From b198d900aa37ee1c4682d852234da632a9f49c8f Mon Sep 17 00:00:00 2001 From: kqlio67 <166700875+kqlio67@users.noreply.github.com> Date: Thu, 5 Dec 2024 00:07:59 +0000 Subject: update providers and documentation with image handling improvements (#2451) * refactor(g4f/Provider/Airforce.py): Enhance Airforce provider with dynamic model fetching * refactor(g4f/Provider/Blackbox.py): Enhance Blackbox AI provider configuration and streamline code * feat(g4f/Provider/RobocodersAPI.py): Add RobocodersAPI new async chat provider * refactor(g4f/client/__init__.py): Improve provider handling in async_generate method * refactor(g4f/models.py): Update provider configurations for multiple models * refactor(g4f/Provider/Blackbox.py): Streamline model configuration and improve response handling * feat(g4f/Provider/DDG.py): Enhance model support and improve conversation handling * refactor(g4f/Provider/Copilot.py): Enhance Copilot provider with model support * refactor(g4f/Provider/AmigoChat.py): update models and improve code structure * chore(g4f/Provider/not_working/AIUncensored.): move AIUncensored to not_working directory * chore(g4f/Provider/not_working/Allyfy.py): remove Allyfy provider * Update (g4f/Provider/not_working/AIUncensored.py g4f/Provider/not_working/__init__.py) * refactor(g4f/Provider/ChatGptEs.py): Implement format_prompt for message handling * refactor(g4f/Provider/Blackbox.py): Update message formatting and improve code structure * refactor(g4f/Provider/LLMPlayground.py): Enhance text generation and error handling * refactor(g4f/Provider/needs_auth/PollinationsAI.py): move PollinationsAI to needs_auth directory * refactor(g4f/Provider/Liaobots.py): Update Liaobots provider models and aliases * feat(g4f/Provider/DeepInfraChat.py): Add new DeepInfra models and aliases * Update (g4f/Provider/__init__.py) * Update (g4f/models.py) * g4f/models.py * Update g4f/models.py * Update g4f/Provider/LLMPlayground.py * Update (g4f/models.py g4f/Provider/Airforce.py g4f/Provider/__init__.py g4f/Provider/LLMPlayground.py) * Update g4f/Provider/__init__.py * refactor(g4f/Provider/Airforce.py): Enhance text generation with retry and timeout * Update g4f/Provider/AmigoChat.py g4f/Provider/__init__.py * refactor(g4f/Provider/Blackbox.py): update model prefixes and image handling Fixes #2445 - Update model prefixes for gpt-4o, gemini-pro, and claude-sonnet-3.5 - Add 'gpt-3.5-turbo' alias for 'blackboxai' model - Modify image handling in create_async_generator method - Add 'imageGenerationMode' and 'webSearchModePrompt' flags to API request - Remove redundant 'imageBase64' field from image data structure * New provider (g4f/Provider/Blackbox2.py) Support for model llama-3.1-70b text generation * docs(docs/async_client.md): update AsyncClient API guide with minor improvements - Improve formatting and readability of code examples - Add line breaks for better visual separation of sections - Fix minor typos and inconsistencies in text - Enhance clarity of explanations in various sections - Remove unnecessary whitespace * feat(docs/client.md): add response_format parameter - Add 'response_format' parameter to image generation examples - Specify 'url' format for standard image generation - Include 'b64_json' format for base64 encoded image response - Update documentation to reflect new parameter usage - Improve code examples for clarity and consistency * docs(README.md): update usage examples and add image generation - Update text generation example to use new Client API - Add image generation example with Client API - Update configuration section with new cookie setting instructions - Add response_format parameter to image generation example - Remove outdated information and reorganize sections - Update contributors list * refactor(g4f/client/__init__.py): optimize image processing and response handling - Modify _process_image_response to handle 'url' format without local saving - Update ImagesResponse construction to include 'created' timestamp - Simplify image processing logic for different response formats - Improve error handling and logging for image generation - Enhance type hints and docstrings for