mirrors/gpt4free
1
Fork 0
mirror of https://github.com/xtekky/gpt4free.git synced 2025-12-06 02:30:41 -08:00
Code Issues Projects Releases Packages Wiki Activity

Improve Yupp provider account handling , request timeout and get byte from url (#3249)

Browse source 
* Add image caching to Yupp provider

Introduces an image cache to avoid redundant uploads in the Yupp provider. Refactors media attachment handling into a new prepare_files method, improving efficiency and code organization. Updates .gitignore to exclude .idea directory.

* Refactor Yupp stream handling and chunk processing

Improves stream segmentation in the Yupp provider by introducing buffers for target, variant, quick, thinking, and extra streams. Refactors chunk processing to better handle image-gen, quick responses, and variant outputs, and adds more robust stream ID extraction and routing logic. Yields a consolidated JsonResponse with all stream segments for downstream use.

* Handle ClientResponseError in Yupp provider

Adds specific handling for aiohttp ClientResponseError in the Yupp provider. Marks account as invalid on 500 Internal Server Error, otherwise increments error count and raises ProviderException for other errors.

* Update Yupp.py

fix 429  'Too Many Requests'

* Update Yupp.py

* Improve Yupp provider account handling and request timeout

Refactored account loading to preserve account history and error counts when updating tokens. Enhanced request logic to support custom timeouts using aiohttp's ClientTimeout, allowing for more flexible timeout configuration.

* Update __init__.py

* Handle multi-line <think> and <yapp> blocks in Yupp

Added logic to capture and process multi-line <think> and <yapp class="image-gen"> blocks referenced by special IDs. Introduced block storage and extraction functions, enabling reasoning and image-gen content to be handled via references in the response stream.

* Update LMArena.py

Not Found Model error

* Refactor to use StreamSession in Qwen and Yupp providers

Replaced aiohttp.ClientSession with StreamSession in Qwen.py and Yupp.py for improved session handling. Updated exception and timeout references in Yupp.py to use aiohttp types. Improved default argument handling in StreamSession initialization.

* Update Yupp.py

* Add status parameter to get_generated_image method

Introduces a 'status' parameter to the get_generated_image method to allow passing image generation status. Updates method calls and response objects to include status in their metadata for improved tracking of image generation progress.

* Update OpenaiChat.py

* Refactor Qwen image upload and caching logic and token

Reworked the image upload flow in Qwen provider to use direct file uploads with OSS headers, added caching for uploaded images, and improved file type detection. Updated prepare_files to handle uploads via session and cache results, and added utility for generating OSS headers. Minor imports and typing adjustments included and token support.

* Refactor Qwen and Yupp providers for improved async handling

Updated Qwen provider to handle timeout via kwargs and improved type annotations. Refactored Yupp provider for better code organization, formatting, and async account rotation logic. Enhanced readability and maintainability by reordering imports, adding whitespace, and clarifying function implementations.

* Add image caching to OpenaiChat provider

Introduces an image cache mechanism to OpenaiChat for uploaded images, reducing redundant uploads and improving efficiency. Also refactors code for clarity, updates type hints, and makes minor formatting improvements throughout the file.
This commit is contained in:
Ammar 2025-11-26 15:02:51 +02:00 • committed by GitHub
parent 32215bb7bb
commit 7771cf3d43
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 623 additions and 289 deletions
Download patch file Download diff file Expand all files Collapse all files

