gpt4free/g4f/Provider/ReplicateHome.py
kqlio67 a358b28f47
Major Provider Updates and Model Support Enhancements (#2467)
* 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 <>
2024-12-08 04:43:51 +01:00

125 lines
4.6 KiB
Python

from __future__ import annotations
import json
import asyncio
from aiohttp import ClientSession, ContentTypeError
from ..typing import AsyncResult, Messages
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
from ..requests.aiohttp import get_connector
from ..requests.raise_for_status import raise_for_status
from .helper import format_prompt
from ..image import ImageResponse
class ReplicateHome(AsyncGeneratorProvider, ProviderModelMixin):
url = "https://replicate.com"
api_endpoint = "https://homepage.replicate.com/api/prediction"
working = True
supports_stream = True
supports_system_message = True
supports_message_history = True
default_model = 'google-deepmind/gemma-2b-it'
default_image_model = 'stability-ai/stable-diffusion-3'
image_models = [
'stability-ai/stable-diffusion-3',
'bytedance/sdxl-lightning-4step',
'playgroundai/playground-v2.5-1024px-aesthetic',
]
text_models = [
'google-deepmind/gemma-2b-it',
]
models = text_models + image_models
model_aliases = {
# image_models
"sd-3": "stability-ai/stable-diffusion-3",
"sdxl": "bytedance/sdxl-lightning-4step",
"playground-v2.5": "playgroundai/playground-v2.5-1024px-aesthetic",
# text_models
"gemma-2b": "google-deepmind/gemma-2b-it",
}
model_versions = {
# image_models
'stability-ai/stable-diffusion-3': "527d2a6296facb8e47ba1eaf17f142c240c19a30894f437feee9b91cc29d8e4f",
'bytedance/sdxl-lightning-4step': "5f24084160c9089501c1b3545d9be3c27883ae2239b6f412990e82d4a6210f8f",
'playgroundai/playground-v2.5-1024px-aesthetic': "a45f82a1382bed5c7aeb861dac7c7d191b0fdf74d8d57c4a0e6ed7d4d0bf7d24",
# text_models
"google-deepmind/gemma-2b-it": "dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626",
}
@classmethod
async def create_async_generator(
cls,
model: str,
messages: Messages,
prompt: str = None,
proxy: str = None,
**kwargs
) -> AsyncResult:
model = cls.get_model(model)
headers = {
"accept": "*/*",
"accept-language": "en-US,en;q=0.9",
"content-type": "application/json",
"origin": "https://replicate.com",
"referer": "https://replicate.com/",
"user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"
}
async with ClientSession(headers=headers, connector=get_connector(proxy=proxy)) as session:
if prompt is None:
if model in cls.image_models:
prompt = messages[-1]['content']
else:
prompt = format_prompt(messages)
data = {
"model": model,
"version": cls.model_versions[model],
"input": {"prompt": prompt},
}
async with session.post(cls.api_endpoint, json=data) as response:
await raise_for_status(response)
result = await response.json()
prediction_id = result['id']
poll_url = f"https://homepage.replicate.com/api/poll?id={prediction_id}"
max_attempts = 30
delay = 5
for _ in range(max_attempts):
async with session.get(poll_url) as response:
await raise_for_status(response)
try:
result = await response.json()
except ContentTypeError:
text = await response.text()
try:
result = json.loads(text)
except json.JSONDecodeError:
raise ValueError(f"Unexpected response format: {text}")
if result['status'] == 'succeeded':
if model in cls.image_models:
image_url = result['output'][0]
yield ImageResponse(image_url, prompt)
return
else:
for chunk in result['output']:
yield chunk
break
elif result['status'] == 'failed':
raise Exception(f"Prediction failed: {result.get('error')}")
await asyncio.sleep(delay)
if result['status'] != 'succeeded':
raise Exception("Prediction timed out")