better code clarity * feat(g4f/models.py): update model providers and add new models - Add Blackbox2 to Provider imports - Update gpt-3.5-turbo best provider to Blackbox - Add Blackbox2 to llama-3.1-70b best providers - Rename dalle_3 to dall_e_3 and update its best providers - Add new models: solar_mini, openhermes_2_5, lfm_40b, zephyr_7b, neural_7b, mythomax_13b - Update ModelUtils.convert with new models and changes - Remove duplicate 'dalle-3' entry in ModelUtils.convert * refactor(Airforce): improve API handling and add authentication - Implement API key authentication with check_api_key method - Refactor image generation to use new imagine2 endpoint - Improve text generation with better error handling and streaming - Update model aliases and add new image models - Enhance content filtering for various model outputs - Replace StreamSession with aiohttp's ClientSession for async operations - Simplify model fetching logic and remove redundant code - Add is_image_model method for better model type checking - Update class attributes for better organization and clarity * feat(g4f/Provider/HuggingChat.py): update HuggingChat model list and aliases Request by @TheFirstNoob - Add 'Qwen/Qwen2.5-72B-Instruct' as the first model in the list - Update model aliases to include 'qwen-2.5-72b' - Reorder existing models in the list for consistency - Remove duplicate entry for 'Qwen/Qwen2.5-72B-Instruct' in models list * refactor(g4f/Provider/ReplicateHome.py): remove unused text models Request by @TheFirstNoob - Removed the 'meta/meta-llama-3-70b-instruct' and 'mistralai/mixtral-8x7b-instruct-v0.1' text models from the list - Updated the list to only include the remaining text and image models - This change simplifies the model configuration and reduces the number of available models, focusing on the core text and image models provided by Replicate * refactor(g4f/Provider/HuggingChat.py): Move HuggingChat to needs_auth directory Request by @TheFirstNoob * Update (g4f/Provider/needs_auth/HuggingChat.py) * Update g4f/models.py * Update g4f/Provider/Airforce.py * Update g4f/models.py g4f/Provider/needs_auth/HuggingChat.py * Added 'Airforce' provider to the 'o1-mini' model (g4f/models.py) * Update (g4f/Provider/Airforce.py g4f/Provider/AmigoChat.py) * Update g4f/models.py g4f/Provider/DeepInfraChat.py g4f/Provider/Airforce.py * Update g4f/Provider/DeepInfraChat.py * Update (g4f/Provider/DeepInfraChat.py) * Update g4f/Provider/Blackbox.py * Update (docs/client.md docs/async_client.md g4f/client/__init__.py) * Update (docs/async_client.md docs/client.md) * Update (g4f/client/__init__.py) --------- Co-authored-by: kqlio67 Co-authored-by: kqlio67 <> Co-authored-by: H Lohaus --- g4f/Provider/needs_auth/HuggingChat.py | 179 +++++++++++++++++++++++++++++++++ 1 file changed, 179 insertions(+) create mode 100644 g4f/Provider/needs_auth/HuggingChat.py (limited to 'g4f/Provider/needs_auth/HuggingChat.py') diff --git a/g4f/Provider/needs_auth/HuggingChat.py b/g4f/Provider/needs_auth/HuggingChat.py new file mode 100644 index 00000000..dfdd9579 --- /dev/null +++ b/g4f/Provider/needs_auth/HuggingChat.py @@ -0,0 +1,179 @@ +from __future__ import annotations + +import json +import requests + +try: + from curl_cffi.requests import Session + has_curl_cffi = True +except ImportError: + has_curl_cffi = False +from ...typing import CreateResult, Messages +from ...errors import MissingRequirementsError +from ...requests.raise_for_status import raise_for_status +from ..base_provider import ProviderModelMixin, AbstractProvider +from ..helper import format_prompt + +class HuggingChat(AbstractProvider, ProviderModelMixin): + url = "https://huggingface.co/chat" + working = True + supports_stream = True + needs_auth = True + default_model = "meta-llama/Meta-Llama-3.1-70B-Instruct" + + models = [ + 'Qwen/Qwen2.5-72B-Instruct', + 'meta-llama/Meta-Llama-3.1-70B-Instruct', + 'CohereForAI/c4ai-command-r-plus-08-2024', + 'Qwen/QwQ-32B-Preview', + 'nvidia/Llama-3.1-Nemotron-70B-Instruct-HF', + 'Qwen/Qwen2.5-Coder-32B-Instruct', + 'meta-llama/Llama-3.2-11B-Vision-Instruct', + 'NousResearch/Hermes-3-Llama-3.1-8B', + 'mistralai/Mistral-Nemo-Instruct-2407', + 