210
g4f/Provider/Qwen.py
View file

@ -1,22 +1,29 @@
from __future__ import annotations from __future__ import annotations
import asyncio import asyncio
import datetime
import hashlib
import hmac
import json import json
import mimetypes
import re import re
import uuid import uuid
from time import time from time import time
from typing import Literal, Optional from typing import Literal, Optional, Dict
from urllib.parse import quote
import aiohttp import aiohttp
from ..errors import RateLimitError, ResponseError
from ..typing import AsyncResult, Messages, MediaListType from g4f.image import to_bytes, detect_file_type
from ..providers.response import JsonConversation, Reasoning, Usage, ImageResponse, FinishReason from g4f.requests import raise_for_status
from ..requests import sse_stream
from ..tools.media import merge_media
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
from .helper import get_last_user_message from .helper import get_last_user_message
from .. import debug from .. import debug
from ..errors import RateLimitError, ResponseError
from ..providers.response import JsonConversation, Reasoning, Usage, ImageResponse, FinishReason
from ..requests import sse_stream
from ..requests.aiohttp import StreamSession
from ..tools.media import merge_media
from ..typing import AsyncResult, Messages, MediaListType
try: try:
import curl_cffi import curl_cffi
@ -25,6 +32,56 @@ try:
except ImportError: except ImportError:
has_curl_cffi = False has_curl_cffi = False
# Global variables to manage Qwen Image Cache
ImagesCache: Dict[str, dict] = {}
def get_oss_headers(method: str, date_str: str, sts_data: dict, content_type: str) -> dict[str, str]:
bucket_name = sts_data.get('bucketname', 'qwen-webui-prod')
file_path = sts_data.get('file_path', '')
access_key_id = sts_data.get('access_key_id')
access_key_secret = sts_data.get('access_key_secret')
security_token = sts_data.get('security_token')
headers = {
'Content-Type': content_type,
'x-oss-content-sha256': 'UNSIGNED-PAYLOAD',
'x-oss-date': date_str,
'x-oss-security-token': security_token,
'x-oss-user-agent': 'aliyun-sdk-js/6.23.0 Chrome 132.0.0.0 on Windows 10 64-bit'
}
headers_lower = {k.lower(): v for k, v in headers.items()}
canonical_headers_list = []
signed_headers_list = []
required_headers = ['content-md5', 'content-type', 'x-oss-content-sha256', 'x-oss-date', 'x-oss-security-token',
'x-oss-user-agent']
for header_name in sorted(required_headers):
if header_name in headers_lower:
canonical_headers_list.append(f"{header_name}:{headers_lower[header_name]}")
signed_headers_list.append(header_name)
canonical_headers = '\n'.join(canonical_headers_list) + '\n'
canonical_uri = f"/{bucket_name}/{quote(file_path, safe='/')}"
canonical_request = f"{method}\n{canonical_uri}\n\n{canonical_headers}\n\nUNSIGNED-PAYLOAD"
date_parts = date_str.split('T')
date_scope = f"{date_parts[0]}/ap-southeast-1/oss/aliyun_v4_request"
string_to_sign = f"OSS4-HMAC-SHA256\n{date_str}\n{date_scope}\n{hashlib.sha256(canonical_request.encode()).hexdigest()}"
def sign(key, msg):
return hmac.new(key, msg.encode() if isinstance(msg, str) else msg, hashlib.sha256).digest()
date_key = sign(f"aliyun_v4{access_key_secret}".encode(), date_parts[0])
region_key = sign(date_key, "ap-southeast-1")
service_key = sign(region_key, "oss")
signing_key = sign(service_key, "aliyun_v4_request")
signature = hmac.new(signing_key, string_to_sign.encode(), hashlib.sha256).hexdigest()
headers['authorization'] = f"OSS4-HMAC-SHA256 Credential={access_key_id}/{date_scope},Signature={signature}"
return headers
text_models = [ text_models = [
'qwen3-max-preview', 'qwen-plus-2025-09-11', 'qwen3-235b-a22b', 'qwen3-coder-plus', 'qwen3-30b-a3b', 'qwen3-max-preview', 'qwen-plus-2025-09-11', 'qwen3-235b-a22b', 'qwen3-coder-plus', 'qwen3-30b-a3b',
'qwen3-coder-30b-a3b-instruct', 'qwen-max-latest', 'qwen-plus-2025-01-25', 'qwq-32b', 'qwen-turbo-2025-02-11', 'qwen3-coder-30b-a3b-instruct', 'qwen-max-latest', 'qwen-plus-2025-01-25', 'qwq-32b', 'qwen-turbo-2025-02-11',
@ -60,19 +117,19 @@ class Qwen(AsyncGeneratorProvider, ProviderModelMixin):
active_by_default = True active_by_default = True
supports_stream = True supports_stream = True
supports_message_history = False supports_message_history = False
image_cache = True
_models_loaded = True _models_loaded = True
image_models = image_models image_models = image_models
text_models = text_models text_models = text_models
vision_models = vision_models vision_models = vision_models
models = models models: list[str] = models
default_model = "qwen3-235b-a22b" default_model = "qwen3-235b-a22b"
_midtoken: str = None _midtoken: str = None
_midtoken_uses: int = 0 _midtoken_uses: int = 0
@classmethod @classmethod
def get_models(cls) -> list[str]: def get_models(cls, **kwargs) -> list[str]:
if not cls._models_loaded and has_curl_cffi: if not cls._models_loaded and has_curl_cffi:
response = curl_cffi.get(f"{cls.url}/api/models") response = curl_cffi.get(f"{cls.url}/api/models")
if response.ok: if response.ok:
@ -97,34 +154,106 @@ class Qwen(AsyncGeneratorProvider, ProviderModelMixin):
return cls.models return cls.models
@classmethod @classmethod
async def prepare_files(cls, media, chat_type="")->list: async def prepare_files(cls, media, session: aiohttp.ClientSession, headers=None) -> list:
if headers is None:
headers = {}
files = [] files = []
for _file, file_name in media: for index, (_file, file_name) in enumerate(media):
file_type, _ = mimetypes.guess_type(file_name)
file_class: Literal["default", "vision", "video", "audio", "document"] = "default"
_type: Literal["file", "image", "video", "audio"] = "file"
showType: Literal["file", "image", "video", "audio"] = "file"
if isinstance(_file, str) and _file.startswith('http'): data_bytes = to_bytes(_file)
if chat_type == "image_edit" or (file_type and file_type.startswith("image")): # Check Cache
file_class = "vision" hasher = hashlib.md5()
hasher.update(data_bytes)
image_hash = hasher.hexdigest()
file = ImagesCache.get(image_hash)
if cls.image_cache and file:
debug.log("Using cached image")
files.append(file)
continue
extension, file_type = detect_file_type(data_bytes)
file_name = file_name or f"file-{len(data_bytes)}{extension}"
file_size = len(data_bytes)
# Get File Url
async with session.post(
f'{cls.url}/api/v2/files/getstsToken',
json={"filename": file_name,
"filesize": file_size, "filetype": file_type},
headers=headers
) as r:
await raise_for_status(r, "Create file failed")
res_data = await r.json()
data = res_data.get("data")
if res_data["success"] is False:
raise RateLimitError(f"{data['code']}:{data['details']}")
file_url = data.get("file_url")
file_id = data.get("file_id")
# Put File into Url
str_date = datetime.datetime.now(datetime.UTC).strftime('%Y%m%dT%H%M%SZ')
headers = get_oss_headers('PUT', str_date, data, file_type)
async with session.put(
file_url.split("?")[0],
data=data_bytes,
headers=headers
) as response:
await raise_for_status(response)
file_class: Literal["default", "vision", "video", "audio", "document"]
_type: Literal["file", "image", "video", "audio"]
show_type: Literal["file", "image", "video", "audio"]
if "image" in file_type:
_type = "image" _type = "image"
if not file_type: show_type = "image"
# Try to infer from file extension, fallback to generic file_class = "vision"
ext = file_name.split('.')[-1].lower() if '.' in file_name else '' elif "video" in file_type:
file_type = mimetypes.types_map.get(f'.{ext}', 'application/octet-stream') _type = "video"
showType = "image" show_type = "video"
file_class = "video"
elif "audio" in file_type:
_type = "audio"
show_type = "audio"
file_class = "audio"
else:
_type = "file"
show_type = "file"
file_class = "document"
files.append( file = {
{
"type": _type, "type": _type,
"file": {
"created_at": int(time() * 1000),
"data": {},
"filename": file_name,
"hash": None,
"id": file_id,
"meta": {
"name": file_name, "name": file_name,
"size": file_size,
"content_type": file_type
},
"update_at": int(time() * 1000),
},
"id": file_id,
"url": file_url,
"name": file_name,
"collection_name": "",
"progress": 0,
"status": "uploaded",
"greenNet": "success",
"size": file_size,
"error": "",
"itemId": str(uuid.uuid4()),
"file_type": file_type, "file_type": file_type,
"showType": showType, "showType": show_type,
"file_class": file_class, "file_class": file_class,
"url": _file "uploadTaskId": str(uuid.uuid4())
} }
) ImagesCache[image_hash] = file
files.append(file)
return files return files
@classmethod @classmethod
@ -135,7 +264,6 @@ class Qwen(AsyncGeneratorProvider, ProviderModelMixin):
media: MediaListType = None, media: MediaListType = None,
conversation: JsonConversation = None, conversation: JsonConversation = None,
proxy: str = None, proxy: str = None,
timeout: int = 120,
stream: bool = True, stream: bool = True,
enable_thinking: bool = True, enable_thinking: bool = True,
chat_type: Literal[ chat_type: Literal[
@ -157,7 +285,7 @@ class Qwen(AsyncGeneratorProvider, ProviderModelMixin):
""" """
model_name = cls.get_model(model) model_name = cls.get_model(model)
token = kwargs.get("token")
headers = { headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36', 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36',
'Accept': '*/*', 'Accept': '*/*',
@ -169,13 +297,24 @@ class Qwen(AsyncGeneratorProvider, ProviderModelMixin):
'Sec-Fetch-Mode': 'cors', 'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin', 'Sec-Fetch-Site': 'same-origin',
'Connection': 'keep-alive', 'Connection': 'keep-alive',
'Authorization': 'Bearer', 'Authorization': f'Bearer {token}' if token else "Bearer",
'Source': 'web' 'Source': 'web'
} }
prompt = get_last_user_message(messages) prompt = get_last_user_message(messages)
_timeout = kwargs.get("timeout")
async with aiohttp.ClientSession(headers=headers) as session: if isinstance(_timeout, aiohttp.ClientTimeout):
timeout = _timeout
else:
total = float(_timeout) if isinstance(_timeout, (int, float)) else 5 * 60
timeout = aiohttp.ClientTimeout(total=total)
async with StreamSession(headers=headers) as session:
try:
async with session.get('https://chat.qwen.ai/api/v1/auths/', proxy=proxy) as user_info_res:
user_info_res.raise_for_status()
debug.log(await user_info_res.json())
except:
...
for attempt in range(5): for attempt in range(5):
try: try:
if not cls._midtoken: if not cls._midtoken:
@ -221,7 +360,8 @@ class Qwen(AsyncGeneratorProvider, ProviderModelMixin):
files = [] files = []
media = list(merge_media(media, messages)) media = list(merge_media(media, messages))
if media: if media:
files = await cls.prepare_files(media, chat_type=chat_type) files = await cls.prepare_files(media, session=session,
headers=req_headers)
msg_payload = { msg_payload = {
"stream": stream, "stream": stream,

