model configuration - Update models list to include gpt-3.5-turbo - Remove chatgpt-4o-latest from supported models - Remove model_aliases mapping for gpt-4o * feat(g4f/Provider/DeepInfraChat.py): add Accept-Language header support - Add Accept-Language header for internationalization - Maintain existing header configuration - Improve request compatibility with language preferences * refactor(g4f/Provider/needs_auth/Gemini.py): add ProviderModelMixin inheritance - Add ProviderModelMixin to class inheritance - Import ProviderModelMixin from base_provider - Move BaseConversation import to base_provider imports * refactor(g4f/Provider/Liaobots.py): update model details and aliases - Add version suffix to o1 model IDs - Update model aliases for o1-preview and o1-mini - Standardize version format across model definitions * refactor(g4f/Provider/PollinationsAI.py): enhance model support and generation - Split generation logic into dedicated image/text methods - Add additional text models including sur and claude - Add width/height parameters for image generation - Add model existence validation - Add hasattr checks for model lists initialization * chore(gitignore): add provider cache directory - Add g4f/Provider/.cache to gitignore patterns * refactor(g4f/Provider/ReplicateHome.py): update model configuration - Update default model to gemma-2b-it - Add default_image_model configuration - Remove llava-13b from supported models - Simplify request headers * feat(g4f/models.py): expand provider and model support - Add new providers DarkAI and PollinationsAI - Add new models for Mistral, Flux and image generation - Update provider lists for existing models - Add P1 and Evil models with experimental providers BREAKING CHANGE: Remove llava-13b model support * refactor(Airforce): Update type hint for split_message return - Change return type of from to for consistency with import. - Maintain overall functionality and structure of the class. - Ensure compatibility with type hinting standards in Python. * refactor(g4f/Provider/Airforce.py): Update type hint for split_message return - Change return type of 'split_message' from 'list[str]' to 'List[str]' for consistency with import. - Maintain overall functionality and structure of the 'Airforce' class. - Ensure compatibility with type hinting standards in Python. * feat(g4f/Provider/RobocodersAPI.py): Add support for optional BeautifulSoup dependency - Introduce a check for the BeautifulSoup library and handle its absence gracefully. - Raise a if BeautifulSoup is not installed, prompting the user to install it. - Remove direct import of BeautifulSoup to avoid import errors when the library is missing. --------- Co-authored-by: kqlio67 <>
81 lines
3.1 KiB
Python
81 lines
3.1 KiB
Python
from __future__ import annotations
|
|
|
|
from aiohttp import ClientSession, ClientResponseError
|
|
import json
|
|
from ..typing import AsyncResult, Messages, ImageType
|
|
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
|
|
|
|
|
|
class DeepInfraChat(AsyncGeneratorProvider, ProviderModelMixin):
|
|
url = "https://deepinfra.com/chat"
|
|
api_endpoint = "https://api.deepinfra.com/v1/openai/chat/completions"
|
|
working = True
|
|
supports_stream = True
|
|
supports_system_message = True
|
|
supports_message_history = True
|
|
|
|
default_model = 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo'
|
|
models = [
|
|
'meta-llama/Meta-Llama-3.1-8B-Instruct',
|
|
default_model,
|
|
'Qwen/QwQ-32B-Preview',
|
|
'microsoft/WizardLM-2-8x22B',
|
|
'Qwen/Qwen2.5-72B-Instruct',
|
|
'Qwen/Qwen2.5-Coder-32B-Instruct',
|
|
'nvidia/Llama-3.1-Nemotron-70B-Instruct',
|
|
]
|
|
model_aliases = {
|
|
"llama-3.1-8b": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"llama-3.1-70b": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
|
|
"qwq-32b": "Qwen/QwQ-32B-Preview",
|
|
"wizardlm-2-8x22b": "microsoft/WizardLM-2-8x22B",
|
|
"qwen-2-72b": "Qwen/Qwen2.5-72B-Instruct",
|
|
"qwen-2.5-coder-32b": "Qwen2.5-Coder-32B-Instruct",
|
|
"nemotron-70b": "nvidia/Llama-3.1-Nemotron-70B-Instruct",
|
|
}
|
|
|
|
@classmethod
|
|
async def create_async_generator(
|
|
cls,
|
|
model: str,
|
|
messages: Messages,
|
|
proxy: str = None,
|
|
**kwargs
|
|
) -> AsyncResult:
|
|
headers = {
|
|
'Accept-Language': 'en-US,en;q=0.9',
|
|
'Content-Type': 'application/json',
|
|
'Origin': 'https://deepinfra.com',
|
|
'Referer': 'https://deepinfra.com/',
|
|
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
|
|
'X-Deepinfra-Source': 'web-page',
|
|
'accept': 'text/event-stream',
|
|
}
|
|
|
|
data = {
|
|
'model': model,
|
|
'messages': messages,
|
|
'stream': True
|
|
}
|
|
|
|
async with ClientSession(headers=headers) as session:
|
|
async with session.post(cls.api_endpoint, json=data, proxy=proxy) as response:
|
|
response.raise_for_status()
|
|
async for line in response.content:
|
|
if line:
|
|
decoded_line = line.decode('utf-8').strip()
|
|
if decoded_line.startswith('data:'):
|
|
json_part = decoded_line[5:].strip()
|
|
if json_part == '[DONE]':
|
|
break
|
|
try:
|
|
data = json.loads(json_part)
|
|
choices = data.get('choices', [])
|
|
if choices:
|
|
delta = choices[0].get('delta', {})
|
|
content = delta.get('content', '')
|
|
if content:
|
|
yield content
|
|
except json.JSONDecodeError:
|
|
print(f"JSON decode error: {json_part}")
|