'microsoft/Phi-3.5-mini-instruct', + ] + + model_aliases = { + "qwen-2.5-72b": "Qwen/Qwen2.5-72B-Instruct", + "llama-3.1-70b": "meta-llama/Meta-Llama-3.1-70B-Instruct", + "command-r-plus": "CohereForAI/c4ai-command-r-plus-08-2024", + "qwq-32b": "Qwen/QwQ-32B-Preview", + "nemotron-70b": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", + "qwen-2.5-coder-32b": "Qwen/Qwen2.5-Coder-32B-Instruct", + "llama-3.2-11b": "meta-llama/Llama-3.2-11B-Vision-Instruct", + "hermes-3": "NousResearch/Hermes-3-Llama-3.1-8B", + "mistral-nemo": "mistralai/Mistral-Nemo-Instruct-2407", + "phi-3.5-mini": "microsoft/Phi-3.5-mini-instruct", + } + + @classmethod + def create_completion( + cls, + model: str, + messages: Messages, + stream: bool, + **kwargs + ) -> CreateResult: + if not has_curl_cffi: + raise MissingRequirementsError('Install "curl_cffi" package | pip install -U curl_cffi') + model = cls.get_model(model) + + if model in cls.models: + session = Session() + session.headers = { + 'accept': '*/*', + 'accept-language': 'en', + 'cache-control': 'no-cache', + 'origin': 'https://huggingface.co', + 'pragma': 'no-cache', + 'priority': 'u=1, i', + 'referer': 'https://huggingface.co/chat/', + 'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"', + 'sec-ch-ua-mobile': '?0', + 'sec-ch-ua-platform': '"macOS"', + 'sec-fetch-dest': 'empty', + 'sec-fetch-mode': 'cors', + 'sec-fetch-site': 'same-origin', + 'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36', + } + json_data = { + 'model': model, + } + response = session.post('https://huggingface.co/chat/conversation', json=json_data) + raise_for_status(response) + + conversationId = response.json().get('conversationId') + + # Get the data response and parse it properly + response = session.get(f'https://huggingface.co/chat/conversation/{conversationId}/__data.json?x-sveltekit-invalidated=11') + raise_for_status(response) + + # Split the response content by newlines and parse each line as JSON + try: + json_data = None + for line in response.text.split('\n'): + if line.strip(): + try: + parsed = json.loads(line) + if isinstance(parsed, dict) and "nodes" in parsed: + json_data = parsed + break + except json.JSONDecodeError: + continue + + if not json_data: + raise RuntimeError("Failed to parse response data") + + data: list = json_data["nodes"][1]["data"] + keys: list[int] = data[data[0]["messages"]] + message_keys: dict = data[keys[0]] + messageId: str = data[message_keys["id"]] + + except (KeyError, IndexError, TypeError) as e: + raise RuntimeError(f"Failed to extract message ID: {str(e)}") + + settings = { + "inputs": format_prompt(messages), + "id": messageId, + "is_retry": False, + "is_continue": False, + "web_search": False, + "tools": [] + } + + headers = { + 'accept': '*/*', + 'accept-language': 'en', + 'cache-control': 'no-cache', + 'origin': 'https://huggingface.co', + 'pragma': 'no-cache', + 'priority': 'u=1, i', + 'referer': f'https://huggingface.co/chat/conversation/{conversationId}', + 'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"', + 'sec-ch-ua-mobile': '?0', + 'sec-ch-ua-platform': '"macOS"', + 'sec-fetch-dest': 'empty', + 'sec-fetch-mode': 'cors', + 'sec-fetch-site': 'same-origin', + 'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36', + } + + files = { + 'data': (None, json.dumps(settings, separators=(',', ':'))), + } + + response = requests.post( + f'https://huggingface.co/chat/conversation/{conversationId}', + cookies=session.cookies, + headers=headers, + files=files, + ) + raise_for_status(response) + + full_response = "" + for line in response.iter_lines(): + if not line: + continue + try: + line = json.loads(line) + except json.JSONDecodeError as e: + print(f"Failed to decode JSON: {line}, error: {e}") + continue + + if "type" not in line: + raise RuntimeError(f"Response: {line}") + + elif line["type"] == "stream": + token = line["token"].replace('\u0000', '') + full_response += token + if stream: + yield token + + elif line["type"] == "finalAnswer": + break + + full_response = full_response.replace('<|im_end|', '').replace('\u0000', '').strip() + + if not stream: + yield full_response -- cgit v1.2.3