170
g4f/Provider/Yupp.py
View file

@ -1,25 +1,26 @@
import asyncio
import hashlib import hashlib
import json import json
import os
import re
import time import time
import uuid import uuid
import re
import os
import asyncio
import aiohttp
from aiohttp import ClientResponseError
from ..typing import AsyncResult, Messages, Optional, Dict, Any, List import aiohttp
from .helper import get_last_user_message
from .yupp.models import YuppModelManager
from ..cookies import get_cookies
from ..debug import log
from ..errors import RateLimitError, ProviderException, MissingAuthError
from ..image import is_accepted_format, to_bytes
from ..providers.base_provider import AsyncGeneratorProvider, ProviderModelMixin from ..providers.base_provider import AsyncGeneratorProvider, ProviderModelMixin
from ..providers.response import Reasoning, PlainTextResponse, PreviewResponse, JsonConversation, ImageResponse, \ from ..providers.response import Reasoning, PlainTextResponse, PreviewResponse, JsonConversation, ImageResponse, \
ProviderInfo, FinishReason, JsonResponse ProviderInfo, FinishReason, JsonResponse
from ..errors import RateLimitError, ProviderException, MissingAuthError from ..requests.aiohttp import StreamSession
from ..cookies import get_cookies
from ..tools.auth import AuthManager from ..tools.auth import AuthManager
from ..tools.media import merge_media from ..tools.media import merge_media
from ..image import is_accepted_format, to_bytes from ..typing import AsyncResult, Messages, Optional, Dict, Any, List
from .yupp.models import YuppModelManager
from .helper import get_last_user_message
from ..debug import log
# Global variables to manage Yupp accounts # Global variables to manage Yupp accounts
YUPP_ACCOUNT = Dict[str, Any] YUPP_ACCOUNT = Dict[str, Any]
@ -29,20 +30,22 @@ account_rotation_lock = asyncio.Lock()
# Global variables to manage Yupp Image Cache # Global variables to manage Yupp Image Cache
ImagesCache: Dict[str, dict] = {} ImagesCache: Dict[str, dict] = {}
class YuppAccount: class YuppAccount:
"""Yupp account representation""" """Yupp account representation"""
def __init__(self, token: str, is_valid: bool = True, error_count: int = 0, last_used: float = 0): def __init__(self, token: str, is_valid: bool = True, error_count: int = 0, last_used: float = 0):
self.token = token self.token = token
self.is_valid = is_valid self.is_valid = is_valid
self.error_count = error_count self.error_count = error_count
self.last_used = last_used self.last_used = last_used
def load_yupp_accounts(tokens_str: str): def load_yupp_accounts(tokens_str: str):
"""Load Yupp accounts from token string""" """Load Yupp accounts from token string"""
global YUPP_ACCOUNTS global YUPP_ACCOUNTS
if not tokens_str: if not tokens_str:
return return
tokens = [token.strip() for token in tokens_str.split(',') if token.strip()] tokens = [token.strip() for token in tokens_str.split(',') if token.strip()]
YUPP_ACCOUNTS = [ YUPP_ACCOUNTS = [
{ {
@ -54,6 +57,7 @@ def load_yupp_accounts(tokens_str: str):
for token in tokens for token in tokens
] ]
def create_headers() -> Dict[str, str]: def create_headers() -> Dict[str, str]:
"""Create headers for requests""" """Create headers for requests"""
return { return {
@ -66,6 +70,7 @@ def create_headers() -> Dict[str, str]:
"Sec-Fetch-Site": "same-origin", "Sec-Fetch-Site": "same-origin",
} }
async def get_best_yupp_account() -> Optional[YUPP_ACCOUNT]: async def get_best_yupp_account() -> Optional[YUPP_ACCOUNT]:
"""Get the best available Yupp account using smart selection algorithm""" """Get the best available Yupp account using smart selection algorithm"""
max_error_count = int(os.getenv("MAX_ERROR_COUNT", "3")) max_error_count = int(os.getenv("MAX_ERROR_COUNT", "3"))
@ -100,6 +105,7 @@ async def get_best_yupp_account() -> Optional[YUPP_ACCOUNT]:
account["last_used"] = now account["last_used"] = now
return account return account
async def claim_yupp_reward(session: aiohttp.ClientSession, account: YUPP_ACCOUNT, reward_id: str): async def claim_yupp_reward(session: aiohttp.ClientSession, account: YUPP_ACCOUNT, reward_id: str):
"""Claim Yupp reward asynchronously""" """Claim Yupp reward asynchronously"""
try: try:
@ -122,6 +128,7 @@ async def claim_yupp_reward(session: aiohttp.ClientSession, account: YUPP_ACCOUN
log_debug(f"Failed to claim reward {reward_id}. Error: {e}") log_debug(f"Failed to claim reward {reward_id}. Error: {e}")
return None return None
async def make_chat_private(session: aiohttp.ClientSession, account: YUPP_ACCOUNT, chat_id: str) -> bool: async def make_chat_private(session: aiohttp.ClientSession, account: YUPP_ACCOUNT, chat_id: str) -> bool:
"""Set a Yupp chat's sharing status to PRIVATE""" """Set a Yupp chat's sharing status to PRIVATE"""
try: try:
@ -159,6 +166,7 @@ async def make_chat_private(session: aiohttp.ClientSession, account: YUPP_ACCOUN
log_debug(f"Failed to make chat {chat_id} private: {e}") log_debug(f"Failed to make chat {chat_id} private: {e}")
return False return False
def log_debug(message: str): def log_debug(message: str):
"""Debug logging""" """Debug logging"""
if os.getenv("DEBUG_MODE", "false").lower() == "true": if os.getenv("DEBUG_MODE", "false").lower() == "true":
@ -166,6 +174,7 @@ def log_debug(message: str):
else: else:
log(f"[Yupp] {message}") log(f"[Yupp] {message}")
def format_messages_for_yupp(messages: Messages) -> str: def format_messages_for_yupp(messages: Messages) -> str:
"""Format multi-turn conversation for Yupp single-turn format""" """Format multi-turn conversation for Yupp single-turn format"""
if not messages: if not messages:
@ -202,6 +211,7 @@ def format_messages_for_yupp(messages: Messages) -> str:
return result return result
class Yupp(AsyncGeneratorProvider, ProviderModelMixin): class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
""" """
Yupp.ai Provider for g4f Yupp.ai Provider for g4f
@ -230,7 +240,8 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
cls.models_tags = {model.get("name"): manager.processor.generate_tags(model) for model in models} cls.models_tags = {model.get("name"): manager.processor.generate_tags(model) for model in models}
cls.models = [model.get("name") for model in models] cls.models = [model.get("name") for model in models]
cls.image_models = [model.get("name") for model in models if model.get("isImageGeneration")] cls.image_models = [model.get("name") for model in models if model.get("isImageGeneration")]
cls.vision_models = [model.get("name") for model in models if "image/*" in model.get("supportedAttachmentMimeTypes", [])] cls.vision_models = [model.get("name") for model in models if
"image/*" in model.get("supportedAttachmentMimeTypes", [])]
return cls.models return cls.models
@classmethod @classmethod
@ -322,7 +333,8 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
else: else:
prompt = get_last_user_message(messages, prompt) prompt = get_last_user_message(messages, prompt)
log_debug(f"Use url_uuid: {url_uuid}, Formatted prompt length: {len(prompt)}, Is new conversation: {is_new_conversation}") log_debug(
f"Use url_uuid: {url_uuid}, Formatted prompt length: {len(prompt)}, Is new conversation: {is_new_conversation}")
# Try all accounts with rotation # Try all accounts with rotation
max_attempts = len(YUPP_ACCOUNTS) max_attempts = len(YUPP_ACCOUNTS)
@ -332,10 +344,9 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
raise ProviderException("No valid Yupp accounts available") raise ProviderException("No valid Yupp accounts available")
try: try:
async with aiohttp.ClientSession() as session: async with StreamSession() as session:
turn_id = str(uuid.uuid4()) turn_id = str(uuid.uuid4())
# Handle media attachments # Handle media attachments
media = kwargs.get("media") media = kwargs.get("media")
if media: if media:
@ -390,16 +401,23 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
log_debug(f"Sending request to: {url}") log_debug(f"Sending request to: {url}")
log_debug(f"Payload structure: {type(payload)}, length: {len(str(payload))}") log_debug(f"Payload structure: {type(payload)}, length: {len(str(payload))}")
_timeout = kwargs.get("timeout")
if isinstance(_timeout, aiohttp.ClientTimeout):
timeout = _timeout
else:
total = float(_timeout) if isinstance(_timeout, (int, float)) else 5 * 60
