mirror of
https://github.com/xtekky/gpt4free.git
synced 2025-11-02 04:22:44 +08:00
9def1aa71f
* Update model configurations, provider implementations, and documentation - Updated model names and aliases for Qwen QVQ 72B and Qwen 2 72B (@TheFirstNoob) - Revised HuggingSpace class configuration, added default_image_model - Added llama-3.2-70b alias for Llama 3.2 70B model in AutonomousAI - Removed BlackboxCreateAgent class - Added gpt-4o alias for Copilot model - Moved api_key to Mhystical class attribute - Added models property with default_model value for Free2GPT - Simplified Jmuz class implementation - Improved image generation and model handling in DeepInfra - Standardized default models and removed aliases in Gemini - Replaced model aliases with direct model list in GlhfChat (@TheFirstNoob) - Removed trailing slash from image generation URL in PollinationsAI (https://github.com/xtekky/gpt4free/issues/2571) - Updated llama and qwen model configurations - Enhanced provider documentation and model details * Removed from (g4f/models.py) 'Yqcloud' provider from Default due to error 'ResponseStatusError: Response 429: 文字过长，请删减后重试。' * Update docs/providers-and-models.md * refactor(g4f/Provider/DDG.py): Add error handling and rate limiting to DDG provider - Add custom exception classes for rate limits, timeouts, and conversation limits - Implement rate limiting with sleep between requests (0.75s minimum delay) - Add model validation method to check supported models - Add proper error handling for API responses with custom exceptions - Improve session cookie handling for conversation persistence - Clean up User-Agent string and remove redundant code - Add proper error propagation through async generator Breaking changes: - New custom exceptions may require updates to error handling code - Rate limiting affects request timing and throughput - Model validation is now stricter Related: - Adds error handling similar to standard API clients - Improves reliability and robustness of chat interactions * Update g4f/models.py g4f/Provider/PollinationsAI.py * Update g4f/models.py * Restored provider which was not working and was disabled (g4f/Provider/DeepInfraChat.py) * Fixing a bug with Streaming Completions * Update g4f/Provider/PollinationsAI.py * Update g4f/Provider/Blackbox.py g4f/Provider/DDG.py * Added another model for generating images 'ImageGeneration2' to the 'Blackbox' provider * Update docs/providers-and-models.md * Update g4f/models.py g4f/Provider/Blackbox.py * Added a new OIVSCode provider from the Text Models and Vision (Image Upload) model * Update docs/providers-and-models.md * docs: add Conversation Memory class with context handling requested by @TheFirstNoob * Simplified README.md documentation added new docs/configuration.md documentation * Update add README.md docs/configuration.md * Update README.md * Update docs/providers-and-models.md g4f/models.py g4f/Provider/PollinationsAI.py * Added new model deepseek-r1 to Blackbox provider. @TheFirstNoob * Fixed bugs and updated docs/providers-and-models.md etc/unittest/client.py g4f/models.py g4f/Provider/. --------- Co-authored-by: kqlio67 <> Co-authored-by: H Lohaus <hlohaus@users.noreply.github.com>
88 lines
3.4 KiB
Python
88 lines
3.4 KiB
Python
from __future__ import annotations
|
|
|
|
from ..base_provider import AsyncGeneratorProvider, ProviderModelMixin
|
|
from ..helper import format_prompt, filter_none
|
|
from ...typing import AsyncResult, Messages
|
|
from ...requests import raise_for_status
|
|
from ...requests.aiohttp import StreamSession
|
|
from ...errors import ResponseError, MissingAuthError
|
|
|
|
class Replicate(AsyncGeneratorProvider, ProviderModelMixin):
|
|
url = "https://replicate.com"
|
|
login_url = "https://replicate.com/account/api-tokens"
|
|
working = True
|
|
needs_auth = True
|
|
default_model = "meta/meta-llama-3-70b-instruct"
|
|
models = [default_model]
|
|
|
|
@classmethod
|
|
async def create_async_generator(
|
|
cls,
|
|
model: str,
|
|
messages: Messages,
|
|
api_key: str = None,
|
|
proxy: str = None,
|
|
timeout: int = 180,
|
|
system_prompt: str = None,
|
|
max_tokens: int = None,
|
|
temperature: float = None,
|
|
top_p: float = None,
|
|
top_k: float = None,
|
|
stop: list = None,
|
|
extra_data: dict = {},
|
|
headers: dict = {
|
|
"accept": "application/json",
|
|
},
|
|
**kwargs
|
|
) -> AsyncResult:
|
|
model = cls.get_model(model)
|
|
if cls.needs_auth and api_key is None:
|
|
raise MissingAuthError("api_key is missing")
|
|
if api_key is not None:
|
|
headers["Authorization"] = f"Bearer {api_key}"
|
|
api_base = "https://api.replicate.com/v1/models/"
|
|
else:
|
|
api_base = "https://replicate.com/api/models/"
|
|
async with StreamSession(
|
|
proxy=proxy,
|
|
headers=headers,
|
|
timeout=timeout
|
|
) as session:
|
|
data = {
|
|
"stream": True,
|
|
"input": {
|
|
"prompt": format_prompt(messages),
|
|
**filter_none(
|
|
system_prompt=system_prompt,
|
|
max_new_tokens=max_tokens,
|
|
temperature=temperature,
|
|
top_p=top_p,
|
|
top_k=top_k,
|
|
stop_sequences=",".join(stop) if stop else None
|
|
),
|
|
**extra_data
|
|
},
|
|
}
|
|
url = f"{api_base.rstrip('/')}/{model}/predictions"
|
|
async with session.post(url, json=data) as response:
|
|
message = "Model not found" if response.status == 404 else None
|
|
await raise_for_status(response, message)
|
|
result = await response.json()
|
|
if "id" not in result:
|
|
raise ResponseError(f"Invalid response: {result}")
|
|
async with session.get(result["urls"]["stream"], headers={"Accept": "text/event-stream"}) as response:
|
|
await raise_for_status(response)
|
|
event = None
|
|
async for line in response.iter_lines():
|
|
if line.startswith(b"event: "):
|
|
event = line[7:]
|
|
if event == b"done":
|
|
break
|
|
elif event == b"output":
|
|
if line.startswith(b"data: "):
|
|
new_text = line[6:].decode()
|
|
if new_text:
|
|
yield new_text
|
|
else:
|
|
yield "\n"
|