From 8ef5207a172e0b3251d1d944564d7538f49ca7cc Mon Sep 17 00:00:00 2001 From: abc <98614666+xtekky@users.noreply.github.com> Date: Fri, 16 Aug 2024 22:25:38 +0200 Subject: update huggingface provider --- g4f/Provider/HuggingChat.py | 127 ++++++++++++++++++++------------------------ g4f/models.py | 3 ++ 2 files changed, 60 insertions(+), 70 deletions(-) diff --git a/g4f/Provider/HuggingChat.py b/g4f/Provider/HuggingChat.py index f7c6b581..c130d183 100644 --- a/g4f/Provider/HuggingChat.py +++ b/g4f/Provider/HuggingChat.py @@ -33,80 +33,78 @@ class HuggingChat(AbstractProvider, ProviderModelMixin): model: str, messages: Messages, stream: bool, - **kwargs - ) -> CreateResult: + **kwargs) -> CreateResult: if (model in cls.models) : - session = requests.Session() - headers = { - 'accept' : '*/*', - 'accept-language' : 'en,fr-FR;q=0.9,fr;q=0.8,es-ES;q=0.7,es;q=0.6,en-US;q=0.5,am;q=0.4,de;q=0.3', - '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="8", "Chromium";v="126", "Google Chrome";v="126"', - 'sec-ch-ua-mobile' : '?0', + session = cf_reqs.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/126.0.0.0 Safari/537.36', + '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', } + print(model) json_data = { - 'searchEnabled' : True, - 'activeModel' : 'CohereForAI/c4ai-command-r-plus', # doesn't matter - 'hideEmojiOnSidebar': False, - 'customPrompts' : {}, - 'assistants' : [], - 'tools' : {}, - 'disableStream' : False, - 'recentlySaved' : False, - 'ethicsModalAccepted' : True, - 'ethicsModalAcceptedAt' : None, - 'shareConversationsWithModelAuthors': False, + 'model': model, } - response = cf_reqs.post('https://huggingface.co/chat/settings', headers=headers, json=json_data) - session.cookies.update(response.cookies) - - response = session.post('https://huggingface.co/chat/conversation', - headers=headers, json={'model': model}) - + response = session.post('https://huggingface.co/chat/conversation', json=json_data) conversationId = response.json()['conversationId'] - response = session.get(f'https://huggingface.co/chat/conversation/{conversationId}/__data.json?x-sveltekit-invalidated=11', - headers=headers, - ) - messageId = extract_id(response.json()) + response = session.get(f'https://huggingface.co/chat/conversation/{conversationId}/__data.json?x-sveltekit-invalidated=01',) + + data: list = (response.json())["nodes"][1]["data"] + keys: list[int] = data[data[0]["messages"]] + message_keys: dict = data[keys[0]] + messageId: str = data[message_keys["id"]] settings = { - "inputs" : format_prompt(messages), - "id" : messageId, - "is_retry" : False, - "is_continue" : False, - "web_search" : False, - - # TODO // add feature to enable/disable tools - "tools": { - "websearch" : True, - "document_parser" : False, - "query_calculator" : False, - "image_generation" : False, - "image_editing" : False, - "fetch_url" : False, - } + "inputs":format_prompt(messages), + "id":messageId, + "is_retry":False, + "is_continue":False, + "web_search":False, + "tools":[] } - payload = { - "data": json.dumps(settings), + 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 = session.post(f"https://huggingface.co/chat/conversation/{conversationId}", - headers=headers, data=payload, stream=True, + response = requests.post(f'https://huggingface.co/chat/conversation/{conversationId}', + cookies=session.cookies, + headers=headers, + files=files, ) first_token = True @@ -125,18 +123,7 @@ class HuggingChat(AbstractProvider, ProviderModelMixin): else: token = token.replace('\u0000', '') - yield token + yield (token) elif line["type"] == "finalAnswer": - break - -def extract_id(response: dict) -> str: - data = response["nodes"][1]["data"] - uuid_pattern = re.compile( - r"^[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}$" - ) - for item in data: - if type(item) == str and uuid_pattern.match(item): - return item - - return None + break \ No newline at end of file diff --git a/g4f/models.py b/g4f/models.py index b6b54792..b6c5fd14 100644 --- a/g4f/models.py +++ b/g4f/models.py @@ -508,6 +508,9 @@ class ModelUtils: 'llama-3-70b-instruct': llama_3_70b_instruct, 'llama-3-70b-chat': llama_3_70b_chat_hf, 'llama-3-70b-instruct': llama_3_70b_instruct, + + 'llama-3.1-70b': llama_3_1_70b_instruct, + 'llama-3.1-405b': llama_3_1_405b_instruct_FP8, 'llama-3.1-70b-instruct': llama_3_1_70b_instruct, 'llama-3.1-405b-instruct': llama_3_1_405b_instruct_FP8, -- cgit v1.2.3