timeout = aiohttp.ClientTimeout(total=total)
# Send request # Send request
async with session.post(url, json=payload, headers=headers, proxy=proxy) as response: async with session.post(url, json=payload, headers=headers, proxy=proxy,
timeout=timeout) as response:
response.raise_for_status() response.raise_for_status()
# Make chat private in background # Make chat private in background
asyncio.create_task(make_chat_private(session, account, url_uuid)) asyncio.create_task(make_chat_private(session, account, url_uuid))
# Process stream # Process stream
async for chunk in cls._process_stream_response(response.content, account, session, prompt, model): async for chunk in cls._process_stream_response(response.content, account, session, prompt,
model):
yield chunk yield chunk
return return
@ -417,7 +435,7 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
else: else:
account["error_count"] += 1 account["error_count"] += 1
continue continue
except ClientResponseError as e: except aiohttp.ClientResponseError as e:
log_debug(f"Account ...{account['token'][-4:]} failed: {str(e)}") log_debug(f"Account ...{account['token'][-4:]} failed: {str(e)}")
# No Available Yupp credits # No Available Yupp credits
if e.status == 500 and 'Internal Server Error' in e.message: if e.status == 500 and 'Internal Server Error' in e.message:
@ -466,10 +484,28 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
} }
# Holds leftStream / rightStream definitions to determine target/variant # Holds leftStream / rightStream definitions to determine target/variant
select_stream = [None, None] select_stream = [None, None]
# State for capturing a multi-line <think> + <yapp> block (fa-style)
capturing_ref_id: Optional[str] = None
capturing_lines: List[bytes] = []
# Storage for special referenced blocks like $fa
think_blocks: Dict[str, str] = {}
image_blocks: Dict[str, str] = {}
def extract_ref_id(ref): def extract_ref_id(ref):
"""Extract ID from reference string, e.g., from '$@123' extract '123'""" """Extract ID from reference string, e.g., from '$@123' extract '123'"""
return ref[2:] if ref and isinstance(ref, str) and ref.startswith("$@") else None return ref[2:] if ref and isinstance(ref, str) and ref.startswith("$@") else None
def extract_ref_name(ref: str) -> Optional[str]:
"""Extract simple ref name from '$fa' → 'fa'"""
if not isinstance(ref, str):
return None
if ref.startswith("$@"):
return ref[2:]
if ref.startswith("$") and len(ref) > 1:
return ref[1:]
return None
def is_valid_content(content: str) -> bool: def is_valid_content(content: str) -> bool:
"""Check if content is valid""" """Check if content is valid"""
if not content or content in [None, "", "$undefined"]: if not content or content in [None, "", "$undefined"]:
@ -516,6 +552,26 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
normal_content += content normal_content += content
yield content yield content
def finalize_capture_block(ref_id: str, lines: List[bytes]):
"""Parse captured <think> + <yapp> block for a given ref ID."""
text = b"".join(lines).decode("utf-8", errors="ignore")
# Extract <think>...</think>
think_start = text.find("<think>")
think_end = text.find("</think>")
if think_start != -1 and think_end != -1 and think_end > think_start:
inner = text[think_start + len("<think>"):think_end].strip()
if inner:
think_blocks[ref_id] = inner
# Extract <yapp class="image-gen">...</yapp>
yapp_start = text.find('<yapp class="image-gen">')
if yapp_start != -1:
yapp_end = text.find("</yapp>", yapp_start)
if yapp_end != -1:
yapp_block = text[yapp_start:yapp_end + len("</yapp>")]
image_blocks[ref_id] = yapp_block
try: try:
line_count = 0 line_count = 0
quick_response_id = None quick_response_id = None
@ -531,9 +587,43 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
right_message_id = None right_message_id = None
nudge_new_chat_id = None nudge_new_chat_id = None
nudge_new_chat = False nudge_new_chat = False
async for line in response_content: async for line in response_content:
line_count += 1 line_count += 1
# If we are currently capturing a think/image block for some ref ID
if capturing_ref_id is not None:
capturing_lines.append(line)
# Check if this line closes the <yapp> block; after that, block is complete
if b"</yapp>" in line: # or b':{"curr"' in line:
# We may have trailing "2:{...}" after </yapp> on the same line
# Get id using re
idx = line.find(b"</yapp>")
suffix = line[idx + len(b"</yapp>"):]
# Finalize captured block for this ref ID
finalize_capture_block(capturing_ref_id, capturing_lines)
capturing_ref_id = None
capturing_lines = []
# If there is trailing content (e.g. '2:{"curr":"$fa"...}')
if suffix.strip():
# Process suffix as a new "line" in the same iteration
line = suffix
else:
# Nothing more on this line
continue
else:
# Still inside captured block; skip normal processing
continue
# Detect start of a <think> block assigned to a ref like 'fa:...<think>'
if b"<think>" in line:
m = line_pattern.match(line)
if m:
capturing_ref_id = m.group(1).decode()
capturing_lines = [line]
# Skip normal parsing; the rest of the block will be captured until </yapp>
continue
match = line_pattern.match(line) match = line_pattern.match(line)
if not match: if not match:
@ -542,6 +632,10 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
chunk_id, chunk_data = match.groups() chunk_id, chunk_data = match.groups()
chunk_id = chunk_id.decode() chunk_id = chunk_id.decode()
if nudge_new_chat_id and chunk_id == nudge_new_chat_id:
nudge_new_chat = chunk_data.decode()
continue
try: try:
data = json.loads(chunk_data) if chunk_data != b"{}" else {} data = json.loads(chunk_data) if chunk_data != b"{}" else {}
except json.JSONDecodeError: except json.JSONDecodeError:
@ -558,7 +652,8 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
left_stream = data.get("leftStream", {}) left_stream = data.get("leftStream", {})
right_stream = data.get("rightStream", {}) right_stream = data.get("rightStream", {})
if data.get("quickResponse", {}) != "$undefined": if data.get("quickResponse", {}) != "$undefined":
quick_response_id = extract_ref_id(data.get("quickResponse", {}).get("stream", {}).get("next")) quick_response_id = extract_ref_id(
data.get("quickResponse", {}).get("stream", {}).get("next"))
if data.get("turnId", {}) != "$undefined": if data.get("turnId", {}) != "$undefined":
turn_id = extract_ref_id(data.get("turnId", {}).get("next")) turn_id = extract_ref_id(data.get("turnId", {}).get("next"))
@ -600,6 +695,32 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
target_stream_id = extract_ref_id(data.get("next")) target_stream_id = extract_ref_id(data.get("next"))
content = data.get("curr", "") content = data.get("curr", "")
if content: if content:
# Handle special "$fa" / "$<id>" reference
ref_name = extract_ref_name(content)
if ref_name and (ref_name in think_blocks or ref_name in image_blocks):
# Thinking block
if ref_name in think_blocks:
t_text = think_blocks[ref_name]
if t_text:
reasoning = Reasoning(t_text)
# thinking_content += t_text
stream["thinking"].append(reasoning)
# yield reasoning
# Image-gen block
if ref_name in image_blocks:
img_block_text = image_blocks[ref_name]
async for chunk in process_content_chunk(
img_block_text,
ref_name,
line_count,
for_target=True
):
stream["target"].append(chunk)
is_started = True
yield chunk
else:
# Normal textual chunk
async for chunk in process_content_chunk( async for chunk in process_content_chunk(
content, content,
chunk_id, chunk_id,
@ -651,8 +772,6 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
... ...
elif chunk_id == left_message_id: elif chunk_id == left_message_id:
... ...
elif chunk_id == nudge_new_chat_id:
nudge_new_chat = data
# Miscellaneous extra content # Miscellaneous extra content
elif isinstance(data, dict) and "curr" in data: elif isinstance(data, dict) and "curr" in data:
content = data.get("curr", "") content = data.get("curr", "")
@ -675,7 +794,6 @@ class Yupp(AsyncGeneratorProvider, ProviderModelMixin):
yield PreviewResponse(variant_text) yield PreviewResponse(variant_text)
yield JsonResponse(**stream) yield JsonResponse(**stream)
log_debug(f"Finished processing {line_count} lines") log_debug(f"Finished processing {line_count} lines")
except: except:
raise raise

2
g4f/Provider/needs_auth/LMArena.py
View file

@ -642,7 +642,7 @@ class LMArena(AsyncGeneratorProvider, ProviderModelMixin, AuthFileMixin):
if not cls._models_loaded: if not cls._models_loaded:
cls.get_models() cls.get_models()
is_image_model = model in image_models is_image_model = model in cls.image_models
if not model: if not model:
model = cls.default_model model = cls.default_model
if model in cls.model_aliases: if model in cls.model_aliases:

141
g4f/Provider/needs_auth/OpenaiChat.py
View file

@ -1,18 +1,20 @@
from __future__ import annotations from __future__ import annotations
import os
import re
import asyncio import asyncio
import uuid
import json
import base64 import base64
import time import hashlib
import json
import os
import random import random
from typing import AsyncIterator, Iterator, Optional, Generator, Dict, Union, List, Any import re
import time
import uuid
from copy import copy from copy import copy
from typing import AsyncIterator, Iterator, Optional, Generator, Dict, Union, List, Any
try: try:
import nodriver import nodriver
has_nodriver = True has_nodriver = True
except ImportError: except ImportError:
has_nodriver = False has_nodriver = False
@ -22,15 +24,17 @@ from ...typing import AsyncResult, Messages, Cookies, MediaListType
from ...requests.raise_for_status import raise_for_status from ...requests.raise_for_status import raise_for_status
from ...requests import StreamSession from ...requests import StreamSession
from ...requests import get_nodriver_session from ...requests import get_nodriver_session
from ...image import ImageRequest, to_image, to_bytes, is_accepted_format, detect_file_type from ...image import ImageRequest, to_image, to_bytes, detect_file_type
from ...errors import MissingAuthError, NoValidHarFileError, ModelNotFoundError from ...errors import MissingAuthError, NoValidHarFileError, ModelNotFoundError
from ...providers.response import JsonConversation, FinishReason, SynthesizeData, AuthResult, ImageResponse, ImagePreview, ResponseType, JsonRequest, format_link from ...providers.response import JsonConversation, FinishReason, SynthesizeData, AuthResult, ImageResponse, \
ImagePreview, ResponseType, JsonRequest, format_link
from ...providers.response import TitleGeneration, RequestLogin, Reasoning from ...providers.response import TitleGeneration, RequestLogin, Reasoning
from ...tools.media import merge_media from ...tools.media import merge_media
from ..helper import format_cookies, format_media_prompt, to_string from ..helper import format_cookies, format_media_prompt, to_string
from ..openai.models import default_model, default_image_model, models, image_models, text_models, model_aliases from ..openai.models import default_model, default_image_model, models, image_models, text_models, model_aliases
from ..openai.har_file import get_request_config from ..openai.har_file import get_request_config
from ..openai.har_file import RequestConfig, arkReq, arkose_url, start_url, conversation_url, backend_url, prepare_url, backend_anon_url from ..openai.har_file import RequestConfig, arkReq, arkose_url, start_url, conversation_url, backend_url, prepare_url, \
backend_anon_url
from ..openai.proofofwork import generate_proof_token from ..openai.proofofwork import generate_proof_token
from ..openai.new import get_requirements_token, get_config from ..openai.new import get_requirements_token, get_config
from ... import debug from ... import debug
@ -87,6 +91,9 @@ UPLOAD_HEADERS = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36" "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
} }
ImagesCache: Dict[str, dict] = {}
class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin): class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
"""A class for creating and managing conversations with OpenAI chat service""" """A class for creating and managing conversations with OpenAI chat service"""
@ -95,6 +102,7 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
working = True working = True
active_by_default = True active_by_default = True
use_nodriver = True use_nodriver = True
image_cache = True
supports_gpt_4 = True supports_gpt_4 = True
supports_message_history = True supports_message_history = True
supports_system_message = True supports_system_message = True
@ -131,7 +139,7 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
session: StreamSession, session: StreamSession,
auth_result: AuthResult, auth_result: AuthResult,
media: MediaListType, media: MediaListType,
) -> list[ImageRequest]: ) -> List[ImageRequest]:
""" """
Upload an image to the service and get the download URL Upload an image to the service and get the download URL
@ -143,11 +151,20 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
Returns: Returns:
An ImageRequest object that contains the download URL, file name, and other data An ImageRequest object that contains the download URL, file name, and other data
""" """
async def upload_file(file, image_name=None):
async def upload_file(file, image_name=None) -> ImageRequest:
debug.log(f"Uploading file: {image_name}") debug.log(f"Uploading file: {image_name}")
file_data = {} file_data = {}
data_bytes = to_bytes(file) data_bytes = to_bytes(file)
# Check Cache
hasher = hashlib.md5()
hasher.update(data_bytes)
image_hash = hasher.hexdigest()
cache_file = ImagesCache.get(image_hash)
if cls.image_cache and file:
debug.log("Using cached image")
return ImageRequest(cache_file)
extension, mime_type = detect_file_type(data_bytes) extension, mime_type = detect_file_type(data_bytes)
if "image" in mime_type: if "image" in mime_type:
# Convert the image to a PIL Image object # Convert the image to a PIL Image object
@ -202,9 +219,10 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
await raise_for_status(response, "Get download url failed") await raise_for_status(response, "Get download url failed")
uploaded_data = await response.json() uploaded_data = await response.json()
file_data["download_url"] = uploaded_data["download_url"] file_data["download_url"] = uploaded_data["download_url"]
ImagesCache[image_hash] = file_data.copy()
return ImageRequest(file_data) return ImageRequest(file_data)
medias = [] medias: List["ImageRequest"] = []
for item in media: for item in media:
item = item if isinstance(item, tuple) else (item,) item = item if isinstance(item, tuple) else (item,)
__uploaded_media = await upload_file(*item) __uploaded_media = await upload_file(*item)
@ -242,7 +260,8 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
"id": str(uuid.uuid4()), "id": str(uuid.uuid4()),
"author": {"role": message["role"]}, "author": {"role": message["role"]},
"content": {"content_type": "text", "parts": [to_string(message["content"])]}, "content": {"content_type": "text", "parts": [to_string(message["content"])]},
"metadata": {"serialization_metadata": {"custom_symbol_offsets": []}, **({"system_hints": system_hints} if system_hints else {})}, "metadata": {"serialization_metadata": {"custom_symbol_offsets": []},
**({"system_hints": system_hints} if system_hints else {})},
"create_time": time.time(), "create_time": time.time(),
} for message in messages] } for message in messages]
# Check if there is an image response # Check if there is an image response
@ -283,7 +302,9 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
return messages return messages
@classmethod @classmethod
async def get_generated_image(cls, session: StreamSession, auth_result: AuthResult, element: Union[dict, str], prompt: str = None, conversation_id: str = None) -> ImagePreview|ImageResponse|None: async def get_generated_image(cls, session: StreamSession, auth_result: AuthResult, element: Union[dict, str],
prompt: str = None, conversation_id: str = None,
status: Optional[str] = None) -> ImagePreview | ImageResponse | None:
download_urls = [] download_urls = []
is_sediment = False is_sediment = False
if prompt is None: if prompt is None:
@ -319,7 +340,11 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
debug.error("OpenaiChat: Download image failed") debug.error("OpenaiChat: Download image failed")
debug.error(e) debug.error(e)
if download_urls: if download_urls:
return ImagePreview(download_urls, prompt, {"headers": auth_result.headers}) if is_sediment else ImageResponse(download_urls, prompt, {"headers": auth_result.headers}) # status = None, finished_successfully
if is_sediment and status is None:
return ImagePreview(download_urls, prompt, {"status": status, "headers": auth_result.headers})
else:
return ImageResponse(download_urls, prompt, {"status": status, "headers": auth_result.headers})
@classmethod @classmethod
async def create_authed( async def create_authed(
@ -446,7 +471,8 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
f"{cls.url}/backend-anon/sentinel/chat-requirements" f"{cls.url}/backend-anon/sentinel/chat-requirements"
if cls._api_key is None else if cls._api_key is None else
f"{cls.url}/backend-api/sentinel/chat-requirements", f"{cls.url}/backend-api/sentinel/chat-requirements",
json={"p": None if not getattr(auth_result, "proof_token", None) else get_requirements_token(getattr(auth_result, "proof_token", None))}, json={"p": None if not getattr(auth_result, "proof_token", None) else get_requirements_token(
getattr(auth_result, "proof_token", None))},
headers=cls._headers headers=cls._headers
) as response: ) as response:
if response.status in (401, 403): if response.status in (401, 403):
@ -491,7 +517,9 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
"system_hints": ["search"] if web_search else None, "system_hints": ["search"] if web_search else None,
"supports_buffering": True, "supports_buffering": True,
"supported_encodings": ["v1"], "supported_encodings": ["v1"],
"client_contextual_info":{"is_dark_mode":False,"time_since_loaded":random.randint(20, 500),"page_height":578,"page_width":1850,"pixel_ratio":1,"screen_height":1080,"screen_width":1920}, "client_contextual_info": {"is_dark_mode": False, "time_since_loaded": random.randint(20, 500),
"page_height": 578, "page_width": 1850, "pixel_ratio": 1,
"screen_height": 1080, "screen_width": 1920},
"paragen_cot_summary_display_override": "allow" "paragen_cot_summary_display_override": "allow"
} }
if temporary: if temporary:
@ -512,7 +540,8 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
new_messages = [] new_messages = []
else: else:
new_messages.append(message) new_messages.append(message)
data["messages"] = cls.create_messages(new_messages, image_requests, ["search"] if web_search else None) data["messages"] = cls.create_messages(new_messages, image_requests,
["search"] if web_search else None)
yield JsonRequest.from_dict(data) yield JsonRequest.from_dict(data)
headers = { headers = {
**cls._headers, **cls._headers,
@ -548,10 +577,12 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
if match.group(0) in matches: if match.group(0) in matches:
continue continue
matches.append(match.group(0)) matches.append(match.group(0))
generated_image = await cls.get_generated_image(session, auth_result, match.group(0), prompt) generated_image = await cls.get_generated_image(session, auth_result, match.group(0),
prompt)
if generated_image is not None: if generated_image is not None:
yield generated_image yield generated_image
async for chunk in cls.iter_messages_line(session, auth_result, line, conversation, sources, references): async for chunk in cls.iter_messages_line(session, auth_result, line, conversation, sources,
references):
if isinstance(chunk, str): if isinstance(chunk, str):
chunk = chunk.replace("\ue203", "").replace("\ue204", "").replace("\ue206", "") chunk = chunk.replace("\ue203", "").replace("\ue204", "").replace("\ue206", "")
buffer += chunk buffer += chunk
@ -582,9 +613,11 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
return f"![{reference.get('title', '')}]({reference.get('content_url')})" return f"![{reference.get('title', '')}]({reference.get('content_url')})"
if is_video_embedding: if is_video_embedding:
if reference.get("url", "") and reference.get("thumbnail_url", ""): if reference.get("url", "") and reference.get("thumbnail_url",
""):
return f"[![{reference.get('title', '')}]({reference['thumbnail_url']})]({reference['url']})" return f"[![{reference.get('title', '')}]({reference['thumbnail_url']})]({reference['url']})"
video_match = re.match(r"video\n(.*?)\nturn[0-9]+", match.group(0)) video_match = re.match(r"video\n(.*?)\nturn[0-9]+",
match.group(0))
if video_match: if video_match:
return video_match.group(1) return video_match.group(1)
return "" return ""
@ -612,7 +645,9 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
return "" return ""
sequence_content = match.group(1) sequence_content = match.group(1)
sequence_content = sequence_content.replace("\ue200", "").replace("\ue202", "\n").replace("\ue201", "") sequence_content = sequence_content.replace("\ue200", "").replace("\ue202",
"\n").replace(
"\ue201", "")
sequence_content = sequence_content.replace("navlist\n", "#### ") sequence_content = sequence_content.replace("navlist\n", "#### ")
# Handle search, news, view and image citations # Handle search, news, view and image citations
@ -623,12 +658,15 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
citation_replacer, citation_replacer,
sequence_content sequence_content
) )
sequence_content = re.sub(r'products\n(.*)', products_replacer, sequence_content) sequence_content = re.sub(r'products\n(.*)', products_replacer,
sequence_content = re.sub(r'product_entity\n\[".*","(.*)"\]', lambda x: x.group(1), sequence_content) sequence_content)
sequence_content = re.sub(r'product_entity\n\[".*","(.*)"\]',
lambda x: x.group(1), sequence_content)
return sequence_content return sequence_content
# process only completed sequences and do not touch start of next not completed sequence # process only completed sequences and do not touch start of next not completed sequence
buffer = re.sub(r'\ue200(.*?)\ue201', sequence_replacer, buffer, flags=re.DOTALL) buffer = re.sub(r'\ue200(.*?)\ue201', sequence_replacer, buffer,
flags=re.DOTALL)
if buffer.find(u"\ue200") != -1: # still have uncompleted sequence if buffer.find(u"\ue200") != -1: # still have uncompleted sequence
continue continue
@ -647,7 +685,8 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
if sources.list: if sources.list:
yield sources yield sources
if conversation.generated_images: if conversation.generated_images:
yield ImageResponse(conversation.generated_images.urls, conversation.prompt, {"headers": auth_result.headers}) yield ImageResponse(conversation.generated_images.urls, conversation.prompt,
{"headers": auth_result.headers})
conversation.generated_images = None conversation.generated_images = None
conversation.prompt = None conversation.prompt = None
if return_conversation: if return_conversation:
@ -667,7 +706,9 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
yield FinishReason(conversation.finish_reason) yield FinishReason(conversation.finish_reason)
@classmethod @classmethod
async def iter_messages_line(cls, session: StreamSession, auth_result: AuthResult, line: bytes, fields: Conversation, sources: OpenAISources, references: ContentReferences) -> AsyncIterator: async def iter_messages_line(cls, session: StreamSession, auth_result: AuthResult, line: bytes,
fields: Conversation, sources: OpenAISources,
references: ContentReferences) -> AsyncIterator:
if not line.startswith(b"data: "): if not line.startswith(b"data: "):
return return
elif line.startswith(b"data: [DONE]"): elif line.startswith(b"data: [DONE]"):
@ -706,7 +747,12 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
elif m.get("p") == "/message/metadata/image_gen_title": elif m.get("p") == "/message/metadata/image_gen_title":
fields.prompt = m.get("v") fields.prompt = m.get("v")
elif m.get("p") == "/message/content/parts/0/asset_pointer": elif m.get("p") == "/message/content/parts/0/asset_pointer":
generated_images = fields.generated_images = await cls.get_generated_image(session, auth_result, m.get("v"), fields.prompt, fields.conversation_id) status = next(filter(lambda x: x.get("p") == '/message/status', v), {}).get('v', None)
generated_images = fields.generated_images = await cls.get_generated_image(session, auth_result,
m.get("v"),
fields.prompt,
fields.conversation_id,
status)
if generated_images is not None: if generated_images is not None:
if buffer: if buffer:
yield buffer yield buffer
@ -735,34 +781,41 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
if match and m.get("o") == "append" and isinstance(m.get("v"), dict): if match and m.get("o") == "append" and isinstance(m.get("v"), dict):
idx = int(match.group(1)) idx = int(match.group(1))
references.merge_reference(idx, m.get("v")) references.merge_reference(idx, m.get("v"))
elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/fallback_items$", m.get("p")) and isinstance(m.get("v"), list): elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/fallback_items$",
m.get("p")) and isinstance(m.get("v"), list):
for link in m.get("v", []) or []: for link in m.get("v", []) or []:
sources.add_source(link) sources.add_source(link)
elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/items$", m.get("p")) and isinstance(m.get("v"), list): elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/items$",
m.get("p")) and isinstance(m.get("v"), list):
for link in m.get("v", []) or []: for link in m.get("v", []) or []:
sources.add_source(link) sources.add_source(link)
elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/refs$", m.get("p")) and isinstance(m.get("v"), list): elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/refs$",
m.get("p")) and isinstance(m.get("v"), list):
match = re.match(r"^/message/metadata/content_references/(\d+)/refs$", m.get("p")) match = re.match(r"^/message/metadata/content_references/(\d+)/refs$", m.get("p"))
if match: if match:
idx = int(match.group(1)) idx = int(match.group(1))
references.update_reference(idx, m.get("o"), "refs", m.get("v")) references.update_reference(idx, m.get("o"), "refs", m.get("v"))
elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/alt$", m.get("p")) and isinstance(m.get("v"), list): elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/alt$",
m.get("p")) and isinstance(m.get("v"), list):
match = re.match(r"^/message/metadata/content_references/(\d+)/alt$", m.get("p")) match = re.match(r"^/message/metadata/content_references/(\d+)/alt$", m.get("p"))
if match: if match:
idx = int(match.group(1)) idx = int(match.group(1))
references.update_reference(idx, m.get("o"), "alt", m.get("v")) references.update_reference(idx, m.get("o"), "alt", m.get("v"))
elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/prompt_text$", m.get("p")) and isinstance(m.get("v"), list): elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/prompt_text$",
m.get("p")) and isinstance(m.get("v"), list):
match = re.match(r"^/message/metadata/content_references/(\d+)/prompt_text$", m.get("p")) match = re.match(r"^/message/metadata/content_references/(\d+)/prompt_text$", m.get("p"))
if match: if match:
idx = int(match.group(1)) idx = int(match.group(1))
references.update_reference(idx, m.get("o"), "prompt_text", m.get("v")) references.update_reference(idx, m.get("o"), "prompt_text", m.get("v"))
elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/refs/\d+$", m.get("p")) and isinstance(m.get("v"), dict): elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/refs/\d+$",
m.get("p")) and isinstance(m.get("v"), dict):
match = re.match(r"^/message/metadata/content_references/(\d+)/refs/(\d+)$", m.get("p")) match = re.match(r"^/message/metadata/content_references/(\d+)/refs/(\d+)$", m.get("p"))
if match: if match:
reference_idx = int(match.group(1)) reference_idx = int(match.group(1))
ref_idx = int(match.group(2)) ref_idx = int(match.group(2))
references.update_reference(reference_idx, m.get("o"), "refs", m.get("v"), ref_idx) references.update_reference(reference_idx, m.get("o"), "refs", m.get("v"), ref_idx)
elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/images$", m.get("p")) and isinstance(m.get("v"), list): elif m.get("p") and re.match(r"^/message/metadata/content_references/\d+/images$",
m.get("p")) and isinstance(m.get("v"), list):
match = re.match(r"^/message/metadata/content_references/(\d+)/images$", m.get("p")) match = re.match(r"^/message/metadata/content_references/(\d+)/images$", m.get("p"))
if match: if match:
idx = int(match.group(1)) idx = int(match.group(1))
@ -785,7 +838,8 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
fields.recipient = m.get("recipient", fields.recipient) fields.recipient = m.get("recipient", fields.recipient)
if fields.recipient == "all": if fields.recipient == "all":
c = m.get("content", {}) c = m.get("content", {})
if c.get("content_type") == "text" and m.get("author", {}).get("role") == "tool" and "initial_text" in m.get("metadata", {}): if c.get("content_type") == "text" and m.get("author", {}).get(
"role") == "tool" and "initial_text" in m.get("metadata", {}):
fields.is_thinking = True fields.is_thinking = True
yield Reasoning(status=m.get("metadata", {}).get("initial_text")) yield Reasoning(status=m.get("metadata", {}).get("initial_text"))
# if c.get("content_type") == "multimodal_text": # if c.get("content_type") == "multimodal_text":
@ -858,6 +912,7 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
async def nodriver_auth(cls, proxy: str = None): async def nodriver_auth(cls, proxy: str = None):
async with get_nodriver_session(proxy=proxy) as browser: async with get_nodriver_session(proxy=proxy) as browser:
page = await browser.get(cls.url) page = await browser.get(cls.url)
def on_request(event: nodriver.cdp.network.RequestWillBeSent, page=None): def on_request(event: nodriver.cdp.network.RequestWillBeSent, page=None):
if event.request.url == start_url or event.request.url.startswith(conversation_url): if event.request.url == start_url or event.request.url.startswith(conversation_url):
if cls.request_config.headers is None: if cls.request_config.headers is None:
@ -867,7 +922,8 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
elif event.request.url in (backend_url, backend_anon_url): elif event.request.url in (backend_url, backend_anon_url):
if "OpenAI-Sentinel-Proof-Token" in event.request.headers: if "OpenAI-Sentinel-Proof-Token" in event.request.headers:
cls.request_config.proof_token = json.loads(base64.b64decode( cls.request_config.proof_token = json.loads(base64.b64decode(
event.request.headers["OpenAI-Sentinel-Proof-Token"].split("gAAAAAB", 1)[-1].split("~")[0].encode() event.request.headers["OpenAI-Sentinel-Proof-Token"].split("gAAAAAB", 1)[-1].split("~")[
0].encode()
).decode()) ).decode())
if "OpenAI-Sentinel-Turnstile-Token" in event.request.headers: if "OpenAI-Sentinel-Turnstile-Token" in event.request.headers:
cls.request_config.turnstile_token = event.request.headers["OpenAI-Sentinel-Turnstile-Token"] cls.request_config.turnstile_token = event.request.headers["OpenAI-Sentinel-Turnstile-Token"]
@ -881,6 +937,7 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
arkBody=event.request.post_data, arkBody=event.request.post_data,
userAgent=event.request.headers.get("User-Agent") userAgent=event.request.headers.get("User-Agent")
) )
await page.send(nodriver.cdp.network.enable()) await page.send(nodriver.cdp.network.enable())
page.add_handler(nodriver.cdp.network.RequestWillBeSent, on_request) page.add_handler(nodriver.cdp.network.RequestWillBeSent, on_request)
await page.reload() await page.reload()
@ -970,11 +1027,14 @@ class OpenaiChat(AsyncAuthedProvider, ProviderModelMixin):
if cls._cookies: if cls._cookies:
cls._headers["cookie"] = format_cookies(cls._cookies) cls._headers["cookie"] = format_cookies(cls._cookies)
class Conversation(JsonConversation): class Conversation(JsonConversation):
""" """
Class to encapsulate response fields. Class to encapsulate response fields.
""" """
def __init__(self, conversation_id: str = None, message_id: str = None, user_id: str = None, finish_reason: str = None, parent_message_id: str = None, is_thinking: bool = False):
def __init__(self, conversation_id: str = None, message_id: str = None, user_id: str = None,
finish_reason: str = None, parent_message_id: str = None, is_thinking: bool = False):
self.conversation_id = conversation_id self.conversation_id = conversation_id
self.message_id = message_id self.message_id = message_id
self.finish_reason = finish_reason self.finish_reason = finish_reason
@ -987,6 +1047,7 @@ class Conversation(JsonConversation):
self.prompt = None self.prompt = None
self.generated_images: ImagePreview = None self.generated_images: ImagePreview = None
def get_cookies( def get_cookies(
urls: Optional[Iterator[str]] = None urls: Optional[Iterator[str]] = None
) -> Generator[Dict, Dict, Dict[str, str]]: ) -> Generator[Dict, Dict, Dict[str, str]]:
@ -1000,6 +1061,7 @@ def get_cookies(
json = yield cmd_dict json = yield cmd_dict
return {c["name"]: c["value"] for c in json['cookies']} if 'cookies' in json else {} return {c["name"]: c["value"] for c in json['cookies']} if 'cookies' in json else {}
class OpenAISources(ResponseType): class OpenAISources(ResponseType):
list: List[Dict[str, str]] list: List[Dict[str, str]]
@ -1085,6 +1147,7 @@ class OpenAISources(ResponseType):
return None return None
class ContentReferences: class ContentReferences:
def __init__(self) -> None: def __init__(self) -> None:
self.list: List[Dict[str, Any]] = [] self.list: List[Dict[str, Any]] = []

9
g4f/image/__init__.py
View file

@ -9,6 +9,8 @@ from pathlib import Path
from typing import Optional from typing import Optional
from urllib.parse import urlparse from urllib.parse import urlparse
import requests
try: try:
from PIL import Image, ImageOps from PIL import Image, ImageOps
has_requirements = True has_requirements = True
@ -383,6 +385,13 @@ def to_bytes(image: ImageType) -> bytes:
return Path(path).read_bytes() return Path(path).read_bytes()
else: else:
raise FileNotFoundError(f"File not found: {path}") raise FileNotFoundError(f"File not found: {path}")
else:
resp = requests.get(image, headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36 Edg/137.0.0.0",
})
if resp.ok and is_accepted_format(resp.content):
return resp.content
raise ValueError("Invalid image url. Expected bytes, str, or PIL Image.")
else: else:
raise ValueError("Invalid image format. Expected bytes, str, or PIL Image.") raise ValueError("Invalid image format. Expected bytes, str, or PIL Image.")
elif isinstance(image, Image.Image): elif isinstance(image, Image.Image):

12
g4f/requests/aiohttp.py
View file

@ -31,17 +31,21 @@ class StreamResponse(ClientResponse):
except json.JSONDecodeError: except json.JSONDecodeError:
continue continue
class StreamSession(): class StreamSession:
def __init__( def __init__(
self, self,
headers: dict = {}, headers=None,
timeout: int = None, timeout: int = None,
connector: BaseConnector = None, connector: BaseConnector = None,
proxy: str = None, proxy: str = None,
proxies: dict = {}, proxies=None,
impersonate = None, impersonate = None,
**kwargs **kwargs
): ):
if proxies is None:
proxies = {}
if headers is None:
headers = {}
if impersonate: if impersonate:
headers = { headers = {
**DEFAULT_HEADERS, **DEFAULT_HEADERS,
@ -49,7 +53,7 @@ class StreamSession():
} }
connect = None connect = None
if isinstance(timeout, tuple): if isinstance(timeout, tuple):
connect, timeout = timeout; connect, timeout = timeout
if timeout is not None: if timeout is not None:
timeout = ClientTimeout(timeout, connect) timeout = ClientTimeout(timeout, connect)
if proxy is None: if proxy is None: